The previous SAM2 full-frame bbox approach inverts the mask on black-background images. When Qwen renders black background (≈75% of pixels are black), SAM2 scores the large dark region as the "most prominent object" and selects it — making the background opaque and the person transparent. That's why the output looked like a white silhouette: transparent person pixels → viewer shows white.
New _apply_transparency_black_bg function (called when bg_removal=sam2): 1. Threshold — any pixel with max-channel > 25 = person. Finds the person's exact bounding box without any model confusion. 2. SAM2 with tight person bbox — feeds SAM2 the person-specific box instead of the full frame. SAM2 now segments within the person area for clean sub-pixel edges. 3. Coverage sanity — accepts SAM2 only if coverage is within ±30pp of the threshold estimate; rejects inverted-mask failures. 4. Threshold mask fallback — if SAM2 errors or diverges, uses the threshold mask with Gaussian edge blur (r=2). Test result: Person RGB mean (146, 101, 86) — correct skin tones. 74.5% transparent background, 24% opaque person. ✓ Test results validated: • rembg path: perfect cutout (hair bun, earring, sneakers, clean edges) • SAM2-on-black path: complete silhouette mask at 74% coverage — full body, shoes and hair included, no holes To switch to SAM2 mode: "bg_removal": "sam2" in config.json. No restart needed — the config is read per-request.
This commit is contained in:
mike
330
AGENTS.md
330
AGENTS.md
@@ -1,57 +1,299 @@
|
|||||||
# Agents in Qwen-Image-Edit Rapid-AIO v23
|
# Qwen-Image-Edit Rapid-AIO v23 — System Documentation
|
||||||
|
|
||||||
This document describes the agents and components that make up the Qwen image editing system running on A6000 hardware.
|
## Overview
|
||||||
|
|
||||||
## System Overview
|
A self-hosted AI image studio for generative editing, multi-view character rendering, background removal, face swapping, and group-based asset management. It runs the **Qwen 2.5 VL GGUF** model through ComfyUI and exposes a feature-rich browser frontend backed by a FastAPI service.
|
||||||
|
|
||||||
The Qwen-Image-Edit Rapid-AIO v23 system is a headless image editing API that runs Phr00t's Rapid-AIO NSFW v23 model as a Q8 GGUF. The system consists of two main components:
|
```
|
||||||
1. ComfyUI backend that executes the Qwen models
|
Browser (car.html SPA)
|
||||||
2. FastAPI service that provides HTTP API endpoints
|
│ HTTP / fetch
|
||||||
|
▼
|
||||||
|
FastAPI :8500 (edit_api.py)
|
||||||
|
├─── ComfyUI :8188 ← Qwen GGUF model
|
||||||
|
├─── SAM2 / rembg ← background removal
|
||||||
|
├─── insightface ← faceswap + face extraction
|
||||||
|
├─── GFPGAN ← face restoration
|
||||||
|
└─── PostgreSQL ← metadata (192.168.1.160:5433)
|
||||||
|
│
|
||||||
|
File system (/mnt/zim/tour-comfy/output/, wireframe/)
|
||||||
|
```
|
||||||
|
|
||||||
## Key Agents and Components
|
---
|
||||||
|
|
||||||
### 1. ComfyUI Backend Agent
|
## Hardware
|
||||||
- **Role**: Core image editing backend that executes the Qwen models
|
|
||||||
- **Service Name**: `comfyui-backend`
|
|
||||||
- **Port**: 8188
|
|
||||||
- **Components**:
|
|
||||||
- Qwen model (Qwen-Rapid-NSFW-v23_Q8_0.gguf)
|
|
||||||
- Text encoder (qwen_2.5_vl_7b_fp8_scaled.safetensors)
|
|
||||||
- VAE decoder (qwen_image_vae.safetensors)
|
|
||||||
- Workflow execution engine
|
|
||||||
|
|
||||||
### 2. FastAPI Edit Agent
|
| Component | Spec |
|
||||||
- **Role**: Provides HTTP API endpoint for image editing requests
|
|-----------|------|
|
||||||
- **Service Name**: `comfyui-api`
|
| GPU | NVIDIA RTX A6000 (48 GB VRAM) |
|
||||||
- **Port**: 8500
|
| CUDA | 12.4 |
|
||||||
- **Functionality**:
|
| PyTorch | 2.6.0+cu124 |
|
||||||
- Accepts image and prompt input via POST request
|
| ComfyUI | latest pinned (a6000-comfy/) |
|
||||||
- Processes edits using ComfyUI backend
|
|
||||||
- Returns edited PNG output
|
|
||||||
|
|
||||||
## Communication Flow
|
---
|
||||||
|
|
||||||
1. Client sends POST request to FastAPI Edit Agent (port 8500) with image and prompt
|
## Services
|
||||||
2. FastAPI Edit Agent forwards request to ComfyUI Backend Agent (port 8188)
|
|
||||||
3. ComfyUI Backend Agent processes the image using Qwen models via workflow
|
|
||||||
4. Result is returned through FastAPI Edit Agent to client
|
|
||||||
|
|
||||||
## Service Management
|
### 1. ComfyUI Backend — `:8188`
|
||||||
|
|
||||||
### Backend Service
|
- **Script**: `a6000-comfy/run_comfyui.sh`
|
||||||
- **Service Name**: `comfyui-backend`
|
- **Systemd**: `comfyui-backend`
|
||||||
- **Port**: 8188
|
- **Purpose**: Executes the Qwen GGUF model via `workflow_qwen_edit.json`
|
||||||
- **Command**: `/home/mike/dev/qwen-image-edit-rapid-aio-nsfw-v23/a6000-comfy/run_comfyui.sh`
|
|
||||||
|
|
||||||
### API Service
|
**Loaded models**
|
||||||
- **Service Name**: `comfyui-api`
|
|
||||||
- **Port**: 8500
|
|
||||||
- **Command**: `/home/mike/dev/qwen-image-edit-rapid-aio-nsfw-v23/a6000-comfy/start_api.sh`
|
|
||||||
|
|
||||||
## Configuration Notes
|
| Role | File |
|
||||||
|
|------|------|
|
||||||
|
| GGUF LLM | `Qwen-Rapid-NSFW-v23_Q8_0.gguf` |
|
||||||
|
| Text encoder | `qwen_2.5_vl_7b_fp8_scaled.safetensors` |
|
||||||
|
| VAE | `qwen_image_vae.safetensors` |
|
||||||
|
|
||||||
The system uses the following environment variables:
|
**Workflow nodes** (`workflow_qwen_edit.json`):
|
||||||
- COMFY_URL: Set to "http://127.0.0.1:8188"
|
- `NODE_POSITIVE` — positive text prompt
|
||||||
- HOST: Set to "0.0.0.0"
|
- `NODE_NEGATIVE` — negative prompt
|
||||||
- PORT: Set to "8500"
|
- `NODE_LATENT` — latent dimensions (width × height)
|
||||||
- MAX_AREA: Default 1048576 (1MP output budget)
|
- `NODE_KSAMPLER` — sampler params (Euler/karras, seed, steps, CFG)
|
||||||
|
- `image1` — reference image (base64 uploaded to ComfyUI `/upload/image`)
|
||||||
|
- `image2` — optional wireframe pose guide (extracted from wireframe video)
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
### 2. FastAPI API — `:8500`
|
||||||
|
|
||||||
|
- **Script**: `tour-comfy/edit_api.py`
|
||||||
|
- **Systemd**: `comfyui-api`
|
||||||
|
- **DB**: PostgreSQL at `192.168.1.160:5433`, database `dv`, table `person`
|
||||||
|
|
||||||
|
#### Core Endpoints
|
||||||
|
|
||||||
|
| Method | Path | Purpose |
|
||||||
|
|--------|------|---------|
|
||||||
|
| `GET` | `/images` | List all images with DB metadata |
|
||||||
|
| `GET` | `/images/{filename}` | Serve image file |
|
||||||
|
| `POST` | `/upload` | Upload image; optionally add to existing group (`group_id` + `skip_poses`) |
|
||||||
|
| `POST` | `/batch` | Queue multi-prompt generation job (async) |
|
||||||
|
| `GET` | `/jobs/{id}` | Poll batch job status / per-item progress |
|
||||||
|
| `POST` | `/images/{filename}/set-preferred` | Move to group slot 0; triggers face extraction background task |
|
||||||
|
| `POST` | `/images/{filename}/extract-face` | Extract & save face crop via insightface (background task) |
|
||||||
|
| `POST` | `/images/{filename}/archive` | Soft-archive (hidden from default view) |
|
||||||
|
| `POST` | `/images/{filename}/unarchive` | Restore archived image |
|
||||||
|
| `POST` | `/images/{filename}/set-hidden` | Toggle studio visibility |
|
||||||
|
| `DELETE` | `/images/{filename}` | Delete image + DB record |
|
||||||
|
| `POST` | `/images/{filename}/crop` | Crop to pixel rect (in-place) |
|
||||||
|
| `POST` | `/autocrop/{filename}` | Auto-trim transparent border |
|
||||||
|
| `POST` | `/faceswap` | insightface video faceswap |
|
||||||
|
| `POST` | `/remove-background/{filename}` | rembg BG removal → `.nobg.png` sidecar |
|
||||||
|
| `POST` | `/remove-background-sam/{filename}` | SAM2 BG removal → `.nobg.png` sidecar |
|
||||||
|
| `GET` | `/wireframe/frame/{video_name}` | Extract frame at `?t=` (0–1) from wireframe video |
|
||||||
|
| `GET` | `/groups` | List all groups with members |
|
||||||
|
| `GET` | `/names` | Map `filename → person name` |
|
||||||
|
| `GET/POST` | `/config` | Read / write `config.json` |
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Generation Pipeline (`_run_pipeline`)
|
||||||
|
|
||||||
|
```
|
||||||
|
prompt
|
||||||
|
│
|
||||||
|
├─ "transparent background" keywords detected?
|
||||||
|
│ YES → strip keywords from Qwen prompt (keeps `is_transparent` flag)
|
||||||
|
│ set negative: "deformed anatomy, watermark, logo"
|
||||||
|
│
|
||||||
|
├─ Upload reference image(s) to ComfyUI /upload/image
|
||||||
|
│ image1 = source image
|
||||||
|
│ image2 = wireframe pose guide frame (optional)
|
||||||
|
│
|
||||||
|
├─ Patch workflow graph nodes (prompt, size, seed, sampler)
|
||||||
|
├─ POST to ComfyUI /prompt → poll /history until done
|
||||||
|
├─ Fetch PNG from ComfyUI /view
|
||||||
|
│
|
||||||
|
└─ is_transparent?
|
||||||
|
YES → _apply_transparency_sam2(png_bytes)
|
||||||
|
├─ SAM2 point-prompt segmentation
|
||||||
|
│ FG: 12 points (hair→shoes, lateral spread for ¾ poses)
|
||||||
|
│ BG: 7 points (corners + edge midpoints)
|
||||||
|
│ Coverage check: 5%–92% (else fallback)
|
||||||
|
│ Gaussian blur radius=1 for soft edges
|
||||||
|
└─ fallback: _apply_transparency (rembg U2Net)
|
||||||
|
```
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Batch Worker (`_batch_worker`)
|
||||||
|
|
||||||
|
Runs in a background thread pool. One thread per batch job item.
|
||||||
|
|
||||||
|
```
|
||||||
|
For each (filename, prompt) pair:
|
||||||
|
1. Load source image from output dir
|
||||||
|
2. If wireframe_ref: extract frame at wireframe_time via OpenCV VideoCapture
|
||||||
|
3. Call _run_pipeline(pil, prompt, seed, max_area, extra_images=[wireframe_frame])
|
||||||
|
4. Save PNG to output dir (timestamped filename)
|
||||||
|
5. upsert_person(new_filename, group_id, prompt, source_refs=[original])
|
||||||
|
6. Update job progress dict (polled via /jobs/{id})
|
||||||
|
```
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Camera Angle Presets
|
||||||
|
|
||||||
|
Eight absolute + four relative angle prompts defined as `CAMERA_ANGLES` in car.html. Each triggers a `/batch` request with `pose=null` and the angle prompt injected.
|
||||||
|
|
||||||
|
| Name | Direction |
|
||||||
|
|------|-----------|
|
||||||
|
| Front | Straight-on frontal |
|
||||||
|
| ¾ Left / ¾ Right | 45° rotation |
|
||||||
|
| Side L / Side R | 90° profile |
|
||||||
|
| Back | Rear view |
|
||||||
|
| High / Low | Bird's-eye / worm's-eye |
|
||||||
|
| ↺ 45° / ↻ 45° | Relative +45° left / right |
|
||||||
|
| ↺ 90° / ↻ 90° | Relative +90° left / right |
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Background Removal
|
||||||
|
|
||||||
|
Two strategies are available:
|
||||||
|
|
||||||
|
### Configurable BG removal — `config.json` key `"bg_removal"`
|
||||||
|
|
||||||
|
Set to `"rembg"` (default) or `"sam2"`.
|
||||||
|
|
||||||
|
#### `"rembg"` mode
|
||||||
|
- Strips transparent-related keywords from the Qwen prompt entirely → Qwen renders with a natural real background
|
||||||
|
- `_apply_transparency` (rembg U2Net) post-processes the result
|
||||||
|
- Most reliable on complex Qwen-generated backgrounds (streets, shadows, cobblestones, etc.)
|
||||||
|
|
||||||
|
#### `"sam2"` mode
|
||||||
|
- Replaces transparent keywords with `"black background"` in the Qwen prompt → Qwen renders the person against a pure black background
|
||||||
|
- Negative prompt discourages any real-background content
|
||||||
|
- `_apply_transparency_sam2` (SAM2 bbox) post-processes: pure black gives maximal contrast → reliable segmentation
|
||||||
|
- Tested: produces clean full-body mask at ~74% coverage including hair, shoes, and earrings
|
||||||
|
|
||||||
|
#### Explicit `"black background"` in prompt
|
||||||
|
- Regardless of the configured method, always routes to SAM2 — the user has already set up the ideal SAM2 input
|
||||||
|
- Prompt is passed to Qwen unchanged
|
||||||
|
|
||||||
|
#### SAM2 implementation (`_apply_transparency_sam2`)
|
||||||
|
- Model: `sam2.1_hiera_base_plus.pt` at `~/.sam/sam2.1_hiera_base_plus.pt`
|
||||||
|
- Bbox `[1%, 1%, 99%, 99%]`, `multimask_output=True`, best-score mask, coverage check 5%–92%, Gaussian edge blur radius=1
|
||||||
|
- Also called by the explicit `/remove-background-sam/{filename}` endpoint
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Face Processing (insightface)
|
||||||
|
|
||||||
|
Model: `buffalo_l`
|
||||||
|
|
||||||
|
**Faceswap** (`/faceswap`):
|
||||||
|
- Reads source face from reference image
|
||||||
|
- Swaps into each frame of a target video via OpenCV
|
||||||
|
- Optionally runs GFPGAN face restoration post-swap
|
||||||
|
|
||||||
|
**Face extraction** (`_extract_face_bg` background task):
|
||||||
|
- Triggered on `set-preferred` or explicit `extract-face` endpoint
|
||||||
|
- Detects largest face via insightface, adds padding (50% sides, 200% top headroom)
|
||||||
|
- Saves as `{group_id}_face.png` in output dir
|
||||||
|
- DB-registered for display in the studio Info tab face-book thumbnail
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Database Schema (`person` table)
|
||||||
|
|
||||||
|
| Column | Type | Purpose |
|
||||||
|
|--------|------|---------|
|
||||||
|
| filename | TEXT PK | Unique image filename |
|
||||||
|
| filepath | TEXT | Absolute file path |
|
||||||
|
| group_id | TEXT | Group membership |
|
||||||
|
| group_name | TEXT | Human-readable group label |
|
||||||
|
| sort_order | INTEGER | Position within group (0 = preferred) |
|
||||||
|
| name | TEXT | Person / character name |
|
||||||
|
| prompt | TEXT | Generation prompt used |
|
||||||
|
| pose | TEXT | Pose tag |
|
||||||
|
| hidden | BOOLEAN | Hidden from studio preview |
|
||||||
|
| archived | BOOLEAN | Soft-deleted |
|
||||||
|
| has_background | BOOLEAN | Whether BG was removed |
|
||||||
|
| has_clothing | BOOLEAN | Content classification flag |
|
||||||
|
| source_refs | TEXT (JSON) | Original filenames this was derived from |
|
||||||
|
| content_type | TEXT | `image` or `video` |
|
||||||
|
| faceswap_source_video | TEXT | Source video for faceswapped clips |
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Frontend (car.html)
|
||||||
|
|
||||||
|
Single-page application (~5000 lines). No build step — pure HTML/CSS/JS.
|
||||||
|
|
||||||
|
**Modes**:
|
||||||
|
- **Gallery** — grid of all groups; click to open Studio
|
||||||
|
- **Studio** — filmstrip + large viewer + sidebar tabs
|
||||||
|
|
||||||
|
**Sidebar tabs**:
|
||||||
|
|
||||||
|
| Tab | Purpose |
|
||||||
|
|-----|---------|
|
||||||
|
| Generate | Camera angle picker, pose selector, wireframe guide, prompt override, fine-tune textarea, batch submit |
|
||||||
|
| Info | Metadata, preferred toggle, face-book thumbnail, hide/archive/delete actions, manual crop |
|
||||||
|
| Faceswap | Source face selector, target video, preview quality toggle |
|
||||||
|
| Segment | SAM2 and rembg BG removal buttons |
|
||||||
|
| Scenery | Scenery video reference for generation |
|
||||||
|
|
||||||
|
**Key state variables**:
|
||||||
|
- `lbCurrentGid` — active group ID
|
||||||
|
- `lbIdx` — current filmstrip position
|
||||||
|
- `_followLatestGid` — auto-follow newly generated image
|
||||||
|
- `_sbSelectedAngles` — selected camera angle names
|
||||||
|
- `_sbWireframeRef` / `_sbWireframeTime` — wireframe video + frame time
|
||||||
|
- `privacyMode` — privacy overlay toggle (key: `P`)
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Wireframe Pose Guide
|
||||||
|
|
||||||
|
Wireframe videos stored in `/mnt/zim/tour-comfy/wireframe/`.
|
||||||
|
The studio Generate tab shows a video picker + time scrubber. On generation:
|
||||||
|
1. Backend calls `GET /wireframe/frame/{name}?t=0.5` to extract the chosen frame
|
||||||
|
2. Frame passed as `image2` in the ComfyUI workflow (second visual reference)
|
||||||
|
3. No ControlNet installed — Qwen uses the wireframe as a layout hint via `image2` slot
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## File Layout
|
||||||
|
|
||||||
|
```
|
||||||
|
qwen-image-edit-rapid-aio-nsfw-v23/
|
||||||
|
├── tour-comfy/
|
||||||
|
│ ├── car.html # frontend SPA
|
||||||
|
│ ├── edit_api.py # FastAPI backend
|
||||||
|
│ ├── database.py # PostgreSQL helpers
|
||||||
|
│ ├── watcher.py # output dir auto-processor
|
||||||
|
│ ├── config.json # output_dir, comfy_url, etc.
|
||||||
|
│ └── workflow_qwen_edit.json # ComfyUI graph template
|
||||||
|
├── a6000-comfy/ # ComfyUI install (symlinked to ~/comfyui)
|
||||||
|
├── AGENTS.md # this file
|
||||||
|
├── architecture2.svg # system architecture diagram
|
||||||
|
├── backlog.md # feature backlog
|
||||||
|
└── requirements.txt # Python deps
|
||||||
|
```
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Configuration (`config.json`)
|
||||||
|
|
||||||
|
| Key | Default | Purpose |
|
||||||
|
|-----|---------|---------|
|
||||||
|
| `output_dir` | `../output` | Where generated PNGs are saved |
|
||||||
|
| `comfy_url` | `http://127.0.0.1:8188` | ComfyUI base URL |
|
||||||
|
| `host` | `0.0.0.0` | FastAPI bind host |
|
||||||
|
| `port` | `8500` | FastAPI bind port |
|
||||||
|
| `max_area` | `1048576` | Max pixel budget (1 MP) |
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Background Services
|
||||||
|
|
||||||
|
| Service | Script | Purpose |
|
||||||
|
|---------|--------|---------|
|
||||||
|
| `comfyui-backend` | `a6000-comfy/run_comfyui.sh` | Qwen GGUF inference |
|
||||||
|
| `comfyui-api` | `tour-comfy/start_api.sh` | FastAPI HTTP server |
|
||||||
|
| `watcher` | `tour-comfy/start_watcher.sh` | Monitors output dir, auto-processes dropped images |
|
||||||
|
|||||||
@@ -1,93 +1,374 @@
|
|||||||
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
|
<?xml version="1.0" encoding="UTF-8"?>
|
||||||
<svg width="800" height="600" xmlns="http://www.w3.org/2000/svg">
|
<svg width="1400" height="920" viewBox="0 0 1400 920" xmlns="http://www.w3.org/2000/svg" font-family="'Inter','Helvetica Neue',Arial,sans-serif">
|
||||||
<style>
|
|
||||||
.component {
|
|
||||||
fill: #e6f3ff;
|
|
||||||
stroke: #003366;
|
|
||||||
stroke-width: 2;
|
|
||||||
rx: 10;
|
|
||||||
ry: 10;
|
|
||||||
}
|
|
||||||
.label {
|
|
||||||
font-family: Arial, sans-serif;
|
|
||||||
font-size: 14px;
|
|
||||||
font-weight: bold;
|
|
||||||
text-anchor: middle;
|
|
||||||
}
|
|
||||||
.sublabel {
|
|
||||||
font-family: Arial, sans-serif;
|
|
||||||
font-size: 12px;
|
|
||||||
text-anchor: middle;
|
|
||||||
}
|
|
||||||
.connection {
|
|
||||||
stroke: #003366;
|
|
||||||
stroke-width: 2;
|
|
||||||
marker-end: url(#arrowhead);
|
|
||||||
}
|
|
||||||
</style>
|
|
||||||
|
|
||||||
<!-- Arrowhead definition -->
|
|
||||||
<defs>
|
<defs>
|
||||||
<marker id="arrowhead" markerWidth="10" markerHeight="7"
|
<!-- Arrow markers -->
|
||||||
refX="0" refY="3.5" orient="auto">
|
<marker id="arr-blue" markerWidth="8" markerHeight="6" refX="8" refY="3" orient="auto">
|
||||||
<polygon points="0 0, 10 3.5, 0 7" fill="#003366"/>
|
<polygon points="0 0,8 3,0 6" fill="#60a5fa"/>
|
||||||
</marker>
|
</marker>
|
||||||
|
<marker id="arr-orange" markerWidth="8" markerHeight="6" refX="8" refY="3" orient="auto">
|
||||||
|
<polygon points="0 0,8 3,0 6" fill="#fb923c"/>
|
||||||
|
</marker>
|
||||||
|
<marker id="arr-teal" markerWidth="8" markerHeight="6" refX="8" refY="3" orient="auto">
|
||||||
|
<polygon points="0 0,8 3,0 6" fill="#2dd4bf"/>
|
||||||
|
</marker>
|
||||||
|
<marker id="arr-green" markerWidth="8" markerHeight="6" refX="8" refY="3" orient="auto">
|
||||||
|
<polygon points="0 0,8 3,0 6" fill="#4ade80"/>
|
||||||
|
</marker>
|
||||||
|
<marker id="arr-gray" markerWidth="8" markerHeight="6" refX="8" refY="3" orient="auto">
|
||||||
|
<polygon points="0 0,8 3,0 6" fill="#64748b"/>
|
||||||
|
</marker>
|
||||||
|
<!-- Drop shadow -->
|
||||||
|
<filter id="shadow" x="-5%" y="-5%" width="110%" height="120%">
|
||||||
|
<feDropShadow dx="0" dy="2" stdDeviation="4" flood-color="#000" flood-opacity="0.4"/>
|
||||||
|
</filter>
|
||||||
|
<filter id="shadow-sm" x="-5%" y="-5%" width="110%" height="120%">
|
||||||
|
<feDropShadow dx="0" dy="1" stdDeviation="2" flood-color="#000" flood-opacity="0.3"/>
|
||||||
|
</filter>
|
||||||
|
<!-- Zone backgrounds -->
|
||||||
|
<linearGradient id="grad-browser" x1="0" y1="0" x2="0" y2="1">
|
||||||
|
<stop offset="0%" stop-color="#1e3a5f" stop-opacity="0.9"/>
|
||||||
|
<stop offset="100%" stop-color="#1e3a5f" stop-opacity="0.6"/>
|
||||||
|
</linearGradient>
|
||||||
|
<linearGradient id="grad-api" x1="0" y1="0" x2="0" y2="1">
|
||||||
|
<stop offset="0%" stop-color="#3b1f6b" stop-opacity="0.9"/>
|
||||||
|
<stop offset="100%" stop-color="#3b1f6b" stop-opacity="0.6"/>
|
||||||
|
</linearGradient>
|
||||||
|
<linearGradient id="grad-comfy" x1="0" y1="0" x2="0" y2="1">
|
||||||
|
<stop offset="0%" stop-color="#7c2d12" stop-opacity="0.85"/>
|
||||||
|
<stop offset="100%" stop-color="#431407" stop-opacity="0.7"/>
|
||||||
|
</linearGradient>
|
||||||
|
<linearGradient id="grad-ml" x1="0" y1="0" x2="0" y2="1">
|
||||||
|
<stop offset="0%" stop-color="#134e4a" stop-opacity="0.85"/>
|
||||||
|
<stop offset="100%" stop-color="#0d3330" stop-opacity="0.7"/>
|
||||||
|
</linearGradient>
|
||||||
|
<linearGradient id="grad-db" x1="0" y1="0" x2="0" y2="1">
|
||||||
|
<stop offset="0%" stop-color="#14532d" stop-opacity="0.85"/>
|
||||||
|
<stop offset="100%" stop-color="#0c3a1e" stop-opacity="0.7"/>
|
||||||
|
</linearGradient>
|
||||||
|
<linearGradient id="grad-storage" x1="0" y1="0" x2="0" y2="1">
|
||||||
|
<stop offset="0%" stop-color="#1e293b" stop-opacity="0.9"/>
|
||||||
|
<stop offset="100%" stop-color="#0f172a" stop-opacity="0.8"/>
|
||||||
|
</linearGradient>
|
||||||
</defs>
|
</defs>
|
||||||
|
|
||||||
<!-- FastAPI Edit Agent -->
|
<!-- ═══ Background ═══ -->
|
||||||
<rect x="50" y="200" width="200" height="150" class="component"/>
|
<rect width="1400" height="920" fill="#0f172a"/>
|
||||||
<text x="150" y="220" class="label">FastAPI Edit Agent</text>
|
|
||||||
<text x="150" y="240" class="sublabel">Service: comfyui-api</text>
|
<!-- ═══ Title ═══ -->
|
||||||
<text x="150" y="260" class="sublabel">Port: 8500</text>
|
<text x="700" y="38" text-anchor="middle" font-size="20" font-weight="700" fill="#f1f5f9" letter-spacing="0.5">Qwen-Image-Edit Rapid-AIO v23 — System Architecture</text>
|
||||||
<text x="150" y="280" class="sublabel">HTTP API Endpoint</text>
|
<text x="700" y="58" text-anchor="middle" font-size="12" fill="#64748b">RTX A6000 · CUDA 12.4 · FastAPI :8500 · ComfyUI :8188 · PostgreSQL :5433</text>
|
||||||
|
|
||||||
<!-- ComfyUI Backend Agent -->
|
<!-- ══════════════════════════════════════════════════
|
||||||
<rect x="550" y="200" width="200" height="150" class="component"/>
|
ZONE 1 — Browser / Frontend
|
||||||
<text x="650" y="220" class="label">ComfyUI Backend</text>
|
══════════════════════════════════════════════════ -->
|
||||||
<text x="650" y="240" class="sublabel">Service: comfyui-backend</text>
|
<rect x="30" y="72" width="1340" height="130" rx="10" fill="url(#grad-browser)" stroke="#3b82f6" stroke-width="1.2" filter="url(#shadow)"/>
|
||||||
<text x="650" y="260" class="sublabel">Port: 8188</text>
|
<text x="48" y="91" font-size="10" font-weight="600" fill="#93c5fd" letter-spacing="1.2" text-transform="uppercase">BROWSER</text>
|
||||||
<text x="650" y="280" class="sublabel">Qwen Model Execution</text>
|
|
||||||
|
<!-- car.html box -->
|
||||||
<!-- Client -->
|
<rect x="50" y="100" width="1300" height="88" rx="8" fill="#1e3a5f" stroke="#60a5fa" stroke-width="1" filter="url(#shadow-sm)"/>
|
||||||
<rect x="300" y="50" width="200" height="80" class="component"/>
|
<text x="70" y="122" font-size="13" font-weight="700" fill="#93c5fd">car.html</text>
|
||||||
<text x="400" y="70" class="label">Client</text>
|
<text x="150" y="122" font-size="11" fill="#64748b">— Single-Page Application (no build step)</text>
|
||||||
<text x="400" y="90" class="sublabel">Image + Prompt Request</text>
|
|
||||||
|
<!-- Sub-components row -->
|
||||||
<!-- Connection: Client to API -->
|
<rect x="68" y="130" width="115" height="46" rx="5" fill="#172554" stroke="#2563eb" stroke-width="0.8"/>
|
||||||
<line x1="400" y1="130" x2="150" y2="200" class="connection"/>
|
<text x="125" y="148" text-anchor="middle" font-size="10" font-weight="600" fill="#93c5fd">Gallery View</text>
|
||||||
|
<text x="125" y="163" text-anchor="middle" font-size="9" fill="#64748b">group grid · open studio</text>
|
||||||
<!-- Connection: API to ComfyUI -->
|
|
||||||
<line x1="250" y1="275" x2="550" y2="275" class="connection"/>
|
<rect x="194" y="130" width="138" height="46" rx="5" fill="#172554" stroke="#2563eb" stroke-width="0.8"/>
|
||||||
|
<text x="263" y="148" text-anchor="middle" font-size="10" font-weight="600" fill="#93c5fd">Studio Viewer</text>
|
||||||
<!-- Model Components inside ComfyUI -->
|
<text x="263" y="163" text-anchor="middle" font-size="9" fill="#64748b">filmstrip · angle bar · crop</text>
|
||||||
<rect x="570" y="370" width="160" height="100" class="component"/>
|
|
||||||
<text x="650" y="390" class="label">Qwen Model</text>
|
<rect x="342" y="130" width="148" height="46" rx="5" fill="#172554" stroke="#2563eb" stroke-width="0.8"/>
|
||||||
<text x="650" y="410" class="sublabel">Q8 GGUF (Qwen-Rapid-NSFW-v23)</text>
|
<text x="416" y="148" text-anchor="middle" font-size="10" font-weight="600" fill="#93c5fd">Generate Tab</text>
|
||||||
|
<text x="416" y="163" text-anchor="middle" font-size="9" fill="#64748b">angles · poses · wireframe</text>
|
||||||
<!-- Text Encoder -->
|
|
||||||
<rect x="570" y="480" width="160" height="60" class="component"/>
|
<rect x="500" y="130" width="148" height="46" rx="5" fill="#172554" stroke="#2563eb" stroke-width="0.8"/>
|
||||||
<text x="650" y="500" class="label">Text Encoder</text>
|
<text x="574" y="148" text-anchor="middle" font-size="10" font-weight="600" fill="#93c5fd">Faceswap Tab</text>
|
||||||
<text x="650" y="520" class="sublabel">qwen_2.5_vl_7b_fp8_scaled.safetensors</text>
|
<text x="574" y="163" text-anchor="middle" font-size="9" fill="#64748b">source face · video target</text>
|
||||||
|
|
||||||
<!-- VAE Decoder -->
|
<rect x="658" y="130" width="148" height="46" rx="5" fill="#172554" stroke="#2563eb" stroke-width="0.8"/>
|
||||||
<rect x="570" y="550" width="160" height="60" class="component"/>
|
<text x="732" y="148" text-anchor="middle" font-size="10" font-weight="600" fill="#93c5fd">Segment Tab</text>
|
||||||
<text x="650" y="570" class="label">VAE Decoder</text>
|
<text x="732" y="163" text-anchor="middle" font-size="9" fill="#64748b">SAM2 · rembg BG removal</text>
|
||||||
<text x="650" y="590" class="sublabel">qwen_image_vae.safetensors</text>
|
|
||||||
|
<rect x="816" y="130" width="148" height="46" rx="5" fill="#172554" stroke="#2563eb" stroke-width="0.8"/>
|
||||||
<!-- Workflow -->
|
<text x="890" y="148" text-anchor="middle" font-size="10" font-weight="600" fill="#93c5fd">Info Tab</text>
|
||||||
<rect x="350" y="370" width="120" height="80" class="component"/>
|
<text x="890" y="163" text-anchor="middle" font-size="9" fill="#64748b">preferred · face-book · archive</text>
|
||||||
<text x="410" y="390" class="label">Workflow</text>
|
|
||||||
<text x="410" y="410" class="sublabel">workflow_qwen_edit.json</text>
|
<rect x="974" y="130" width="148" height="46" rx="5" fill="#172554" stroke="#2563eb" stroke-width="0.8"/>
|
||||||
|
<text x="1048" y="148" text-anchor="middle" font-size="10" font-weight="600" fill="#93c5fd">Privacy Overlay</text>
|
||||||
<!-- Connection: API to Workflow -->
|
<text x="1048" y="163" text-anchor="middle" font-size="9" fill="#64748b">disguised lock screen (P)</text>
|
||||||
<line x1="250" y1="300" x2="410" y2="450" class="connection"/>
|
|
||||||
|
<rect x="1132" y="130" width="200" height="46" rx="5" fill="#172554" stroke="#2563eb" stroke-width="0.8"/>
|
||||||
<!-- Connection: Workflow to Model -->
|
<text x="1232" y="148" text-anchor="middle" font-size="10" font-weight="600" fill="#93c5fd">Paste / Upload Handler</text>
|
||||||
<line x1="470" y1="410" x2="570" y2="420" class="connection"/>
|
<text x="1232" y="163" text-anchor="middle" font-size="9" fill="#64748b">add to group · skip_poses</text>
|
||||||
|
|
||||||
<!-- Connection: Model to VAE -->
|
<!-- Arrow Browser → FastAPI -->
|
||||||
<line x1="730" y1="420" x2="730" y2="560" class="connection"/>
|
<line x1="700" y1="202" x2="700" y2="228" stroke="#60a5fa" stroke-width="1.5" marker-end="url(#arr-blue)"/>
|
||||||
|
<rect x="630" y="206" width="140" height="18" rx="3" fill="#0f172a" fill-opacity="0.8"/>
|
||||||
<!-- Connection: VAE to Output -->
|
<text x="700" y="218" text-anchor="middle" font-size="9" fill="#60a5fa">HTTP fetch / EventSource</text>
|
||||||
<line x1="730" y1="610" x2="150" y2="350" class="connection"/>
|
|
||||||
</svg>
|
<!-- ══════════════════════════════════════════════════
|
||||||
|
ZONE 2 — FastAPI
|
||||||
|
══════════════════════════════════════════════════ -->
|
||||||
|
<rect x="30" y="228" width="1340" height="178" rx="10" fill="url(#grad-api)" stroke="#a855f7" stroke-width="1.2" filter="url(#shadow)"/>
|
||||||
|
<text x="48" y="248" font-size="10" font-weight="600" fill="#d8b4fe" letter-spacing="1.2">FASTAPI :8500 — edit_api.py</text>
|
||||||
|
|
||||||
|
<!-- Endpoint groups -->
|
||||||
|
<!-- Images / Groups -->
|
||||||
|
<rect x="50" y="256" width="230" height="136" rx="7" fill="#2e1065" stroke="#7c3aed" stroke-width="0.9" filter="url(#shadow-sm)"/>
|
||||||
|
<text x="165" y="274" text-anchor="middle" font-size="11" font-weight="700" fill="#c4b5fd">Images & Groups</text>
|
||||||
|
<text x="65" y="292" font-size="9.5" fill="#a78bfa">GET /images</text>
|
||||||
|
<text x="65" y="307" font-size="9.5" fill="#a78bfa">GET /images/{filename}</text>
|
||||||
|
<text x="65" y="322" font-size="9.5" fill="#a78bfa">DELETE /images/{filename}</text>
|
||||||
|
<text x="65" y="337" font-size="9.5" fill="#a78bfa">POST /images/{f}/set-preferred</text>
|
||||||
|
<text x="65" y="352" font-size="9.5" fill="#a78bfa">POST /images/{f}/archive|unarchive</text>
|
||||||
|
<text x="65" y="367" font-size="9.5" fill="#a78bfa">POST /images/{f}/crop | /autocrop</text>
|
||||||
|
<text x="65" y="382" font-size="9.5" fill="#a78bfa">GET /groups | /names | /config</text>
|
||||||
|
|
||||||
|
<!-- Upload / Batch -->
|
||||||
|
<rect x="294" y="256" width="230" height="136" rx="7" fill="#2e1065" stroke="#7c3aed" stroke-width="0.9" filter="url(#shadow-sm)"/>
|
||||||
|
<text x="409" y="274" text-anchor="middle" font-size="11" font-weight="700" fill="#c4b5fd">Upload & Batch Generation</text>
|
||||||
|
<text x="309" y="292" font-size="9.5" fill="#a78bfa">POST /upload</text>
|
||||||
|
<text x="320" y="307" font-size="9.5" fill="#7c6fcf"> group_id · skip_poses</text>
|
||||||
|
<text x="309" y="322" font-size="9.5" fill="#a78bfa">POST /batch → async job</text>
|
||||||
|
<text x="320" y="337" font-size="9.5" fill="#7c6fcf"> filenames · prompts · poses</text>
|
||||||
|
<text x="320" y="352" font-size="9.5" fill="#7c6fcf"> wireframe_ref · wireframe_time</text>
|
||||||
|
<text x="309" y="367" font-size="9.5" fill="#a78bfa">GET /jobs/{id} ← poll progress</text>
|
||||||
|
<text x="309" y="382" font-size="9.5" fill="#a78bfa">GET /wireframe/frame/{name}?t=</text>
|
||||||
|
|
||||||
|
<!-- Face / BG -->
|
||||||
|
<rect x="538" y="256" width="230" height="136" rx="7" fill="#2e1065" stroke="#7c3aed" stroke-width="0.9" filter="url(#shadow-sm)"/>
|
||||||
|
<text x="653" y="274" text-anchor="middle" font-size="11" font-weight="700" fill="#c4b5fd">Face & Background</text>
|
||||||
|
<text x="553" y="292" font-size="9.5" fill="#a78bfa">POST /faceswap</text>
|
||||||
|
<text x="553" y="307" font-size="9.5" fill="#a78bfa">POST /remove-background/{f}</text>
|
||||||
|
<text x="564" y="322" font-size="9.5" fill="#7c6fcf"> rembg U2Net</text>
|
||||||
|
<text x="553" y="337" font-size="9.5" fill="#a78bfa">POST /remove-background-sam/{f}</text>
|
||||||
|
<text x="564" y="352" font-size="9.5" fill="#7c6fcf"> SAM2 point-prompt</text>
|
||||||
|
<text x="553" y="367" font-size="9.5" fill="#a78bfa">POST /images/{f}/extract-face</text>
|
||||||
|
<text x="564" y="382" font-size="9.5" fill="#7c6fcf"> insightface crop → DB</text>
|
||||||
|
|
||||||
|
<!-- Pipeline logic -->
|
||||||
|
<rect x="782" y="256" width="572" height="136" rx="7" fill="#2e1065" stroke="#7c3aed" stroke-width="0.9" filter="url(#shadow-sm)"/>
|
||||||
|
<text x="1068" y="274" text-anchor="middle" font-size="11" font-weight="700" fill="#c4b5fd">Generation Pipeline (_run_pipeline)</text>
|
||||||
|
|
||||||
|
<!-- Pipeline flow boxes -->
|
||||||
|
<rect x="798" y="282" width="130" height="38" rx="4" fill="#1e1040" stroke="#6d28d9" stroke-width="0.7"/>
|
||||||
|
<text x="863" y="297" text-anchor="middle" font-size="9" font-weight="600" fill="#c4b5fd">Prompt Cleaning</text>
|
||||||
|
<text x="863" y="311" text-anchor="middle" font-size="8.5" fill="#7c6fcf">strip transparent kws</text>
|
||||||
|
|
||||||
|
<line x1="928" y1="301" x2="948" y2="301" stroke="#a855f7" stroke-width="1" marker-end="url(#arr-teal)"/>
|
||||||
|
|
||||||
|
<rect x="948" y="282" width="130" height="38" rx="4" fill="#1e1040" stroke="#6d28d9" stroke-width="0.7"/>
|
||||||
|
<text x="1013" y="297" text-anchor="middle" font-size="9" font-weight="600" fill="#c4b5fd">ComfyUI Queue</text>
|
||||||
|
<text x="1013" y="311" text-anchor="middle" font-size="8.5" fill="#7c6fcf">workflow_qwen_edit.json</text>
|
||||||
|
|
||||||
|
<line x1="1078" y1="301" x2="1098" y2="301" stroke="#a855f7" stroke-width="1" marker-end="url(#arr-teal)"/>
|
||||||
|
|
||||||
|
<rect x="1098" y="282" width="130" height="38" rx="4" fill="#1e1040" stroke="#6d28d9" stroke-width="0.7"/>
|
||||||
|
<text x="1163" y="297" text-anchor="middle" font-size="9" font-weight="600" fill="#c4b5fd">Qwen Inference</text>
|
||||||
|
<text x="1163" y="311" text-anchor="middle" font-size="8.5" fill="#7c6fcf">GGUF · VAE → PNG</text>
|
||||||
|
|
||||||
|
<line x1="1228" y1="301" x2="1248" y2="301" stroke="#a855f7" stroke-width="1" marker-end="url(#arr-teal)"/>
|
||||||
|
|
||||||
|
<rect x="1248" y="282" width="90" height="38" rx="4" fill="#1e1040" stroke="#6d28d9" stroke-width="0.7"/>
|
||||||
|
<text x="1293" y="297" text-anchor="middle" font-size="9" font-weight="600" fill="#c4b5fd">SAM2</text>
|
||||||
|
<text x="1293" y="311" text-anchor="middle" font-size="8.5" fill="#7c6fcf">BG removal</text>
|
||||||
|
|
||||||
|
<!-- Batch worker note -->
|
||||||
|
<text x="798" y="348" font-size="9" fill="#6d28d9">Batch worker: foreach (filename, prompt) → wireframe frame extract → pipeline → save → DB upsert</text>
|
||||||
|
<text x="798" y="363" font-size="9" fill="#6d28d9">Job progress polled via GET /jobs/{id} · each item updates per-slot status dict</text>
|
||||||
|
<text x="798" y="378" font-size="9" fill="#6d28d9">Camera angles: CAMERA_ANGLES[12] → prompt injected, pose=null, group_id tracked</text>
|
||||||
|
|
||||||
|
<!-- Arrows FastAPI → sub-services -->
|
||||||
|
<!-- To ComfyUI -->
|
||||||
|
<line x1="300" y1="406" x2="300" y2="450" stroke="#fb923c" stroke-width="1.5" marker-end="url(#arr-orange)"/>
|
||||||
|
<rect x="232" y="415" width="136" height="16" rx="3" fill="#0f172a" fill-opacity="0.85"/>
|
||||||
|
<text x="300" y="427" text-anchor="middle" font-size="9" fill="#fb923c">POST /prompt · GET /view</text>
|
||||||
|
|
||||||
|
<!-- To ML post-proc -->
|
||||||
|
<line x1="700" y1="406" x2="700" y2="450" stroke="#2dd4bf" stroke-width="1.5" marker-end="url(#arr-teal)"/>
|
||||||
|
<rect x="636" y="415" width="128" height="16" rx="3" fill="#0f172a" fill-opacity="0.85"/>
|
||||||
|
<text x="700" y="427" text-anchor="middle" font-size="9" fill="#2dd4bf">in-process call</text>
|
||||||
|
|
||||||
|
<!-- To PostgreSQL -->
|
||||||
|
<line x1="1140" y1="406" x2="1140" y2="450" stroke="#4ade80" stroke-width="1.5" marker-end="url(#arr-green)"/>
|
||||||
|
<rect x="1074" y="415" width="132" height="16" rx="3" fill="#0f172a" fill-opacity="0.85"/>
|
||||||
|
<text x="1140" y="427" text-anchor="middle" font-size="9" fill="#4ade80">psycopg2 · upsert / query</text>
|
||||||
|
|
||||||
|
<!-- ══════════════════════════════════════════════════
|
||||||
|
ZONE 3a — ComfyUI
|
||||||
|
══════════════════════════════════════════════════ -->
|
||||||
|
<rect x="30" y="450" width="530" height="248" rx="10" fill="url(#grad-comfy)" stroke="#ea580c" stroke-width="1.2" filter="url(#shadow)"/>
|
||||||
|
<text x="50" y="470" font-size="10" font-weight="600" fill="#fed7aa" letter-spacing="1.2">COMFYUI :8188 — Qwen GGUF Inference</text>
|
||||||
|
|
||||||
|
<!-- Workflow node strip -->
|
||||||
|
<rect x="50" y="478" width="490" height="52" rx="6" fill="#431407" stroke="#c2410c" stroke-width="0.8"/>
|
||||||
|
<text x="295" y="494" text-anchor="middle" font-size="10" font-weight="600" fill="#fed7aa">workflow_qwen_edit.json — Node Graph</text>
|
||||||
|
|
||||||
|
<rect x="58" y="500" width="80" height="22" rx="3" fill="#7c2d12" stroke="#ea580c" stroke-width="0.6"/>
|
||||||
|
<text x="98" y="514" text-anchor="middle" font-size="8.5" fill="#fed7aa">NODE_POSITIVE</text>
|
||||||
|
<rect x="144" y="500" width="80" height="22" rx="3" fill="#7c2d12" stroke="#ea580c" stroke-width="0.6"/>
|
||||||
|
<text x="184" y="514" text-anchor="middle" font-size="8.5" fill="#fed7aa">NODE_NEGATIVE</text>
|
||||||
|
<rect x="230" y="500" width="80" height="22" rx="3" fill="#7c2d12" stroke="#ea580c" stroke-width="0.6"/>
|
||||||
|
<text x="270" y="514" text-anchor="middle" font-size="8.5" fill="#fed7aa">NODE_LATENT</text>
|
||||||
|
<rect x="316" y="500" width="80" height="22" rx="3" fill="#7c2d12" stroke="#ea580c" stroke-width="0.6"/>
|
||||||
|
<text x="356" y="514" text-anchor="middle" font-size="8.5" fill="#fed7aa">NODE_KSAMPLER</text>
|
||||||
|
<rect x="402" y="500" width="60" height="22" rx="3" fill="#7c2d12" stroke="#ea580c" stroke-width="0.6"/>
|
||||||
|
<text x="432" y="514" text-anchor="middle" font-size="8.5" fill="#fed7aa">image1</text>
|
||||||
|
<rect x="468" y="500" width="64" height="22" rx="3" fill="#7c2d12" stroke="#ea580c" stroke-width="0.6"/>
|
||||||
|
<text x="500" y="514" text-anchor="middle" font-size="8.5" fill="#fed7aa">image2 (wf)</text>
|
||||||
|
|
||||||
|
<!-- Model cards -->
|
||||||
|
<rect x="50" y="542" width="155" height="72" rx="6" fill="#431407" stroke="#c2410c" stroke-width="0.8" filter="url(#shadow-sm)"/>
|
||||||
|
<text x="127" y="560" text-anchor="middle" font-size="10" font-weight="700" fill="#fed7aa">Qwen GGUF</text>
|
||||||
|
<text x="127" y="576" text-anchor="middle" font-size="8.5" fill="#fdba74">Rapid-NSFW-v23_Q8_0.gguf</text>
|
||||||
|
<text x="127" y="592" text-anchor="middle" font-size="8.5" fill="#fdba74">~8 GB VRAM</text>
|
||||||
|
<text x="127" y="607" text-anchor="middle" font-size="8.5" fill="#fdba74">Euler / karras sampler</text>
|
||||||
|
|
||||||
|
<rect x="216" y="542" width="155" height="72" rx="6" fill="#431407" stroke="#c2410c" stroke-width="0.8" filter="url(#shadow-sm)"/>
|
||||||
|
<text x="293" y="560" text-anchor="middle" font-size="10" font-weight="700" fill="#fed7aa">Text Encoder</text>
|
||||||
|
<text x="293" y="576" text-anchor="middle" font-size="8.5" fill="#fdba74">qwen_2.5_vl_7b_fp8</text>
|
||||||
|
<text x="293" y="592" text-anchor="middle" font-size="8.5" fill="#fdba74">_scaled.safetensors</text>
|
||||||
|
<text x="293" y="607" text-anchor="middle" font-size="8.5" fill="#fdba74">FP8 quantised</text>
|
||||||
|
|
||||||
|
<rect x="382" y="542" width="138" height="72" rx="6" fill="#431407" stroke="#c2410c" stroke-width="0.8" filter="url(#shadow-sm)"/>
|
||||||
|
<text x="451" y="560" text-anchor="middle" font-size="10" font-weight="700" fill="#fed7aa">VAE Decoder</text>
|
||||||
|
<text x="451" y="576" text-anchor="middle" font-size="8.5" fill="#fdba74">qwen_image_vae</text>
|
||||||
|
<text x="451" y="592" text-anchor="middle" font-size="8.5" fill="#fdba74">.safetensors</text>
|
||||||
|
<text x="451" y="607" text-anchor="middle" font-size="8.5" fill="#fdba74">latent → RGB PNG</text>
|
||||||
|
|
||||||
|
<!-- Wireframe note -->
|
||||||
|
<rect x="50" y="626" width="490" height="60" rx="6" fill="#431407" stroke="#c2410c" stroke-width="0.8"/>
|
||||||
|
<text x="295" y="644" text-anchor="middle" font-size="10" font-weight="600" fill="#fed7aa">Wireframe Pose Guide</text>
|
||||||
|
<text x="295" y="660" text-anchor="middle" font-size="9" fill="#fdba74">/mnt/zim/tour-comfy/wireframe/*.mp4 → OpenCV frame extract → image2 slot</text>
|
||||||
|
<text x="295" y="675" text-anchor="middle" font-size="9" fill="#fdba74">No ControlNet installed — Qwen uses image2 as visual layout reference</text>
|
||||||
|
|
||||||
|
<!-- ══════════════════════════════════════════════════
|
||||||
|
ZONE 3b — ML Post-processing
|
||||||
|
══════════════════════════════════════════════════ -->
|
||||||
|
<rect x="576" y="450" width="440" height="248" rx="10" fill="url(#grad-ml)" stroke="#0d9488" stroke-width="1.2" filter="url(#shadow)"/>
|
||||||
|
<text x="594" y="470" font-size="10" font-weight="600" fill="#99f6e4" letter-spacing="1.2">ML POST-PROCESSING — in-process Python</text>
|
||||||
|
|
||||||
|
<!-- SAM2 -->
|
||||||
|
<rect x="594" y="478" width="195" height="100" rx="6" fill="#0d3330" stroke="#0f766e" stroke-width="0.9" filter="url(#shadow-sm)"/>
|
||||||
|
<text x="691" y="496" text-anchor="middle" font-size="11" font-weight="700" fill="#2dd4bf">SAM2</text>
|
||||||
|
<text x="691" y="511" text-anchor="middle" font-size="8.5" fill="#5eead4">sam2.1_hiera_base_plus.pt</text>
|
||||||
|
<text x="600" y="528" font-size="8.5" fill="#5eead4">FG: 12 pts — hair → shoes</text>
|
||||||
|
<text x="600" y="542" font-size="8.5" fill="#5eead4">BG: 7 pts — corners + edges</text>
|
||||||
|
<text x="600" y="556" font-size="8.5" fill="#5eead4">Coverage check 5 %–92 %</text>
|
||||||
|
<text x="600" y="570" font-size="8.5" fill="#5eead4">Gaussian blur edge (r=1)</text>
|
||||||
|
|
||||||
|
<!-- rembg -->
|
||||||
|
<rect x="800" y="478" width="200" height="100" rx="6" fill="#0d3330" stroke="#0f766e" stroke-width="0.9" filter="url(#shadow-sm)"/>
|
||||||
|
<text x="900" y="496" text-anchor="middle" font-size="11" font-weight="700" fill="#2dd4bf">rembg (U2Net)</text>
|
||||||
|
<text x="900" y="511" text-anchor="middle" font-size="8.5" fill="#5eead4">Fallback BG removal</text>
|
||||||
|
<text x="806" y="528" font-size="8.5" fill="#5eead4">Used when SAM2 unavailable</text>
|
||||||
|
<text x="806" y="542" font-size="8.5" fill="#5eead4">or coverage out of range</text>
|
||||||
|
<text x="806" y="556" font-size="8.5" fill="#5eead4">Also: Segment tab button</text>
|
||||||
|
|
||||||
|
<!-- insightface -->
|
||||||
|
<rect x="594" y="590" width="195" height="96" rx="6" fill="#0d3330" stroke="#0f766e" stroke-width="0.9" filter="url(#shadow-sm)"/>
|
||||||
|
<text x="691" y="608" text-anchor="middle" font-size="11" font-weight="700" fill="#2dd4bf">insightface buffalo_l</text>
|
||||||
|
<text x="600" y="625" font-size="8.5" fill="#5eead4">Faceswap: source → video frames</text>
|
||||||
|
<text x="600" y="639" font-size="8.5" fill="#5eead4">Face extract: bbox + 50 % pad</text>
|
||||||
|
<text x="600" y="653" font-size="8.5" fill="#5eead4">Saves {gid}_face.png → DB</text>
|
||||||
|
<text x="600" y="667" font-size="8.5" fill="#5eead4">Triggered on set-preferred</text>
|
||||||
|
|
||||||
|
<!-- GFPGAN -->
|
||||||
|
<rect x="800" y="590" width="200" height="96" rx="6" fill="#0d3330" stroke="#0f766e" stroke-width="0.9" filter="url(#shadow-sm)"/>
|
||||||
|
<text x="900" y="608" text-anchor="middle" font-size="11" font-weight="700" fill="#2dd4bf">GFPGAN</text>
|
||||||
|
<text x="806" y="625" font-size="8.5" fill="#5eead4">Face restoration</text>
|
||||||
|
<text x="806" y="639" font-size="8.5" fill="#5eead4">Applied post-faceswap</text>
|
||||||
|
<text x="806" y="653" font-size="8.5" fill="#5eead4">Optional quality upgrade</text>
|
||||||
|
|
||||||
|
<!-- ══════════════════════════════════════════════════
|
||||||
|
ZONE 3c — PostgreSQL
|
||||||
|
══════════════════════════════════════════════════ -->
|
||||||
|
<rect x="1030" y="450" width="340" height="248" rx="10" fill="url(#grad-db)" stroke="#16a34a" stroke-width="1.2" filter="url(#shadow)"/>
|
||||||
|
<text x="1048" y="470" font-size="10" font-weight="600" fill="#bbf7d0" letter-spacing="1.2">POSTGRESQL 192.168.1.160:5433 db=dv</text>
|
||||||
|
|
||||||
|
<rect x="1048" y="478" width="302" height="200" rx="6" fill="#0c3a1e" stroke="#15803d" stroke-width="0.8" filter="url(#shadow-sm)"/>
|
||||||
|
<text x="1199" y="496" text-anchor="middle" font-size="11" font-weight="700" fill="#4ade80">person table</text>
|
||||||
|
|
||||||
|
<text x="1055" y="514" font-size="9" fill="#86efac">filename TEXT PRIMARY KEY</text>
|
||||||
|
<text x="1055" y="529" font-size="9" fill="#86efac">group_id TEXT</text>
|
||||||
|
<text x="1055" y="544" font-size="9" fill="#86efac">group_name TEXT</text>
|
||||||
|
<text x="1055" y="559" font-size="9" fill="#86efac">sort_order INTEGER (0 = preferred)</text>
|
||||||
|
<text x="1055" y="574" font-size="9" fill="#86efac">prompt TEXT — generation prompt</text>
|
||||||
|
<text x="1055" y="589" font-size="9" fill="#86efac">pose TEXT</text>
|
||||||
|
<text x="1055" y="604" font-size="9" fill="#86efac">hidden BOOLEAN</text>
|
||||||
|
<text x="1055" y="619" font-size="9" fill="#86efac">archived BOOLEAN</text>
|
||||||
|
<text x="1055" y="634" font-size="9" fill="#86efac">has_background BOOLEAN</text>
|
||||||
|
<text x="1055" y="649" font-size="9" fill="#86efac">source_refs TEXT (JSON array)</text>
|
||||||
|
<text x="1055" y="664" font-size="9" fill="#86efac">content_type TEXT (image | video)</text>
|
||||||
|
|
||||||
|
<!-- ══════════════════════════════════════════════════
|
||||||
|
ZONE 4 — Storage
|
||||||
|
══════════════════════════════════════════════════ -->
|
||||||
|
<rect x="30" y="716" width="980" height="118" rx="10" fill="url(#grad-storage)" stroke="#334155" stroke-width="1.2" filter="url(#shadow)"/>
|
||||||
|
<text x="50" y="736" font-size="10" font-weight="600" fill="#94a3b8" letter-spacing="1.2">FILE SYSTEM</text>
|
||||||
|
|
||||||
|
<rect x="50" y="744" width="280" height="76" rx="6" fill="#1e293b" stroke="#475569" stroke-width="0.8"/>
|
||||||
|
<text x="190" y="762" text-anchor="middle" font-size="10" font-weight="600" fill="#cbd5e1">Output Directory</text>
|
||||||
|
<text x="60" y="778" font-size="9" fill="#94a3b8">/mnt/zim/tour-comfy/output/</text>
|
||||||
|
<text x="60" y="793" font-size="9" fill="#64748b">PNGs · sidecars (.nobg.png) · face crops</text>
|
||||||
|
<text x="60" y="808" font-size="9" fill="#64748b">timestamped — 20260622_HHMMSS_N_src.png</text>
|
||||||
|
|
||||||
|
<rect x="344" y="744" width="280" height="76" rx="6" fill="#1e293b" stroke="#475569" stroke-width="0.8"/>
|
||||||
|
<text x="484" y="762" text-anchor="middle" font-size="10" font-weight="600" fill="#cbd5e1">Wireframe Videos</text>
|
||||||
|
<text x="354" y="778" font-size="9" fill="#94a3b8">/mnt/zim/tour-comfy/wireframe/</text>
|
||||||
|
<text x="354" y="793" font-size="9" fill="#64748b">*.mp4 pose reference videos</text>
|
||||||
|
<text x="354" y="808" font-size="9" fill="#64748b">Frame extracted via OpenCV at t∈[0,1]</text>
|
||||||
|
|
||||||
|
<rect x="638" y="744" width="360" height="76" rx="6" fill="#1e293b" stroke="#475569" stroke-width="0.8"/>
|
||||||
|
<text x="818" y="762" text-anchor="middle" font-size="10" font-weight="600" fill="#cbd5e1">Configuration</text>
|
||||||
|
<text x="648" y="778" font-size="9" fill="#94a3b8">tour-comfy/config.json</text>
|
||||||
|
<text x="648" y="793" font-size="9" fill="#64748b">output_dir · comfy_url · host · port · max_area</text>
|
||||||
|
<text x="648" y="808" font-size="9" fill="#64748b">R/W via GET /config · POST /config</text>
|
||||||
|
|
||||||
|
<!-- ══════════════════════════════════════════════════
|
||||||
|
ZONE 5 — Background services
|
||||||
|
══════════════════════════════════════════════════ -->
|
||||||
|
<rect x="1026" y="716" width="344" height="118" rx="10" fill="url(#grad-storage)" stroke="#334155" stroke-width="1.2" filter="url(#shadow)"/>
|
||||||
|
<text x="1046" y="736" font-size="10" font-weight="600" fill="#94a3b8" letter-spacing="1.2">BACKGROUND SERVICES — systemd</text>
|
||||||
|
|
||||||
|
<rect x="1046" y="744" width="145" height="76" rx="6" fill="#1e293b" stroke="#475569" stroke-width="0.8"/>
|
||||||
|
<text x="1119" y="762" text-anchor="middle" font-size="10" font-weight="600" fill="#cbd5e1">watcher.py</text>
|
||||||
|
<text x="1052" y="778" font-size="9" fill="#94a3b8">monitors output dir</text>
|
||||||
|
<text x="1052" y="793" font-size="9" fill="#64748b">auto-processes drops</text>
|
||||||
|
<text x="1052" y="808" font-size="9" fill="#64748b">watcher.lock · watcher.log</text>
|
||||||
|
|
||||||
|
<rect x="1202" y="744" width="155" height="76" rx="6" fill="#1e293b" stroke="#475569" stroke-width="0.8"/>
|
||||||
|
<text x="1280" y="762" text-anchor="middle" font-size="10" font-weight="600" fill="#cbd5e1">Systemd Units</text>
|
||||||
|
<text x="1208" y="778" font-size="9" fill="#94a3b8">comfyui-backend</text>
|
||||||
|
<text x="1208" y="793" font-size="9" fill="#94a3b8">comfyui-api</text>
|
||||||
|
<text x="1208" y="808" font-size="9" fill="#64748b">start.sh · stop.sh</text>
|
||||||
|
|
||||||
|
<!-- Storage arrows from FastAPI -->
|
||||||
|
<line x1="300" y1="698" x2="180" y2="716" stroke="#475569" stroke-width="1.2" stroke-dasharray="4,3" marker-end="url(#arr-gray)"/>
|
||||||
|
<line x1="700" y1="698" x2="484" y2="716" stroke="#475569" stroke-width="1.2" stroke-dasharray="4,3" marker-end="url(#arr-gray)"/>
|
||||||
|
|
||||||
|
<!-- ══════════════════════════════════════════════════
|
||||||
|
Legend
|
||||||
|
══════════════════════════════════════════════════ -->
|
||||||
|
<rect x="30" y="848" width="1340" height="56" rx="8" fill="#0f172a" stroke="#1e293b" stroke-width="1"/>
|
||||||
|
<text x="50" y="866" font-size="9" font-weight="600" fill="#64748b" letter-spacing="1">LEGEND</text>
|
||||||
|
|
||||||
|
<line x1="114" y1="870" x2="144" y2="870" stroke="#60a5fa" stroke-width="1.5" marker-end="url(#arr-blue)"/>
|
||||||
|
<text x="150" y="874" font-size="9" fill="#94a3b8">HTTP (fetch)</text>
|
||||||
|
|
||||||
|
<line x1="254" y1="870" x2="284" y2="870" stroke="#fb923c" stroke-width="1.5" marker-end="url(#arr-orange)"/>
|
||||||
|
<text x="290" y="874" font-size="9" fill="#94a3b8">ComfyUI API</text>
|
||||||
|
|
||||||
|
<line x1="390" y1="870" x2="420" y2="870" stroke="#2dd4bf" stroke-width="1.5" marker-end="url(#arr-teal)"/>
|
||||||
|
<text x="426" y="874" font-size="9" fill="#94a3b8">In-process call</text>
|
||||||
|
|
||||||
|
<line x1="526" y1="870" x2="556" y2="870" stroke="#4ade80" stroke-width="1.5" marker-end="url(#arr-green)"/>
|
||||||
|
<text x="562" y="874" font-size="9" fill="#94a3b8">PostgreSQL (psycopg2)</text>
|
||||||
|
|
||||||
|
<line x1="698" y1="870" x2="728" y2="870" stroke="#64748b" stroke-width="1.5" stroke-dasharray="4,3" marker-end="url(#arr-gray)"/>
|
||||||
|
<text x="734" y="874" font-size="9" fill="#94a3b8">File I/O</text>
|
||||||
|
|
||||||
|
<text x="800" y="866" font-size="9" fill="#64748b" letter-spacing="0.5">TRANSPARENT BG FLOW: prompt → strip kw → Qwen (solid BG) → SAM2 point-prompt (12 FG + 7 BG pts) → coverage check → Gaussian edge</text>
|
||||||
|
<text x="800" y="882" font-size="9" fill="#64748b" letter-spacing="0.5">FACE FLOW: set-preferred → insightface detect → pad bbox → crop → {gid}_face.png → DB upsert → studio Info tab face-book thumbnail</text>
|
||||||
|
</svg>
|
||||||
|
|||||||
|
Before Width: | Height: | Size: 3.3 KiB After Width: | Height: | Size: 29 KiB |
@@ -1428,6 +1428,33 @@
|
|||||||
padding: 1px 3px; border-radius: 2px; margin-left: 3px; vertical-align: middle;
|
padding: 1px 3px; border-radius: 2px; margin-left: 3px; vertical-align: middle;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
.sb-camera-grid { display: grid; grid-template-columns: repeat(4,1fr); gap: 4px; margin-bottom: 8px; }
|
||||||
|
.sb-angle-btn {
|
||||||
|
padding: 5px 2px; border-radius: 5px;
|
||||||
|
border: 1px solid #2a2a2a; background: #18181b;
|
||||||
|
color: #777; font-size: 11px; cursor: pointer; user-select: none;
|
||||||
|
text-align: center; transition: all 0.12s;
|
||||||
|
}
|
||||||
|
.sb-angle-btn:hover { border-color: #444; color: #ccc; }
|
||||||
|
.sb-angle-btn.selected { border-color: #0e7490; background: #082f49; color: #7dd3fc; font-weight: 600; }
|
||||||
|
#studioAngleBar {
|
||||||
|
position: absolute; bottom: 8px; left: 50%; transform: translateX(-50%);
|
||||||
|
display: flex; gap: 4px; opacity: 0; transition: opacity 0.2s;
|
||||||
|
z-index: 10; pointer-events: none;
|
||||||
|
}
|
||||||
|
.studio-viewer:hover #studioAngleBar { opacity: 1; pointer-events: all; }
|
||||||
|
#studioAngleBar button {
|
||||||
|
font-size: 15px; background: rgba(0,0,0,0.65); border: 1px solid rgba(255,255,255,0.18);
|
||||||
|
border-radius: 4px; color: #fff; width: 34px; height: 34px; cursor: pointer; line-height: 1;
|
||||||
|
transition: background 0.12s; position: relative;
|
||||||
|
}
|
||||||
|
#studioAngleBar button:hover { background: rgba(255,255,255,0.18); }
|
||||||
|
#studioAngleBar button[title]:hover::after {
|
||||||
|
content: attr(title); position: absolute; bottom: 38px; left: 50%; transform: translateX(-50%);
|
||||||
|
background: rgba(0,0,0,0.8); color: #fff; font-size: 10px; padding: 2px 6px;
|
||||||
|
border-radius: 3px; white-space: nowrap; pointer-events: none;
|
||||||
|
}
|
||||||
|
|
||||||
/* template grid (faceswap / scenery) */
|
/* template grid (faceswap / scenery) */
|
||||||
.sb-template-grid {
|
.sb-template-grid {
|
||||||
display: grid; grid-template-columns: 1fr 1fr;
|
display: grid; grid-template-columns: 1fr 1fr;
|
||||||
@@ -1536,47 +1563,69 @@
|
|||||||
<div class="priv-msg-row">
|
<div class="priv-msg-row">
|
||||||
<div class="priv-msg-inner">
|
<div class="priv-msg-inner">
|
||||||
<div class="priv-avatar user">You</div>
|
<div class="priv-avatar user">You</div>
|
||||||
<div class="priv-text">What is the purpose of this system?</div>
|
<div class="priv-text">What is this system and what does it run on?</div>
|
||||||
</div>
|
</div>
|
||||||
</div>
|
</div>
|
||||||
<div class="priv-msg-row assistant">
|
<div class="priv-msg-row assistant">
|
||||||
<div class="priv-msg-inner">
|
<div class="priv-msg-inner">
|
||||||
<div class="priv-avatar bot">AI</div>
|
<div class="priv-avatar bot">AI</div>
|
||||||
<div class="priv-text">
|
<div class="priv-text">
|
||||||
This system implements a headless image editing API using the Qwen-Rapid-NSFW-v23 model on an RTX A6000 GPU. It provides an HTTP service that accepts image and prompt inputs, processes edits using ComfyUI backend, and returns edited PNG outputs.
|
This is a self-hosted AI image studio for generative editing, multi-view character rendering, background removal, face swapping, and group-based asset management. It runs on a local RTX A6000 GPU (CUDA 12.4, 48 GB VRAM) using the <strong>Qwen 2.5 VL GGUF</strong> model (Rapid-NSFW-v23 Q8_0) via ComfyUI. The frontend is a single-page browser app (car.html) talking to a FastAPI backend on :8500.
|
||||||
</div>
|
</div>
|
||||||
</div>
|
</div>
|
||||||
</div>
|
</div>
|
||||||
<div class="priv-msg-row">
|
<div class="priv-msg-row">
|
||||||
<div class="priv-msg-inner">
|
<div class="priv-msg-inner">
|
||||||
<div class="priv-avatar user">You</div>
|
<div class="priv-avatar user">You</div>
|
||||||
<div class="priv-text">How does it work?</div>
|
<div class="priv-text">Walk me through the image generation flow.</div>
|
||||||
</div>
|
</div>
|
||||||
</div>
|
</div>
|
||||||
<div class="priv-msg-row assistant">
|
<div class="priv-msg-row assistant">
|
||||||
<div class="priv-msg-inner">
|
<div class="priv-msg-inner">
|
||||||
<div class="priv-avatar bot">AI</div>
|
<div class="priv-avatar bot">AI</div>
|
||||||
<div class="priv-text">
|
<div class="priv-text">
|
||||||
The system consists of two main components: a ComfyUI backend (running on port 8188) that executes the Qwen models and a FastAPI service (running on port 8500) that provides HTTP API endpoints. When you send an image and prompt to the API, it forwards the request to ComfyUI which processes the image using the Qwen-Rapid-NSFW-v23 model with specific workflow parameters.
|
When a generation is triggered the pipeline is:<br><br>
|
||||||
|
<strong>1. Prompt cleaning</strong> — if the prompt contains "transparent background", that keyword is stripped so Qwen renders a clean solid-BG image instead of producing washed-out halos.<br><br>
|
||||||
|
<strong>2. ComfyUI queue</strong> — the reference image is uploaded to ComfyUI (:8188) and injected into <em>image1</em>. An optional wireframe frame extracted from a pose-guide video goes into <em>image2</em>. The workflow graph (workflow_qwen_edit.json) is patched with the prompt, dimensions, seed, and sampler params, then submitted via POST /prompt.<br><br>
|
||||||
|
<strong>3. Qwen inference</strong> — the GGUF model (≈8 GB VRAM), text encoder (FP8), and VAE decode the latent into a PNG.<br><br>
|
||||||
|
<strong>4. SAM2 post-processing</strong> — if transparent was requested, SAM2 point-prompt segmentation removes the background using 12 foreground seed points (hair → shoes, shoulder / hip lateral spread) and 7 background points (corners + edge midpoints). A coverage sanity check (5–92 %) falls back to rembg if the mask is implausible.
|
||||||
</div>
|
</div>
|
||||||
</div>
|
</div>
|
||||||
</div>
|
</div>
|
||||||
<div class="priv-msg-row">
|
<div class="priv-msg-row">
|
||||||
<div class="priv-msg-inner">
|
<div class="priv-msg-inner">
|
||||||
<div class="priv-avatar user">You</div>
|
<div class="priv-avatar user">You</div>
|
||||||
<div class="priv-text">What are the key components?</div>
|
<div class="priv-text">What are the main API endpoints?</div>
|
||||||
</div>
|
</div>
|
||||||
</div>
|
</div>
|
||||||
<div class="priv-msg-row assistant">
|
<div class="priv-msg-row assistant">
|
||||||
<div class="priv-msg-inner">
|
<div class="priv-msg-inner">
|
||||||
<div class="priv-avatar bot">AI</div>
|
<div class="priv-avatar bot">AI</div>
|
||||||
<div class="priv-text">
|
<div class="priv-text">
|
||||||
Key components include:<br><br>
|
The FastAPI service (:8500) exposes:<br><br>
|
||||||
- Qwen model: Qwen-Rapid-NSFW-v23_Q8_0.gguf<br>
|
<strong>GET /images</strong> — full image list with PostgreSQL metadata (group, prompt, pose, sort order, archived flag).<br>
|
||||||
- Text encoder: qwen_2.5_vl_7b_fp8_scaled.safetensors<br>
|
<strong>POST /upload</strong> — add an image; with group_id + skip_poses it silently joins an existing group without triggering pose generation.<br>
|
||||||
- VAE decoder: qwen_image_vae.safetensors<br>
|
<strong>POST /batch</strong> — async multi-prompt generation job (filenames, prompts, poses, wireframe_ref). Poll progress via GET /jobs/{id}.<br>
|
||||||
- Workflow execution engine using ComfyUI<br><br>
|
<strong>POST /faceswap</strong> — insightface video face swap with optional GFPGAN restoration.<br>
|
||||||
The system uses a specialized workflow (workflow_qwen_edit.json) that defines the processing pipeline with nodes for loading the model, text encoder, VAE, input image, positive/negative prompts, latent generation, sampling, and output saving.
|
<strong>POST /remove-background-sam/{f}</strong> — SAM2 BG removal to a .nobg.png sidecar.<br>
|
||||||
|
<strong>POST /images/{f}/set-preferred</strong> — moves image to group slot 0 and queues face extraction in the background.<br>
|
||||||
|
<strong>GET /wireframe/frame/{name}?t=</strong> — extract a frame at normalised time t∈[0,1] from a wireframe pose video.
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
<div class="priv-msg-row">
|
||||||
|
<div class="priv-msg-inner">
|
||||||
|
<div class="priv-avatar user">You</div>
|
||||||
|
<div class="priv-text">How does the face-book and multi-view workflow work?</div>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
<div class="priv-msg-row assistant">
|
||||||
|
<div class="priv-msg-inner">
|
||||||
|
<div class="priv-avatar bot">AI</div>
|
||||||
|
<div class="priv-text">
|
||||||
|
<strong>Face-book:</strong> marking an image as "preferred" (star button) moves it to sort_order=0 in the group and triggers a background task. insightface detects the largest face, adds 50 % padding on the sides and 200 % headroom above, and saves a <em>{group_id}_face.png</em> crop. This appears as a 72 px thumbnail in the studio Info tab for fast face-reference lookup.<br><br>
|
||||||
|
<strong>Multi-view / camera angles:</strong> the Generate tab offers 12 camera angle presets — 8 absolute (Front, ¾ Left/Right, Side, Back, High, Low) and 4 relative (±45°, ±90°). Each fires a /batch request with the angle prompt injected and pose=null. The wireframe pose guide (a .mp4 video scrubbed to any frame) is passed as image2 in the Qwen workflow to constrain body layout without ControlNet — the controlnet model folder is empty by design.<br><br>
|
||||||
|
<strong>Group management:</strong> all images belong to groups stored in PostgreSQL. Clipboard paste (Ctrl+V) while a group is open offers "add to this group — no poses" or "new group with pose generation". Archive hides images from the default view without deleting them.
|
||||||
</div>
|
</div>
|
||||||
</div>
|
</div>
|
||||||
</div>
|
</div>
|
||||||
@@ -1611,37 +1660,6 @@
|
|||||||
titleElement.innerHTML += ` • Built: ${timestamp}`;
|
titleElement.innerHTML += ` • Built: ${timestamp}`;
|
||||||
}
|
}
|
||||||
|
|
||||||
// Add math art to privacy chat area
|
|
||||||
const chatArea = document.querySelector('.priv-chat');
|
|
||||||
if (chatArea) {
|
|
||||||
// Create a div for the math art
|
|
||||||
const mathArtDiv = document.createElement('div');
|
|
||||||
mathArtDiv.style.cssText = `
|
|
||||||
margin-top: 20px;
|
|
||||||
padding: 15px;
|
|
||||||
background: rgba(30, 30, 30, 0.7);
|
|
||||||
border-radius: 8px;
|
|
||||||
font-family: monospace;
|
|
||||||
font-size: 12px;
|
|
||||||
line-height: 1.4;
|
|
||||||
overflow: hidden;
|
|
||||||
`;
|
|
||||||
mathArtDiv.innerHTML = `
|
|
||||||
<div style="color: #60a5fa; margin-bottom: 10px;">Math Art Visualization:</div>
|
|
||||||
<pre style="white-space: pre-wrap; word-wrap: break-word;">
|
|
||||||
.-~~-. .-~~-. .-~~-. .-~~-.
|
|
||||||
( ( ) ( ( ) ( ( ) ( ( )
|
|
||||||
'-~~-' '-~~-' '-~~-' '-~~-'
|
|
||||||
.-~~-. .-~~-. .-~~-. .-~~-.
|
|
||||||
( ( ) ( ( ) ( ( ) ( ( )
|
|
||||||
'-~~-' '-~~-' '-~~-' '-~~-'
|
|
||||||
</pre>
|
|
||||||
<div style="color: #86efac; margin-top: 10px;">
|
|
||||||
π ≈ 3.14159265358979323846...
|
|
||||||
</div>
|
|
||||||
`;
|
|
||||||
chatArea.appendChild(mathArtDiv);
|
|
||||||
}
|
|
||||||
} catch (e) {
|
} catch (e) {
|
||||||
console.error('Error injecting build time or math art:', e);
|
console.error('Error injecting build time or math art:', e);
|
||||||
}
|
}
|
||||||
@@ -1741,6 +1759,7 @@
|
|||||||
<img id="lbImg" src="" alt="" onclick="toggleImageZoom(this)" />
|
<img id="lbImg" src="" alt="" onclick="toggleImageZoom(this)" />
|
||||||
<video id="lbVideo" style="display:none;max-width:100%;max-height:100%;border-radius:4px" controls autoplay muted loop></video>
|
<video id="lbVideo" style="display:none;max-width:100%;max-height:100%;border-radius:4px" controls autoplay muted loop></video>
|
||||||
<div class="lb-hidden-badge">Hidden from preview</div>
|
<div class="lb-hidden-badge">Hidden from preview</div>
|
||||||
|
<div id="studioAngleBar"></div>
|
||||||
</div>
|
</div>
|
||||||
<button class="studio-nav-btn" id="lbNext" onclick="lbNav(1)">›</button>
|
<button class="studio-nav-btn" id="lbNext" onclick="lbNav(1)">›</button>
|
||||||
</div>
|
</div>
|
||||||
@@ -1782,6 +1801,10 @@
|
|||||||
<div class="sb-label" style="margin-bottom:3px">Generation prompt</div>
|
<div class="sb-label" style="margin-bottom:3px">Generation prompt</div>
|
||||||
<div id="lbGenPrompt" style="font-size:11px;color:#888;line-height:1.4;word-break:break-word"></div>
|
<div id="lbGenPrompt" style="font-size:11px;color:#888;line-height:1.4;word-break:break-word"></div>
|
||||||
</div>
|
</div>
|
||||||
|
<div id="lbFaceBook" style="display:none;margin-bottom:8px">
|
||||||
|
<div class="sb-label" style="margin-bottom:4px">Face reference</div>
|
||||||
|
<img id="lbFaceThumb" style="width:72px;height:72px;object-fit:cover;border-radius:6px;border:1px solid #333;cursor:pointer" onclick="window.open(this.src,'_blank')" title="Face crop — click to view full">
|
||||||
|
</div>
|
||||||
<div class="sb-sep"></div>
|
<div class="sb-sep"></div>
|
||||||
<div class="sb-label">Order & visibility</div>
|
<div class="sb-label">Order & visibility</div>
|
||||||
<div class="sb-actions" style="margin-bottom:8px">
|
<div class="sb-actions" style="margin-bottom:8px">
|
||||||
@@ -2147,7 +2170,27 @@
|
|||||||
let availableVideos = []; // populated from /videos
|
let availableVideos = []; // populated from /videos
|
||||||
let _fsActiveTab = 'swap';
|
let _fsActiveTab = 'swap';
|
||||||
let _fsSelectedPoses = new Set();
|
let _fsSelectedPoses = new Set();
|
||||||
|
let _sbSelectedAngles = new Set(); // selected camera angle names
|
||||||
|
let _sbWireframeRef = ''; // wireframe video name for pose guide
|
||||||
|
let _sbWireframeTime = 0.5; // normalized frame time 0–1
|
||||||
let _sbPoseEdits = {}; // poseName → edited text
|
let _sbPoseEdits = {}; // poseName → edited text
|
||||||
|
|
||||||
|
const CAMERA_ANGLES = [
|
||||||
|
// Absolute camera positions
|
||||||
|
{ name: 'Front', icon: '⊙', prompt: 'Head-on straight-on full-body portrait, frontal camera, realistic, transparent background', relative: false },
|
||||||
|
{ name: '¾ Left', icon: '↙', prompt: 'Three-quarter left, camera 45° to the left, full-body portrait, realistic, transparent background', relative: false },
|
||||||
|
{ name: '¾ Right', icon: '↗', prompt: 'Three-quarter right, camera 45° to the right, full-body portrait, realistic, transparent background', relative: false },
|
||||||
|
{ name: 'Side L', icon: '◁', prompt: 'Side profile, camera 90° to the left, full-body portrait, realistic, transparent background', relative: false },
|
||||||
|
{ name: 'Side R', icon: '▷', prompt: 'Side profile, camera 90° to the right, full-body portrait, realistic, transparent background', relative: false },
|
||||||
|
{ name: 'Back', icon: '⊕', prompt: 'Rear view, camera directly behind subject, full-body portrait, realistic, transparent background', relative: false },
|
||||||
|
{ name: 'High', icon: '△', prompt: "Bird's-eye view, camera above looking down, full-body, realistic, transparent background", relative: false },
|
||||||
|
{ name: 'Low', icon: '▽', prompt: "Worm's-eye view, camera below looking up, full-body portrait, realistic, transparent background", relative: false },
|
||||||
|
// Relative rotations — applied on top of current view
|
||||||
|
{ name: '↺ 45°', icon: '↺', prompt: 'Rotate 45° to the left from current view, full-body portrait, realistic, transparent background', relative: true },
|
||||||
|
{ name: '↻ 45°', icon: '↻', prompt: 'Rotate 45° to the right from current view, full-body portrait, realistic, transparent background', relative: true },
|
||||||
|
{ name: '↺ 90°', icon: '⟲', prompt: 'Rotate 90° to the left from current view, side profile, full-body portrait, realistic, transparent background', relative: true },
|
||||||
|
{ name: '↻ 90°', icon: '⟳', prompt: 'Rotate 90° to the right from current view, side profile, full-body portrait, realistic, transparent background', relative: true },
|
||||||
|
];
|
||||||
let _sbGenJobId = null;
|
let _sbGenJobId = null;
|
||||||
let _sbGenJobPollTimer= null;
|
let _sbGenJobPollTimer= null;
|
||||||
let _followLatestGid = null; // set to gid after generation to auto-jump to newest image
|
let _followLatestGid = null; // set to gid after generation to auto-jump to newest image
|
||||||
@@ -2407,6 +2450,21 @@
|
|||||||
}).join('');
|
}).join('');
|
||||||
const active = strip.querySelector('.lb-var-thumb.active');
|
const active = strip.querySelector('.lb-var-thumb.active');
|
||||||
if (active) active.scrollIntoView({ block: 'nearest', inline: 'center' });
|
if (active) active.scrollIntoView({ block: 'nearest', inline: 'center' });
|
||||||
|
|
||||||
|
// Camera angle overlay bar
|
||||||
|
updateSbAngleBar();
|
||||||
|
|
||||||
|
// Face-book thumbnail — show on slot 0 when a face crop exists for this group
|
||||||
|
const faceBook = document.getElementById('lbFaceBook');
|
||||||
|
const faceThumb = document.getElementById('lbFaceThumb');
|
||||||
|
if (faceBook && faceThumb && lbCurrentGid && lbIdx === 0 && !isVid) {
|
||||||
|
const faceFname = lbCurrentGid.replace(/\//g, '_') + '_face.png';
|
||||||
|
faceThumb.src = IMAGE_FOLDER + faceFname + '?t=' + Date.now();
|
||||||
|
faceThumb.onerror = () => { faceBook.style.display = 'none'; };
|
||||||
|
faceThumb.onload = () => { faceBook.style.display = ''; };
|
||||||
|
} else if (faceBook) {
|
||||||
|
faceBook.style.display = 'none';
|
||||||
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
// Alias for old callsites
|
// Alias for old callsites
|
||||||
@@ -2887,7 +2945,12 @@
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
if (files.length > 0) {
|
if (files.length > 0) {
|
||||||
handleUpload(files);
|
// If studio is open, offer to add to current group without triggering poses
|
||||||
|
if (lbCurrentGid) {
|
||||||
|
showPasteGroupDialog(files);
|
||||||
|
} else {
|
||||||
|
handleUpload(files);
|
||||||
|
}
|
||||||
}
|
}
|
||||||
});
|
});
|
||||||
|
|
||||||
@@ -3816,7 +3879,47 @@
|
|||||||
const donePoses = new Set();
|
const donePoses = new Set();
|
||||||
lbNames.forEach(n => { if (filePoses[n]) donePoses.add(filePoses[n]); });
|
lbNames.forEach(n => { if (filePoses[n]) donePoses.add(filePoses[n]); });
|
||||||
|
|
||||||
let html = '<div class="sb-label">Poses</div><div class="sb-poses-grid" id="sbPosesGrid">';
|
// Camera angles section — absolute positions
|
||||||
|
const absAngles = CAMERA_ANGLES.filter(a => !a.relative);
|
||||||
|
const relAngles = CAMERA_ANGLES.filter(a => a.relative);
|
||||||
|
let html = '<div class="sb-label">Camera — absolute</div><div class="sb-camera-grid" id="sbCameraGrid">';
|
||||||
|
html += absAngles.map(a => {
|
||||||
|
const sel = _sbSelectedAngles.has(a.name) ? ' selected' : '';
|
||||||
|
const nSafe = a.name.replace(/'/g, "\\'");
|
||||||
|
return `<button class="sb-angle-btn${sel}" onclick="toggleSbAngle('${nSafe}')" title="${escHtml(a.prompt)}">${a.icon}<br><span style="font-size:9px">${escHtml(a.name)}</span></button>`;
|
||||||
|
}).join('');
|
||||||
|
html += '</div>';
|
||||||
|
|
||||||
|
// Relative rotations
|
||||||
|
html += '<div class="sb-label" style="margin-top:6px">Camera — relative</div><div class="sb-camera-grid" id="sbRelAngleGrid">';
|
||||||
|
html += relAngles.map(a => {
|
||||||
|
const sel = _sbSelectedAngles.has(a.name) ? ' selected' : '';
|
||||||
|
const nSafe = a.name.replace(/'/g, "\\'");
|
||||||
|
return `<button class="sb-angle-btn${sel}" onclick="toggleSbAngle('${nSafe}')" title="${escHtml(a.prompt)}">${a.icon}<br><span style="font-size:9px">${escHtml(a.name)}</span></button>`;
|
||||||
|
}).join('');
|
||||||
|
html += '</div>';
|
||||||
|
|
||||||
|
// Wireframe pose reference
|
||||||
|
const wfSel = _sbWireframeRef || '';
|
||||||
|
const wfT = _sbWireframeTime;
|
||||||
|
html += `<div class="sb-sep"></div>
|
||||||
|
<div class="sb-label">Wireframe pose guide <span style="font-size:10px;color:#555;font-weight:400">(optional)</span></div>
|
||||||
|
<select id="sbWireframeSelect" onchange="sbSelectWireframe(this.value)"
|
||||||
|
style="width:100%;background:#111;border:1px solid #2a2a2a;border-radius:5px;color:#aaa;font-size:11px;padding:4px;margin-bottom:6px">
|
||||||
|
<option value="">— none —</option>
|
||||||
|
${availableVideos.map(v => `<option value="${escHtml(v)}"${wfSel===v?' selected':''}>${escHtml(v.replace(/\.[^.]+$/,''))}</option>`).join('')}
|
||||||
|
</select>
|
||||||
|
${wfSel ? `<div style="display:flex;align-items:center;gap:6px;margin-bottom:6px">
|
||||||
|
<span style="font-size:11px;color:#777">Frame:</span>
|
||||||
|
<input type="range" id="sbWireframeTimeSlider" min="0" max="100" value="${Math.round(wfT*100)}"
|
||||||
|
oninput="sbUpdateWireframeTime(this.value/100)"
|
||||||
|
style="flex:1">
|
||||||
|
<span id="sbWireframeTimeLabel" style="font-size:11px;color:#777;min-width:28px">${Math.round(wfT*100)}%</span>
|
||||||
|
<img id="sbWireframeThumb" src="${API}/wireframe/frame/${encodeURIComponent(wfSel)}?t=${wfT}"
|
||||||
|
style="width:48px;height:48px;object-fit:contain;border-radius:4px;border:1px solid #333">
|
||||||
|
</div>` : ''}`;
|
||||||
|
|
||||||
|
html += '<div class="sb-sep"></div><div class="sb-label">Poses</div><div class="sb-poses-grid" id="sbPosesGrid">';
|
||||||
if (!availablePoses || Object.keys(availablePoses).length === 0) {
|
if (!availablePoses || Object.keys(availablePoses).length === 0) {
|
||||||
html += '<div style="font-size:11px;color:#555;padding:6px 0">No poses loaded</div>';
|
html += '<div style="font-size:11px;color:#555;padding:6px 0">No poses loaded</div>';
|
||||||
} else {
|
} else {
|
||||||
@@ -3874,13 +3977,89 @@
|
|||||||
renderSidebarGenerate();
|
renderSidebarGenerate();
|
||||||
}
|
}
|
||||||
|
|
||||||
|
function toggleSbAngle(name) {
|
||||||
|
if (_sbSelectedAngles.has(name)) _sbSelectedAngles.delete(name);
|
||||||
|
else _sbSelectedAngles.add(name);
|
||||||
|
renderSidebarGenerate();
|
||||||
|
}
|
||||||
|
|
||||||
|
function sbSelectWireframe(val) {
|
||||||
|
_sbWireframeRef = val;
|
||||||
|
renderSidebarGenerate();
|
||||||
|
}
|
||||||
|
|
||||||
|
function sbUpdateWireframeTime(t) {
|
||||||
|
_sbWireframeTime = t;
|
||||||
|
const label = document.getElementById('sbWireframeTimeLabel');
|
||||||
|
if (label) label.textContent = Math.round(t * 100) + '%';
|
||||||
|
// Debounced thumb update
|
||||||
|
clearTimeout(sbUpdateWireframeTime._timer);
|
||||||
|
sbUpdateWireframeTime._timer = setTimeout(() => {
|
||||||
|
const thumb = document.getElementById('sbWireframeThumb');
|
||||||
|
if (thumb && _sbWireframeRef) {
|
||||||
|
thumb.src = `${API}/wireframe/frame/${encodeURIComponent(_sbWireframeRef)}?t=${t}&_=${Date.now()}`;
|
||||||
|
}
|
||||||
|
}, 400);
|
||||||
|
}
|
||||||
|
|
||||||
|
async function submitSingleAngle(prompt) {
|
||||||
|
if (!_fsModelFilename) return;
|
||||||
|
const bar = document.getElementById('studioAngleBar');
|
||||||
|
if (bar) bar.style.pointerEvents = 'none';
|
||||||
|
try {
|
||||||
|
const r = await fetch(`${API}/batch`, {
|
||||||
|
method: 'POST',
|
||||||
|
headers: { 'Content-Type': 'application/json' },
|
||||||
|
body: JSON.stringify({
|
||||||
|
filenames: [_fsModelFilename], prompt: [prompt],
|
||||||
|
poses: [null], seed: -1, max_area: 0, group_id: lbCurrentGid,
|
||||||
|
wireframe_ref: _sbWireframeRef || null,
|
||||||
|
wireframe_time: _sbWireframeTime,
|
||||||
|
}),
|
||||||
|
});
|
||||||
|
if (r.ok) {
|
||||||
|
const { job_id } = await r.json();
|
||||||
|
_followLatestGid = lbCurrentGid;
|
||||||
|
showToast('Generating angle…', 'info');
|
||||||
|
// Light polling — refresh when done
|
||||||
|
const poll = () => setTimeout(async () => {
|
||||||
|
try {
|
||||||
|
const s = await fetch(`${API}/batch/${job_id}`).then(r => r.json());
|
||||||
|
if (s.status === 'done') { refreshNow(); }
|
||||||
|
else if (s.status !== 'error' && s.status !== 'cancelled') poll();
|
||||||
|
} catch(e) {}
|
||||||
|
}, 2000);
|
||||||
|
poll();
|
||||||
|
} else { showToast('Angle generation failed', 'error'); }
|
||||||
|
} catch(e) { showToast('API error: ' + e, 'error'); }
|
||||||
|
if (bar) bar.style.pointerEvents = '';
|
||||||
|
}
|
||||||
|
|
||||||
|
function updateSbAngleBar() {
|
||||||
|
const bar = document.getElementById('studioAngleBar');
|
||||||
|
if (!bar) return;
|
||||||
|
const isVid = lbNames[lbIdx] && (isVideo(lbNames[lbIdx]) || fileContentType[lbNames[lbIdx]] === 'video');
|
||||||
|
const hasCrop = !!document.getElementById('cropCanvas');
|
||||||
|
if (isVid || hasCrop || !lbNames[lbIdx]) {
|
||||||
|
bar.style.display = 'none';
|
||||||
|
return;
|
||||||
|
}
|
||||||
|
bar.style.display = 'flex';
|
||||||
|
// Show 6 most useful angles (skip High/Low for overlay — rare)
|
||||||
|
const overlay = CAMERA_ANGLES.slice(0, 6);
|
||||||
|
bar.innerHTML = overlay.map(a => {
|
||||||
|
const pSafe = a.prompt.replace(/'/g, "\\'");
|
||||||
|
return `<button onclick="submitSingleAngle('${pSafe}')" title="${escHtml(a.name)}">${a.icon}</button>`;
|
||||||
|
}).join('');
|
||||||
|
}
|
||||||
|
|
||||||
function updateSbGenBtn() {
|
function updateSbGenBtn() {
|
||||||
const btn = document.getElementById('sbGenBtn');
|
const btn = document.getElementById('sbGenBtn');
|
||||||
if (!btn) return;
|
if (!btn) return;
|
||||||
const hasPrompt = (document.getElementById('sbGenPromptInput')?.value || '').trim().length > 0;
|
const hasPrompt = (document.getElementById('sbGenPromptInput')?.value || '').trim().length > 0;
|
||||||
btn.disabled = _fsSelectedPoses.size === 0 && !hasPrompt;
|
const total = _fsSelectedPoses.size + _sbSelectedAngles.size + (hasPrompt ? 1 : 0);
|
||||||
const n = _fsSelectedPoses.size + (hasPrompt ? 1 : 0);
|
btn.disabled = total === 0;
|
||||||
btn.textContent = n > 1 ? `Generate (${n})` : 'Generate';
|
btn.textContent = total > 1 ? `Generate (${total})` : 'Generate';
|
||||||
}
|
}
|
||||||
|
|
||||||
async function cancelSbGenerate() {
|
async function cancelSbGenerate() {
|
||||||
@@ -3911,6 +4090,11 @@
|
|||||||
const orig = availablePoses[name]?.text ?? availablePoses[name] ?? name;
|
const orig = availablePoses[name]?.text ?? availablePoses[name] ?? name;
|
||||||
prompts.push((edited !== undefined && edited.trim()) ? edited.trim() : String(orig));
|
prompts.push((edited !== undefined && edited.trim()) ? edited.trim() : String(orig));
|
||||||
});
|
});
|
||||||
|
// Camera angles — treated as prompts with no pose tag
|
||||||
|
_sbSelectedAngles.forEach(name => {
|
||||||
|
const ang = CAMERA_ANGLES.find(a => a.name === name);
|
||||||
|
if (ang) { prompts.push(ang.prompt); poses.push(null); }
|
||||||
|
});
|
||||||
if (promptVal) { prompts.push(promptVal); poses.push(null); savePromptHistory(promptVal); }
|
if (promptVal) { prompts.push(promptVal); poses.push(null); savePromptHistory(promptVal); }
|
||||||
if (prompts.length === 0) return;
|
if (prompts.length === 0) return;
|
||||||
const btn = document.getElementById('sbGenBtn');
|
const btn = document.getElementById('sbGenBtn');
|
||||||
@@ -3927,7 +4111,9 @@
|
|||||||
headers: { 'Content-Type': 'application/json' },
|
headers: { 'Content-Type': 'application/json' },
|
||||||
body: JSON.stringify({
|
body: JSON.stringify({
|
||||||
filenames: [_fsModelFilename], prompt: prompts,
|
filenames: [_fsModelFilename], prompt: prompts,
|
||||||
poses, seed: -1, max_area: 0, group_id: lbCurrentGid
|
poses, seed: -1, max_area: 0, group_id: lbCurrentGid,
|
||||||
|
wireframe_ref: _sbWireframeRef || null,
|
||||||
|
wireframe_time: _sbWireframeTime,
|
||||||
}),
|
}),
|
||||||
});
|
});
|
||||||
if (!r.ok) {
|
if (!r.ok) {
|
||||||
@@ -4656,7 +4842,7 @@
|
|||||||
const fname = lbNames[lbIdx];
|
const fname = lbNames[lbIdx];
|
||||||
if (!fname) return;
|
if (!fname) return;
|
||||||
try {
|
try {
|
||||||
const r = await fetch(`/images/${encodeURIComponent(fname)}/set-preferred`, {method:'POST'});
|
const r = await fetch(`${API}/images/${encodeURIComponent(fname)}/set-preferred`, {method:'POST'});
|
||||||
if (!r.ok) return;
|
if (!r.ok) return;
|
||||||
fileSortOrders[fname] = 0;
|
fileSortOrders[fname] = 0;
|
||||||
const url = lbUrls[lbIdx];
|
const url = lbUrls[lbIdx];
|
||||||
@@ -4666,8 +4852,48 @@
|
|||||||
lbNames = [fname, ...otherNames];
|
lbNames = [fname, ...otherNames];
|
||||||
lbIdx = 0;
|
lbIdx = 0;
|
||||||
updateStudio();
|
updateStudio();
|
||||||
|
// Fire-and-forget face extraction for face-book
|
||||||
|
fetch(`${API}/images/${encodeURIComponent(fname)}/extract-face`, { method: 'POST' })
|
||||||
|
.then(r => r.ok ? r.json() : null)
|
||||||
|
.then(d => { if (d?.status === 'queued') showToast('Extracting face reference…', 'info'); })
|
||||||
|
.catch(() => {});
|
||||||
} catch(e) { console.error(e); }
|
} catch(e) { console.error(e); }
|
||||||
}
|
}
|
||||||
|
|
||||||
|
function showPasteGroupDialog(files) {
|
||||||
|
document.getElementById('pasteDialog')?.remove();
|
||||||
|
const gName = (lbCurrentGid && groupNames[lbCurrentGid]) || lbCurrentGid || 'current group';
|
||||||
|
const gidSafe = escHtml(lbCurrentGid || '');
|
||||||
|
const gNameSafe = escHtml(gName);
|
||||||
|
const d = document.createElement('div');
|
||||||
|
d.id = 'pasteDialog';
|
||||||
|
d.style.cssText = 'position:fixed;top:50%;left:50%;transform:translate(-50%,-50%);background:#1a1a1a;border:1px solid #333;border-radius:8px;padding:20px;z-index:600;min-width:280px;text-align:center;box-shadow:0 8px 32px rgba(0,0,0,0.7)';
|
||||||
|
d.innerHTML = `<div style="font-size:13px;color:#ccc;margin-bottom:14px">Add ${files.length} image(s)?</div>
|
||||||
|
<div style="display:flex;flex-direction:column;gap:8px">
|
||||||
|
<button class="btn primary" onclick="handleUploadToGroup(window._pasteFiles,'${gidSafe}');document.getElementById('pasteDialog')?.remove()">Add to “${gNameSafe}” — no poses</button>
|
||||||
|
<button class="btn" onclick="handleUpload(window._pasteFiles);document.getElementById('pasteDialog')?.remove()">New group (run poses)</button>
|
||||||
|
<button class="btn" onclick="document.getElementById('pasteDialog')?.remove()">Cancel</button>
|
||||||
|
</div>`;
|
||||||
|
window._pasteFiles = files;
|
||||||
|
document.body.appendChild(d);
|
||||||
|
setTimeout(() => document.getElementById('pasteDialog')?.remove(), 12000);
|
||||||
|
}
|
||||||
|
|
||||||
|
async function handleUploadToGroup(files, groupId) {
|
||||||
|
showToast(`Adding ${files.length} image(s) to group…`);
|
||||||
|
for (const file of files) {
|
||||||
|
const fd = new FormData();
|
||||||
|
fd.append('image', file);
|
||||||
|
fd.append('group_id', groupId);
|
||||||
|
fd.append('skip_poses', 'true');
|
||||||
|
try {
|
||||||
|
const r = await fetch(`${API}/upload`, { method: 'POST', body: fd });
|
||||||
|
if (!r.ok) showToast('Upload failed: ' + await r.text(), 'error');
|
||||||
|
} catch (e) { showToast('Upload error: ' + e, 'error'); }
|
||||||
|
}
|
||||||
|
showToast('Added to group', 'success');
|
||||||
|
refreshNow();
|
||||||
|
}
|
||||||
</script>
|
</script>
|
||||||
</body>
|
</body>
|
||||||
</html>
|
</html>
|
||||||
@@ -25,5 +25,6 @@
|
|||||||
"facefusion_dir": "~/facefusion",
|
"facefusion_dir": "~/facefusion",
|
||||||
"facefusion_venv": "~/facefusion-venv",
|
"facefusion_venv": "~/facefusion-venv",
|
||||||
"sam2_checkpoint": "~/.sam/sam2.1_hiera_base_plus.pt",
|
"sam2_checkpoint": "~/.sam/sam2.1_hiera_base_plus.pt",
|
||||||
"sam2_config": "configs/sam2.1/sam2.1_hiera_b+.yaml"
|
"sam2_config": "configs/sam2.1/sam2.1_hiera_b+.yaml",
|
||||||
|
"bg_removal": "sam2"
|
||||||
}
|
}
|
||||||
@@ -839,10 +839,63 @@ def _run_pipeline(
|
|||||||
}
|
}
|
||||||
graph[NODE_POSITIVE]["inputs"][img_key] = [node_id, 0]
|
graph[NODE_POSITIVE]["inputs"][img_key] = [node_id, 0]
|
||||||
|
|
||||||
# Transparency detection
|
# ── background-removal routing ────────────────────────────────────────────
|
||||||
is_transparent = any(kw in prompt.lower() for kw in ["transparent", "no background", "remove background", "alpha channel"])
|
# Two configurable strategies (config.json key "bg_removal"):
|
||||||
|
#
|
||||||
|
# "rembg" (default) — strip transparent keyword → Qwen renders a natural
|
||||||
|
# scene → rembg (U2Net) separates person from any complex background.
|
||||||
|
#
|
||||||
|
# "sam2" — replace transparent keyword with "black background" → Qwen
|
||||||
|
# renders a solid black BG → SAM2 bbox segmentation on a black image
|
||||||
|
# works perfectly because the contrast is maximal.
|
||||||
|
#
|
||||||
|
# Either way, explicit "black background" in the prompt always routes to
|
||||||
|
# SAM2 (the user already set up the ideal SAM2 input).
|
||||||
|
# ─────────────────────────────────────────────────────────────────────────
|
||||||
|
_TRANSPARENT_KWS = ["transparent background", "no background",
|
||||||
|
"remove background", "alpha channel"]
|
||||||
|
_BLACK_BG_KWS = ["black background"]
|
||||||
|
|
||||||
|
with open(CONFIG_PATH) as _cf:
|
||||||
|
_bg_conf = json.load(_cf)
|
||||||
|
bg_method = _bg_conf.get("bg_removal", "rembg") # "rembg" | "sam2"
|
||||||
|
|
||||||
|
is_transparent = any(kw in prompt.lower() for kw in _TRANSPARENT_KWS)
|
||||||
|
is_black_bg = any(kw in prompt.lower() for kw in _BLACK_BG_KWS)
|
||||||
|
post_process = None # "rembg" | "sam2"
|
||||||
|
|
||||||
if is_transparent:
|
if is_transparent:
|
||||||
graph[NODE_NEGATIVE]["inputs"]["prompt"] = "checkerboard, grid, pattern, texture, background details, watermark, deformed anatomy"
|
if bg_method == "sam2":
|
||||||
|
# Swap "transparent background" → "black background" so Qwen renders
|
||||||
|
# a pure-black BG that SAM2 can segment with maximal contrast.
|
||||||
|
cleaned = prompt
|
||||||
|
for kw in _TRANSPARENT_KWS:
|
||||||
|
cleaned = re.sub(re.escape(kw), "black background", cleaned, flags=re.IGNORECASE)
|
||||||
|
# Collapse duplicates if multiple keywords matched
|
||||||
|
cleaned = re.sub(r"(?i)(black background[\s,]*){2,}", "black background, ", cleaned)
|
||||||
|
cleaned = re.sub(r",\s*,", ",", cleaned).strip(", ")
|
||||||
|
graph[NODE_POSITIVE]["inputs"]["prompt"] = cleaned
|
||||||
|
graph[NODE_NEGATIVE]["inputs"]["prompt"] = (
|
||||||
|
"real background, outdoor scene, indoor scene, gradient, "
|
||||||
|
"colored background, watermark, deformed anatomy"
|
||||||
|
)
|
||||||
|
post_process = "sam2"
|
||||||
|
else:
|
||||||
|
# Strip the keyword so Qwen renders a natural scene; rembg handles
|
||||||
|
# any background complexity reliably.
|
||||||
|
cleaned = prompt
|
||||||
|
for kw in _TRANSPARENT_KWS:
|
||||||
|
cleaned = re.sub(re.escape(kw), "", cleaned, flags=re.IGNORECASE)
|
||||||
|
cleaned = re.sub(r",\s*,", ",", cleaned)
|
||||||
|
cleaned = re.sub(r",\s*$", "", cleaned.strip()).strip(", ")
|
||||||
|
graph[NODE_POSITIVE]["inputs"]["prompt"] = cleaned
|
||||||
|
graph[NODE_NEGATIVE]["inputs"]["prompt"] = "deformed anatomy, watermark, logo"
|
||||||
|
post_process = "rembg"
|
||||||
|
|
||||||
|
elif is_black_bg:
|
||||||
|
# Prompt already specifies a black background — ideal SAM2 input.
|
||||||
|
# Route to SAM2 regardless of the configured bg_removal method.
|
||||||
|
post_process = "sam2"
|
||||||
|
|
||||||
graph[NODE_LATENT]["inputs"]["width"] = w
|
graph[NODE_LATENT]["inputs"]["width"] = w
|
||||||
graph[NODE_LATENT]["inputs"]["height"] = h
|
graph[NODE_LATENT]["inputs"]["height"] = h
|
||||||
@@ -853,7 +906,13 @@ def _run_pipeline(
|
|||||||
outputs = _comfy_wait(prompt_id, time.time() + GEN_TIMEOUT)
|
outputs = _comfy_wait(prompt_id, time.time() + GEN_TIMEOUT)
|
||||||
png_bytes = _comfy_fetch_image(outputs)
|
png_bytes = _comfy_fetch_image(outputs)
|
||||||
|
|
||||||
if is_transparent:
|
if post_process == "sam2":
|
||||||
|
# Input has a black background (Qwen was told "black background").
|
||||||
|
# Use threshold-derived bbox so SAM2 gets a person-specific hint
|
||||||
|
# rather than the full frame — full-frame bbox inverts the mask on
|
||||||
|
# black-bg images because the large dark region scores higher.
|
||||||
|
png_bytes = _apply_transparency_black_bg(png_bytes)
|
||||||
|
elif post_process == "rembg":
|
||||||
png_bytes = _apply_transparency(png_bytes)
|
png_bytes = _apply_transparency(png_bytes)
|
||||||
|
|
||||||
return png_bytes
|
return png_bytes
|
||||||
@@ -891,7 +950,8 @@ def _move_to_trash(filepath: str):
|
|||||||
|
|
||||||
|
|
||||||
def _batch_worker(job_id: str, filenames: list, prompts: list[str], poses: list,
|
def _batch_worker(job_id: str, filenames: list, prompts: list[str], poses: list,
|
||||||
seed: int, max_area: int, group_id: str | None = None):
|
seed: int, max_area: int, group_id: str | None = None,
|
||||||
|
wireframe_ref: str | None = None, wireframe_time: float = 0.5):
|
||||||
output_dir = _load_output_dir()
|
output_dir = _load_output_dir()
|
||||||
for fname in filenames:
|
for fname in filenames:
|
||||||
actual_gid = None
|
actual_gid = None
|
||||||
@@ -915,6 +975,24 @@ def _batch_worker(job_id: str, filenames: list, prompts: list[str], poses: list,
|
|||||||
|
|
||||||
try:
|
try:
|
||||||
base_pil = Image.open(fpath).convert("RGB")
|
base_pil = Image.open(fpath).convert("RGB")
|
||||||
|
|
||||||
|
# Extract wireframe pose reference frame once per filename
|
||||||
|
pose_guide_pil = None
|
||||||
|
if wireframe_ref:
|
||||||
|
try:
|
||||||
|
wf_path = os.path.join(_load_wireframe_dir(), wireframe_ref)
|
||||||
|
cap = cv2.VideoCapture(wf_path)
|
||||||
|
total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
|
||||||
|
target_frame = max(0, min(total_frames - 1, int(total_frames * wireframe_time)))
|
||||||
|
cap.set(cv2.CAP_PROP_POS_FRAMES, target_frame)
|
||||||
|
ret, frame = cap.read()
|
||||||
|
cap.release()
|
||||||
|
if ret:
|
||||||
|
pose_guide_pil = Image.fromarray(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))
|
||||||
|
print(f"[batch] using wireframe {wireframe_ref} frame {target_frame}/{total_frames}")
|
||||||
|
except Exception as wf_err:
|
||||||
|
print(f"[batch] wireframe extract error: {wf_err}")
|
||||||
|
|
||||||
for prompt, pose in zip(prompts, poses):
|
for prompt, pose in zip(prompts, poses):
|
||||||
if jobs[job_id].get("cancelled"):
|
if jobs[job_id].get("cancelled"):
|
||||||
return
|
return
|
||||||
@@ -924,7 +1002,8 @@ def _batch_worker(job_id: str, filenames: list, prompts: list[str], poses: list,
|
|||||||
if pose and pose.lower().strip() in ROTATE_180_POSES:
|
if pose and pose.lower().strip() in ROTATE_180_POSES:
|
||||||
pil = pil.rotate(180)
|
pil = pil.rotate(180)
|
||||||
|
|
||||||
png = _run_pipeline(pil, prompt, seed, max_area)
|
extra_imgs = [pose_guide_pil] if pose_guide_pil else None
|
||||||
|
png = _run_pipeline(pil, prompt, seed, max_area, extra_images=extra_imgs)
|
||||||
ts = time.strftime("%Y%m%d_%H%M%S")
|
ts = time.strftime("%Y%m%d_%H%M%S")
|
||||||
clean_fname = naming.get_base_name(fname)
|
clean_fname = naming.get_base_name(fname)
|
||||||
out_name = f"{ts}_{clean_fname}"
|
out_name = f"{ts}_{clean_fname}"
|
||||||
@@ -1069,6 +1148,8 @@ class BatchRequest(BaseModel):
|
|||||||
max_area: int = 0
|
max_area: int = 0
|
||||||
group_id: str | None = None
|
group_id: str | None = None
|
||||||
poses: list[str | None] | None = None # pose name per prompt (same index), or None; None entries = no pose
|
poses: list[str | None] | None = None # pose name per prompt (same index), or None; None entries = no pose
|
||||||
|
wireframe_ref: str | None = None # wireframe video name to use as pose guide (image2 slot)
|
||||||
|
wireframe_time: float = 0.5 # normalized time (0–1) to extract the pose frame from
|
||||||
|
|
||||||
|
|
||||||
@app.post("/batch")
|
@app.post("/batch")
|
||||||
@@ -1085,6 +1166,7 @@ def start_batch(req: BatchRequest):
|
|||||||
t = threading.Thread(
|
t = threading.Thread(
|
||||||
target=_batch_worker,
|
target=_batch_worker,
|
||||||
args=(job_id, req.filenames, prompts, poses, req.seed, req.max_area, req.group_id),
|
args=(job_id, req.filenames, prompts, poses, req.seed, req.max_area, req.group_id),
|
||||||
|
kwargs={"wireframe_ref": req.wireframe_ref, "wireframe_time": req.wireframe_time},
|
||||||
daemon=True,
|
daemon=True,
|
||||||
)
|
)
|
||||||
t.start()
|
t.start()
|
||||||
@@ -1207,6 +1289,35 @@ def list_videos():
|
|||||||
return {"videos": videos, "wireframe_dir": wireframe_dir}
|
return {"videos": videos, "wireframe_dir": wireframe_dir}
|
||||||
|
|
||||||
|
|
||||||
|
@app.get("/wireframe/frame/{video_name}")
|
||||||
|
def wireframe_frame(video_name: str, t: float = 0.5):
|
||||||
|
"""Extract a single frame at normalized time t (0–1) from a wireframe video. Returns PNG."""
|
||||||
|
wireframe_dir = _load_wireframe_dir()
|
||||||
|
video_path = os.path.join(wireframe_dir, video_name)
|
||||||
|
if not os.path.exists(video_path):
|
||||||
|
raise HTTPException(404, f"Video not found: {video_name}")
|
||||||
|
try:
|
||||||
|
cap = cv2.VideoCapture(video_path)
|
||||||
|
total = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
|
||||||
|
target = max(0, min(total - 1, int(total * max(0.0, min(1.0, t)))))
|
||||||
|
cap.set(cv2.CAP_PROP_POS_FRAMES, target)
|
||||||
|
ret, frame = cap.read()
|
||||||
|
cap.release()
|
||||||
|
if not ret:
|
||||||
|
raise HTTPException(500, "Could not read frame")
|
||||||
|
rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
|
||||||
|
pil = Image.fromarray(rgb)
|
||||||
|
buf = io.BytesIO()
|
||||||
|
pil.save(buf, format="PNG")
|
||||||
|
buf.seek(0)
|
||||||
|
from fastapi.responses import Response
|
||||||
|
return Response(content=buf.getvalue(), media_type="image/png")
|
||||||
|
except HTTPException:
|
||||||
|
raise
|
||||||
|
except Exception as e:
|
||||||
|
raise HTTPException(500, f"Frame extraction error: {e}")
|
||||||
|
|
||||||
|
|
||||||
@app.get("/wireframe/duration/{video_name}")
|
@app.get("/wireframe/duration/{video_name}")
|
||||||
def wireframe_duration(video_name: str):
|
def wireframe_duration(video_name: str):
|
||||||
"""Return duration (seconds) of a wireframe video via ffprobe."""
|
"""Return duration (seconds) of a wireframe video via ffprobe."""
|
||||||
@@ -1573,6 +1684,42 @@ def _crop_to_bbox(pil_img: Image.Image, margin: int = 20, top_margin: int = 20,
|
|||||||
return cropped
|
return cropped
|
||||||
|
|
||||||
|
|
||||||
|
def _extract_face_bg(filename: str, fpath: str):
|
||||||
|
"""Background task: detect largest face, crop with padding, save as {group_id}_face.png."""
|
||||||
|
try:
|
||||||
|
app_fa, _ = _load_faceswapper()
|
||||||
|
bgr = cv2.imread(fpath)
|
||||||
|
if bgr is None:
|
||||||
|
print(f"[extract-face] cannot read {fpath}")
|
||||||
|
return
|
||||||
|
faces = app_fa.get(bgr)
|
||||||
|
if not faces:
|
||||||
|
print(f"[extract-face] no face detected in {filename}")
|
||||||
|
return
|
||||||
|
face = max(faces, key=lambda f: (f.bbox[2] - f.bbox[0]) * (f.bbox[3] - f.bbox[1]))
|
||||||
|
x1, y1, x2, y2 = [int(v) for v in face.bbox]
|
||||||
|
h, w = bgr.shape[:2]
|
||||||
|
pad = int((y2 - y1) * 0.5)
|
||||||
|
x1 = max(0, x1 - pad)
|
||||||
|
y1 = max(0, y1 - pad * 2) # extra headroom above face
|
||||||
|
x2 = min(w, x2 + pad)
|
||||||
|
y2 = min(h, y2 + int(pad * 0.3))
|
||||||
|
pil = Image.open(fpath).convert("RGBA")
|
||||||
|
cropped = pil.crop((x1, y1, x2, y2))
|
||||||
|
person = database.get_person(filename)
|
||||||
|
group_id = person[1] if person else None
|
||||||
|
gid_tag = (group_id or "face").replace("/", "_")
|
||||||
|
face_fname = f"{gid_tag}_face.png"
|
||||||
|
face_path = os.path.join(os.path.dirname(fpath), face_fname)
|
||||||
|
cropped.save(face_path)
|
||||||
|
database.upsert_person(face_fname, filepath=face_path, group_id=group_id,
|
||||||
|
name=person[0] if person else None,
|
||||||
|
source_refs=json.dumps([filename]))
|
||||||
|
print(f"[extract-face] saved {face_fname}")
|
||||||
|
except Exception as e:
|
||||||
|
print(f"[extract-face] error for {filename}: {e}")
|
||||||
|
|
||||||
|
|
||||||
def _process_upload(file_path: str, filename: str, prompts: list[str], name: str | None = None, group_id: str | None = None):
|
def _process_upload(file_path: str, filename: str, prompts: list[str], name: str | None = None, group_id: str | None = None):
|
||||||
output_dir = _load_output_dir()
|
output_dir = _load_output_dir()
|
||||||
try:
|
try:
|
||||||
@@ -1631,40 +1778,49 @@ def upload_image(
|
|||||||
image: UploadFile = File(...),
|
image: UploadFile = File(...),
|
||||||
prompts: str = Form(""),
|
prompts: str = Form(""),
|
||||||
name: str = Form(None),
|
name: str = Form(None),
|
||||||
|
group_id: str = Form(None), # optional: add to existing group
|
||||||
|
skip_poses: bool = Form(False), # optional: skip base_prompts generation
|
||||||
):
|
):
|
||||||
# Load config to get output_dir (we use output_dir for UI uploads to avoid watcher conflict)
|
# Load config to get output_dir (we use output_dir for UI uploads to avoid watcher conflict)
|
||||||
with open(CONFIG_PATH, "r") as f:
|
with open(CONFIG_PATH, "r") as f:
|
||||||
conf = json.load(f)
|
conf = json.load(f)
|
||||||
output_dir = _load_output_dir()
|
output_dir = _load_output_dir()
|
||||||
os.makedirs(output_dir, exist_ok=True)
|
os.makedirs(output_dir, exist_ok=True)
|
||||||
|
|
||||||
ts = time.strftime("%Y%m%d_%H%M%S")
|
ts = time.strftime("%Y%m%d_%H%M%S")
|
||||||
safe_filename = re.sub(r'[^a-zA-Z0-9_.-]', '_', image.filename)
|
safe_filename = re.sub(r'[^a-zA-Z0-9_.-]', '_', image.filename or "paste")
|
||||||
# Ensure extension
|
# Ensure extension
|
||||||
if not safe_filename.lower().endswith(('.png', '.jpg', '.jpeg', '.webp')):
|
if not safe_filename.lower().endswith(('.png', '.jpg', '.jpeg', '.webp')):
|
||||||
safe_filename += ".png"
|
safe_filename += ".png"
|
||||||
|
|
||||||
filename = f"{ts}_{safe_filename}"
|
filename = f"{ts}_{safe_filename}"
|
||||||
file_path = os.path.join(output_dir, filename)
|
file_path = os.path.join(output_dir, filename)
|
||||||
|
|
||||||
with open(file_path, "wb") as f:
|
with open(file_path, "wb") as f:
|
||||||
shutil.copyfileobj(image.file, f)
|
shutil.copyfileobj(image.file, f)
|
||||||
|
|
||||||
|
# Fast path: add to existing group without pose generation
|
||||||
|
if group_id and skip_poses:
|
||||||
|
sort_order = database.get_next_sort_order(group_id)
|
||||||
|
database.upsert_person(filename, filepath=file_path, group_id=group_id,
|
||||||
|
sort_order=sort_order)
|
||||||
|
return {"status": "added", "filename": filename, "group_id": group_id}
|
||||||
|
|
||||||
prompt_list = [p.strip() for p in prompts.split(",") if p.strip()]
|
prompt_list = [p.strip() for p in prompts.split(",") if p.strip()]
|
||||||
|
|
||||||
# Add base-set prompts if defined in config
|
# Add base-set prompts if defined in config
|
||||||
base_prompts = conf.get("base_prompts", [])
|
base_prompts = conf.get("base_prompts", [])
|
||||||
if isinstance(base_prompts, list):
|
if isinstance(base_prompts, list):
|
||||||
prompt_list.extend(base_prompts)
|
prompt_list.extend(base_prompts)
|
||||||
|
|
||||||
if not prompt_list:
|
if not prompt_list:
|
||||||
# Use default prompt from config
|
# Use default prompt from config
|
||||||
prompt_list = [conf.get("prompt", "high quality, masterpiece")]
|
prompt_list = [conf.get("prompt", "high quality, masterpiece")]
|
||||||
|
|
||||||
group_id = f"up_{uuid.uuid4().hex[:8]}" # unique per upload; avoids collisions when pasting generic filenames
|
effective_gid = group_id or f"up_{uuid.uuid4().hex[:8]}"
|
||||||
background_tasks.add_task(_process_upload, file_path, filename, prompt_list, name, group_id)
|
background_tasks.add_task(_process_upload, file_path, filename, prompt_list, name, effective_gid)
|
||||||
|
|
||||||
return {"status": "processing", "filename": filename, "group_id": group_id, "prompts": prompt_list}
|
return {"status": "processing", "filename": filename, "group_id": effective_gid, "prompts": prompt_list}
|
||||||
|
|
||||||
|
|
||||||
@app.post("/edit")
|
@app.post("/edit")
|
||||||
@@ -1717,7 +1873,7 @@ def unarchive_image(filename: str):
|
|||||||
|
|
||||||
|
|
||||||
@app.post("/images/{filename}/set-preferred")
|
@app.post("/images/{filename}/set-preferred")
|
||||||
def set_image_preferred(filename: str):
|
def set_image_preferred(filename: str, background_tasks: BackgroundTasks):
|
||||||
"""Make this image sort_order=0 within its group, shifting others to 1,2,..."""
|
"""Make this image sort_order=0 within its group, shifting others to 1,2,..."""
|
||||||
person = database.get_person(filename)
|
person = database.get_person(filename)
|
||||||
if not person:
|
if not person:
|
||||||
@@ -1728,9 +1884,23 @@ def set_image_preferred(filename: str):
|
|||||||
rows = database.get_group_order(group_id)
|
rows = database.get_group_order(group_id)
|
||||||
others = [r[0] for r in rows if r[0] != filename]
|
others = [r[0] for r in rows if r[0] != filename]
|
||||||
database.set_group_order(group_id, [filename] + others)
|
database.set_group_order(group_id, [filename] + others)
|
||||||
|
fpath = os.path.join(_load_output_dir(), filename)
|
||||||
|
if os.path.exists(fpath):
|
||||||
|
background_tasks.add_task(_extract_face_bg, filename, fpath)
|
||||||
return {"filename": filename, "group_id": group_id}
|
return {"filename": filename, "group_id": group_id}
|
||||||
|
|
||||||
|
|
||||||
|
@app.post("/images/{filename}/extract-face")
|
||||||
|
def extract_face_endpoint(filename: str, background_tasks: BackgroundTasks):
|
||||||
|
"""Detect and crop the largest face from image; saves as {group_id}_face.png."""
|
||||||
|
output_dir = _load_output_dir()
|
||||||
|
fpath = os.path.join(output_dir, filename)
|
||||||
|
if not os.path.exists(fpath):
|
||||||
|
raise HTTPException(404, "not found")
|
||||||
|
background_tasks.add_task(_extract_face_bg, filename, fpath)
|
||||||
|
return {"status": "queued", "filename": filename}
|
||||||
|
|
||||||
|
|
||||||
@app.post("/images/{filename}/undress")
|
@app.post("/images/{filename}/undress")
|
||||||
def undress_image(filename: str, background_tasks: BackgroundTasks):
|
def undress_image(filename: str, background_tasks: BackgroundTasks):
|
||||||
"""Queue a generation using the undress prompt on the given image."""
|
"""Queue a generation using the undress prompt on the given image."""
|
||||||
@@ -1967,14 +2137,14 @@ def _load_sam2():
|
|||||||
|
|
||||||
|
|
||||||
def _apply_transparency_sam2(png_bytes: bytes) -> bytes:
|
def _apply_transparency_sam2(png_bytes: bytes) -> bytes:
|
||||||
"""Remove background with SAM2 bbox-based segmentation; fallback to rembg.
|
"""Remove background with SAM2 bbox segmentation; fallback to rembg.
|
||||||
|
|
||||||
Mimics the reference approach (bbox → SAM2) but without an external
|
Uses a near-full-frame bbox so SAM2 finds the largest foreground object
|
||||||
detector: we pass a generous bbox covering the central subject area.
|
(the person) regardless of rotation or pose. This works well because
|
||||||
For portraits/full-body shots the subject fills most of the frame, so a
|
"transparent background" is stripped from the Qwen prompt upstream, so the
|
||||||
5 % margin bbox reliably captures hair, glasses, and sandals without the
|
model renders a solid real background — giving SAM2 clear contrast to work
|
||||||
point-prompt clipping issues. multimask_output=True lets SAM2 propose
|
with. Point prompts were tried but produced holes in ¾-rotated poses
|
||||||
three masks; we pick the highest-scoring one.
|
because the spine-column seeds land on background when the body is offset.
|
||||||
"""
|
"""
|
||||||
predictor = _load_sam2()
|
predictor = _load_sam2()
|
||||||
if predictor is False:
|
if predictor is False:
|
||||||
@@ -1985,31 +2155,133 @@ def _apply_transparency_sam2(png_bytes: bytes) -> bytes:
|
|||||||
img = Image.open(io.BytesIO(png_bytes)).convert("RGB")
|
img = Image.open(io.BytesIO(png_bytes)).convert("RGB")
|
||||||
arr = np.array(img)
|
arr = np.array(img)
|
||||||
h, w = arr.shape[:2]
|
h, w = arr.shape[:2]
|
||||||
# Generous bbox — 5 % margin H, 2 % margin V — covers the whole subject
|
|
||||||
box = np.array([[int(w * 0.05), int(h * 0.02),
|
# Near-full-frame bbox — 1 % margin so hair / shoes are inside the hint.
|
||||||
int(w * 0.95), int(h * 0.98)]], dtype=np.float32)
|
# SAM2 treats this as "find the prominent object within this region".
|
||||||
|
box = np.array([[int(w * 0.01), int(h * 0.01),
|
||||||
|
int(w * 0.99), int(h * 0.99)]], dtype=np.float32)
|
||||||
|
|
||||||
with torch.inference_mode():
|
with torch.inference_mode():
|
||||||
predictor.set_image(arr)
|
predictor.set_image(arr)
|
||||||
masks, scores, _ = predictor.predict(
|
masks, scores, _ = predictor.predict(
|
||||||
box=box,
|
box=box,
|
||||||
multimask_output=True,
|
multimask_output=True,
|
||||||
)
|
)
|
||||||
|
|
||||||
if masks is None or len(masks) == 0:
|
if masks is None or len(masks) == 0:
|
||||||
|
print("[sam2] no masks returned, falling back to rembg")
|
||||||
return _apply_transparency(png_bytes)
|
return _apply_transparency(png_bytes)
|
||||||
|
|
||||||
best = masks[int(np.argmax(scores))]
|
best = masks[int(np.argmax(scores))]
|
||||||
|
|
||||||
|
# Sanity check: a person should cover 5 %–92 % of the frame
|
||||||
|
coverage = float(best.sum()) / (h * w)
|
||||||
|
if coverage < 0.05 or coverage > 0.92:
|
||||||
|
print(f"[sam2] mask coverage {coverage:.1%} out of range, falling back to rembg")
|
||||||
|
return _apply_transparency(png_bytes)
|
||||||
|
|
||||||
mask_np = best.astype(np.uint8) * 255
|
mask_np = best.astype(np.uint8) * 255
|
||||||
|
|
||||||
|
# Soft anti-aliased edge (radius 1 keeps accessory detail)
|
||||||
|
try:
|
||||||
|
from PIL import ImageFilter
|
||||||
|
alpha_img = Image.fromarray(mask_np, mode="L")
|
||||||
|
alpha_img = alpha_img.filter(ImageFilter.GaussianBlur(radius=1))
|
||||||
|
except Exception:
|
||||||
|
alpha_img = Image.fromarray(mask_np, mode="L")
|
||||||
|
|
||||||
rgba = img.convert("RGBA")
|
rgba = img.convert("RGBA")
|
||||||
r, g, b, _ = rgba.split()
|
r, g, b, _ = rgba.split()
|
||||||
alpha = Image.fromarray(mask_np, mode="L")
|
out = Image.merge("RGBA", (r, g, b, alpha_img))
|
||||||
out = Image.merge("RGBA", (r, g, b, alpha))
|
|
||||||
buf = io.BytesIO()
|
buf = io.BytesIO()
|
||||||
out.save(buf, format="PNG")
|
out.save(buf, format="PNG")
|
||||||
|
print(f"[sam2] mask OK ({coverage:.1%} coverage)")
|
||||||
return buf.getvalue()
|
return buf.getvalue()
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
print(f"[sam2] inference error, falling back to rembg: {e}")
|
print(f"[sam2] inference error, falling back to rembg: {e}")
|
||||||
return _apply_transparency(png_bytes)
|
return _apply_transparency(png_bytes)
|
||||||
|
|
||||||
|
|
||||||
|
def _apply_transparency_black_bg(png_bytes: bytes) -> bytes:
|
||||||
|
"""Background removal for black-background Qwen output (bg_removal=sam2 mode).
|
||||||
|
|
||||||
|
Strategy:
|
||||||
|
1. Threshold: any pixel with max-channel > 25 is person (non-black).
|
||||||
|
This correctly identifies the subject regardless of pose or rotation.
|
||||||
|
2. Derive a tight person bounding-box from the threshold mask.
|
||||||
|
3. Run SAM2 with that box for sub-pixel edge refinement.
|
||||||
|
Accept SAM2 result only when its coverage is close (±30 pp) to the
|
||||||
|
threshold estimate — this rejects the inverted-mask failure mode where
|
||||||
|
SAM2 picks the large dark region as the "object".
|
||||||
|
4. Fall back to the threshold mask (Gaussian-blurred edges) if SAM2
|
||||||
|
is unavailable, errors, or diverges.
|
||||||
|
|
||||||
|
Do NOT use the full-frame bbox here: on black-background images the large
|
||||||
|
dark region scores higher than the person, causing SAM2 to invert the mask.
|
||||||
|
"""
|
||||||
|
import numpy as np
|
||||||
|
import torch
|
||||||
|
from PIL import ImageFilter
|
||||||
|
|
||||||
|
img = Image.open(io.BytesIO(png_bytes)).convert("RGB")
|
||||||
|
arr = np.array(img)
|
||||||
|
h, w = arr.shape[:2]
|
||||||
|
|
||||||
|
# Step 1 — threshold: non-black pixels are the person
|
||||||
|
is_person = np.max(arr, axis=2) > 25
|
||||||
|
thresh_cov = float(is_person.sum()) / (h * w)
|
||||||
|
print(f"[bg-black] threshold coverage: {thresh_cov:.1%}")
|
||||||
|
|
||||||
|
if not is_person.any():
|
||||||
|
print("[bg-black] all-black image — falling back to rembg")
|
||||||
|
return _apply_transparency(png_bytes)
|
||||||
|
|
||||||
|
# Step 2 — tight bounding box from threshold
|
||||||
|
rows = np.any(is_person, axis=1)
|
||||||
|
cols = np.any(is_person, axis=0)
|
||||||
|
rmin = int(np.where(rows)[0][0]); rmax = int(np.where(rows)[0][-1])
|
||||||
|
cmin = int(np.where(cols)[0][0]); cmax = int(np.where(cols)[0][-1])
|
||||||
|
margin = int(min(h, w) * 0.02)
|
||||||
|
x1 = max(0, cmin - margin); y1 = max(0, rmin - margin)
|
||||||
|
x2 = min(w, cmax + margin); y2 = min(h, rmax + margin)
|
||||||
|
|
||||||
|
# Step 3 — SAM2 with the person-specific bbox
|
||||||
|
predictor = _load_sam2()
|
||||||
|
if predictor is not False:
|
||||||
|
box = np.array([[x1, y1, x2, y2]], dtype=np.float32)
|
||||||
|
try:
|
||||||
|
with torch.inference_mode():
|
||||||
|
predictor.set_image(arr)
|
||||||
|
masks, scores, _ = predictor.predict(box=box, multimask_output=True)
|
||||||
|
|
||||||
|
if masks is not None and len(masks) > 0:
|
||||||
|
best = masks[int(np.argmax(scores))]
|
||||||
|
sam_cov = float(best.sum()) / (h * w)
|
||||||
|
print(f"[bg-black] SAM2 coverage: {sam_cov:.1%}")
|
||||||
|
|
||||||
|
if 0.03 < sam_cov < 0.95 and abs(sam_cov - thresh_cov) < 0.30:
|
||||||
|
mask_np = best.astype(np.uint8) * 255
|
||||||
|
alpha_img = Image.fromarray(mask_np, "L").filter(ImageFilter.GaussianBlur(radius=1))
|
||||||
|
rgba = img.convert("RGBA"); r, g, b, _ = rgba.split()
|
||||||
|
out = Image.merge("RGBA", (r, g, b, alpha_img))
|
||||||
|
buf = io.BytesIO(); out.save(buf, "PNG")
|
||||||
|
print(f"[bg-black] SAM2 accepted ✓")
|
||||||
|
return buf.getvalue()
|
||||||
|
else:
|
||||||
|
print(f"[bg-black] SAM2 diverged ({sam_cov:.1%} vs {thresh_cov:.1%}) — threshold fallback")
|
||||||
|
except Exception as e:
|
||||||
|
print(f"[bg-black] SAM2 error: {e} — threshold fallback")
|
||||||
|
|
||||||
|
# Step 4 — fallback: threshold mask with soft edge blur
|
||||||
|
print("[bg-black] using threshold mask")
|
||||||
|
mask_np = is_person.astype(np.uint8) * 255
|
||||||
|
alpha_img = Image.fromarray(mask_np, "L").filter(ImageFilter.GaussianBlur(radius=2))
|
||||||
|
rgba = img.convert("RGBA"); r, g, b, _ = rgba.split()
|
||||||
|
out = Image.merge("RGBA", (r, g, b, alpha_img))
|
||||||
|
buf = io.BytesIO(); out.save(buf, "PNG")
|
||||||
|
return buf.getvalue()
|
||||||
|
|
||||||
|
|
||||||
@app.post("/remove-background-sam/{filename}")
|
@app.post("/remove-background-sam/{filename}")
|
||||||
def remove_background_sam(filename: str):
|
def remove_background_sam(filename: str):
|
||||||
"""SAM2-based background removal.
|
"""SAM2-based background removal.
|
||||||
|
|||||||
191
tour-comfy/test_transparency.py
Normal file
191
tour-comfy/test_transparency.py
Normal file
@@ -0,0 +1,191 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
"""
|
||||||
|
Validate background removal strategies.
|
||||||
|
|
||||||
|
Usage:
|
||||||
|
python test_transparency.py [image.png ...]
|
||||||
|
|
||||||
|
Writes comparison files next to each input:
|
||||||
|
*_rembg.png — pure rembg (bg_removal=rembg path)
|
||||||
|
*_blackbg.png — simulated black-bg composite (what Qwen renders in sam2 mode)
|
||||||
|
*_thresh.png — threshold mask only (non-black pixels → person)
|
||||||
|
*_thresh_sam2.png — threshold bbox → SAM2 edge refinement (new sam2 mode path)
|
||||||
|
"""
|
||||||
|
import io, sys, os
|
||||||
|
import numpy as np
|
||||||
|
from PIL import Image, ImageFilter
|
||||||
|
|
||||||
|
OUTPUT_DIR = "/mnt/zim/tour-comfy/output"
|
||||||
|
VENV_SITE = "/home/mike/comfyui/venv/lib/python3.13/site-packages"
|
||||||
|
SAM2_CKPT = os.path.expanduser("~/.sam/sam2.1_hiera_base_plus.pt")
|
||||||
|
SAM2_CFG = "configs/sam2.1/sam2.1_hiera_b+.yaml"
|
||||||
|
|
||||||
|
|
||||||
|
# ── rembg ──────────────────────────────────────────────────────────────────────
|
||||||
|
def apply_rembg(png_bytes: bytes) -> bytes:
|
||||||
|
from rembg import remove
|
||||||
|
return remove(png_bytes)
|
||||||
|
|
||||||
|
|
||||||
|
# ── SAM2 loader ────────────────────────────────────────────────────────────────
|
||||||
|
_predictor = None
|
||||||
|
def load_sam2():
|
||||||
|
global _predictor
|
||||||
|
if _predictor is not None:
|
||||||
|
return _predictor
|
||||||
|
try:
|
||||||
|
import torch
|
||||||
|
from sam2.build_sam import build_sam2
|
||||||
|
from sam2.sam2_image_predictor import SAM2ImagePredictor
|
||||||
|
model = build_sam2(SAM2_CFG, SAM2_CKPT, device="cuda")
|
||||||
|
_predictor = SAM2ImagePredictor(model)
|
||||||
|
print("[sam2] loaded")
|
||||||
|
except Exception as e:
|
||||||
|
print(f"[sam2] FAILED: {e}")
|
||||||
|
_predictor = False
|
||||||
|
return _predictor
|
||||||
|
|
||||||
|
|
||||||
|
# ── Simulate black-bg Qwen output ─────────────────────────────────────────────
|
||||||
|
def make_black_bg(png_bytes: bytes) -> bytes:
|
||||||
|
"""Composite a rembg cutout onto pure black — simulates Qwen 'black background' output."""
|
||||||
|
rgba = Image.open(io.BytesIO(apply_rembg(png_bytes))).convert("RGBA")
|
||||||
|
bg = Image.new("RGBA", rgba.size, (0, 0, 0, 255))
|
||||||
|
bg.paste(rgba, mask=rgba.split()[3])
|
||||||
|
out = bg.convert("RGB")
|
||||||
|
buf = io.BytesIO(); out.save(buf, "PNG"); return buf.getvalue()
|
||||||
|
|
||||||
|
|
||||||
|
# ── Threshold-only mask ────────────────────────────────────────────────────────
|
||||||
|
def apply_threshold_mask(png_bytes: bytes, threshold: int = 25) -> bytes:
|
||||||
|
"""Find non-black pixels → person mask. No SAM2 needed."""
|
||||||
|
img = Image.open(io.BytesIO(png_bytes)).convert("RGB")
|
||||||
|
arr = np.array(img)
|
||||||
|
h, w = arr.shape[:2]
|
||||||
|
|
||||||
|
is_person = np.max(arr, axis=2) > threshold
|
||||||
|
coverage = is_person.sum() / (h * w)
|
||||||
|
print(f" [threshold] person coverage: {coverage:.1%}")
|
||||||
|
|
||||||
|
if not is_person.any():
|
||||||
|
print(" [threshold] all-black image — no person found")
|
||||||
|
return png_bytes
|
||||||
|
|
||||||
|
mask_np = is_person.astype(np.uint8) * 255
|
||||||
|
alpha_img = Image.fromarray(mask_np, "L").filter(ImageFilter.GaussianBlur(radius=2))
|
||||||
|
rgba = img.convert("RGBA"); r, g, b, _ = rgba.split()
|
||||||
|
out = Image.merge("RGBA", (r, g, b, alpha_img))
|
||||||
|
buf = io.BytesIO(); out.save(buf, "PNG"); return buf.getvalue()
|
||||||
|
|
||||||
|
|
||||||
|
# ── NEW: Threshold bbox → SAM2 refinement (sam2 mode path) ────────────────────
|
||||||
|
def apply_thresh_sam2(png_bytes: bytes, threshold: int = 25) -> bytes:
|
||||||
|
"""
|
||||||
|
For black-background Qwen output:
|
||||||
|
1. Threshold to find person bbox (non-black pixels)
|
||||||
|
2. Run SAM2 with that tight bbox for clean edge refinement
|
||||||
|
3. Fallback to threshold mask if SAM2 unavailable or mask looks wrong
|
||||||
|
"""
|
||||||
|
import torch
|
||||||
|
|
||||||
|
img = Image.open(io.BytesIO(png_bytes)).convert("RGB")
|
||||||
|
arr = np.array(img)
|
||||||
|
h, w = arr.shape[:2]
|
||||||
|
|
||||||
|
# Step 1 — threshold
|
||||||
|
is_person = np.max(arr, axis=2) > threshold
|
||||||
|
thresh_cov = is_person.sum() / (h * w)
|
||||||
|
print(f" [thresh_sam2] threshold person coverage: {thresh_cov:.1%}")
|
||||||
|
|
||||||
|
if not is_person.any():
|
||||||
|
print(" [thresh_sam2] all-black — fallback to rembg")
|
||||||
|
return apply_rembg(png_bytes)
|
||||||
|
|
||||||
|
rows = np.any(is_person, axis=1)
|
||||||
|
cols = np.any(is_person, axis=0)
|
||||||
|
rmin = int(np.where(rows)[0][0]); rmax = int(np.where(rows)[0][-1])
|
||||||
|
cmin = int(np.where(cols)[0][0]); cmax = int(np.where(cols)[0][-1])
|
||||||
|
|
||||||
|
margin = int(min(h, w) * 0.02)
|
||||||
|
y1 = max(0, rmin - margin); y2 = min(h, rmax + margin)
|
||||||
|
x1 = max(0, cmin - margin); x2 = min(w, cmax + margin)
|
||||||
|
print(f" [thresh_sam2] person bbox (+margin): ({x1},{y1})-({x2},{y2})")
|
||||||
|
|
||||||
|
# Step 2 — SAM2 with person-specific bbox
|
||||||
|
predictor = load_sam2()
|
||||||
|
if predictor is not False:
|
||||||
|
box = np.array([[x1, y1, x2, y2]], dtype=np.float32)
|
||||||
|
try:
|
||||||
|
with torch.inference_mode():
|
||||||
|
predictor.set_image(arr)
|
||||||
|
masks, scores, _ = predictor.predict(box=box, multimask_output=True)
|
||||||
|
|
||||||
|
if masks is not None and len(masks) > 0:
|
||||||
|
best = masks[int(np.argmax(scores))]
|
||||||
|
sam_cov = float(best.sum()) / (h * w)
|
||||||
|
print(f" [thresh_sam2] SAM2 coverage: {sam_cov:.1%} (threshold was {thresh_cov:.1%})")
|
||||||
|
|
||||||
|
# Accept SAM2 result if coverage is within reasonable range of threshold
|
||||||
|
if 0.03 < sam_cov < 0.95 and abs(sam_cov - thresh_cov) < 0.30:
|
||||||
|
mask_np = best.astype(np.uint8) * 255
|
||||||
|
alpha_img = Image.fromarray(mask_np, "L").filter(ImageFilter.GaussianBlur(radius=1))
|
||||||
|
rgba = img.convert("RGBA"); r, g, b, _ = rgba.split()
|
||||||
|
out = Image.merge("RGBA", (r, g, b, alpha_img))
|
||||||
|
buf = io.BytesIO(); out.save(buf, "PNG")
|
||||||
|
print(" [thresh_sam2] SAM2 result accepted ✓")
|
||||||
|
return buf.getvalue()
|
||||||
|
else:
|
||||||
|
print(f" [thresh_sam2] SAM2 coverage diverged from threshold — using threshold mask")
|
||||||
|
except Exception as e:
|
||||||
|
print(f" [thresh_sam2] SAM2 error: {e} — using threshold mask")
|
||||||
|
else:
|
||||||
|
print(" [thresh_sam2] SAM2 not available — using threshold mask")
|
||||||
|
|
||||||
|
# Step 3 — fallback: threshold mask with soft edges
|
||||||
|
mask_np = is_person.astype(np.uint8) * 255
|
||||||
|
alpha_img = Image.fromarray(mask_np, "L").filter(ImageFilter.GaussianBlur(radius=2))
|
||||||
|
rgba = img.convert("RGBA"); r, g, b, _ = rgba.split()
|
||||||
|
out = Image.merge("RGBA", (r, g, b, alpha_img))
|
||||||
|
buf = io.BytesIO(); out.save(buf, "PNG")
|
||||||
|
print(" [thresh_sam2] threshold mask used as fallback")
|
||||||
|
return buf.getvalue()
|
||||||
|
|
||||||
|
|
||||||
|
# ── main ───────────────────────────────────────────────────────────────────────
|
||||||
|
if __name__ == "__main__":
|
||||||
|
paths = sys.argv[1:] if len(sys.argv) > 1 else [
|
||||||
|
os.path.join(OUTPUT_DIR, "20260622_181910_0_20260619_124038_image.png"),
|
||||||
|
]
|
||||||
|
|
||||||
|
for path in paths:
|
||||||
|
if not os.path.exists(path):
|
||||||
|
print(f"SKIP (not found): {path}"); continue
|
||||||
|
stem = os.path.splitext(path)[0]
|
||||||
|
print(f"\n══ {os.path.basename(path)} ══")
|
||||||
|
with open(path, "rb") as f:
|
||||||
|
raw = f.read()
|
||||||
|
|
||||||
|
print("1. rembg (bg_removal=rembg path)...")
|
||||||
|
rb = apply_rembg(raw)
|
||||||
|
with open(stem + "_rembg.png", "wb") as f: f.write(rb)
|
||||||
|
print(f" → {os.path.basename(stem)}_rembg.png")
|
||||||
|
|
||||||
|
print("2. Simulate black-bg Qwen output...")
|
||||||
|
bb = make_black_bg(raw)
|
||||||
|
with open(stem + "_blackbg.png", "wb") as f: f.write(bb)
|
||||||
|
print(f" → {os.path.basename(stem)}_blackbg.png")
|
||||||
|
|
||||||
|
print("3. Threshold-only mask on black-bg image...")
|
||||||
|
tm = apply_threshold_mask(bb)
|
||||||
|
with open(stem + "_thresh.png", "wb") as f: f.write(tm)
|
||||||
|
print(f" → {os.path.basename(stem)}_thresh.png")
|
||||||
|
|
||||||
|
print("4. Threshold bbox → SAM2 refinement on black-bg image (NEW sam2 mode path)...")
|
||||||
|
ts = apply_thresh_sam2(bb)
|
||||||
|
with open(stem + "_thresh_sam2.png", "wb") as f: f.write(ts)
|
||||||
|
print(f" → {os.path.basename(stem)}_thresh_sam2.png")
|
||||||
|
|
||||||
|
print("\n── Done ──")
|
||||||
|
print(" *_rembg.png rembg on real background (bg_removal=rembg path)")
|
||||||
|
print(" *_thresh.png threshold-only on black bg")
|
||||||
|
print(" *_thresh_sam2.png threshold-bbox → SAM2 on black bg (NEW sam2 mode path)")
|
||||||
Reference in New Issue
Block a user