Spaces:
Sleeping
Sleeping
Upload 17 files
#8
by kajalan - opened
- .env.example +5 -0
- Dockerfile +9 -9
- README.md +39 -332
- docker-compose.yml +3 -3
.env.example
CHANGED
|
@@ -7,6 +7,11 @@ HOST=0.0.0.0
|
|
| 7 |
PORT=8000
|
| 8 |
DEBUG=false
|
| 9 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
# ── Model ─────────────────────────────────────────────────────────────────────
|
| 11 |
# Recommended CPU models (smallest to largest):
|
| 12 |
#
|
|
|
|
| 7 |
PORT=8000
|
| 8 |
DEBUG=false
|
| 9 |
|
| 10 |
+
# ── Hugging Face ──────────────────────────────────────────────────────────────
|
| 11 |
+
# Get your free token at https://huggingface.co/settings/tokens
|
| 12 |
+
# Removes the rate-limit warning and speeds up model file resolution
|
| 13 |
+
HF_TOKEN=
|
| 14 |
+
|
| 15 |
# ── Model ─────────────────────────────────────────────────────────────────────
|
| 16 |
# Recommended CPU models (smallest to largest):
|
| 17 |
#
|
Dockerfile
CHANGED
|
@@ -39,21 +39,21 @@ COPY . .
|
|
| 39 |
# Create runtime directories
|
| 40 |
RUN mkdir -p outputs model_cache
|
| 41 |
|
| 42 |
-
#
|
| 43 |
RUN useradd -m -u 1000 appuser \
|
| 44 |
&& chown -R appuser:appuser /app
|
| 45 |
USER appuser
|
| 46 |
|
| 47 |
-
#
|
| 48 |
-
EXPOSE
|
| 49 |
|
| 50 |
-
# Health check —
|
| 51 |
-
HEALTHCHECK --interval=30s --timeout=10s --start-period=
|
| 52 |
-
CMD curl -f http://localhost:
|
| 53 |
|
| 54 |
-
# Default env (override
|
| 55 |
ENV HOST=0.0.0.0 \
|
| 56 |
-
PORT=
|
| 57 |
MODEL_ID=nota-ai/bk-sdm-small \
|
| 58 |
MODEL_CACHE_DIR=/app/model_cache \
|
| 59 |
AUTO_LOAD_MODEL=true \
|
|
@@ -70,4 +70,4 @@ ENV HOST=0.0.0.0 \
|
|
| 70 |
JOB_TTL_SECONDS=0
|
| 71 |
|
| 72 |
CMD ["python", "-m", "uvicorn", "main:app", \
|
| 73 |
-
"--host", "0.0.0.0", "--port", "
|
|
|
|
| 39 |
# Create runtime directories
|
| 40 |
RUN mkdir -p outputs model_cache
|
| 41 |
|
| 42 |
+
# HF Spaces runs containers as UID 1000 — match it
|
| 43 |
RUN useradd -m -u 1000 appuser \
|
| 44 |
&& chown -R appuser:appuser /app
|
| 45 |
USER appuser
|
| 46 |
|
| 47 |
+
# ── Port 7860 is REQUIRED by Hugging Face Spaces ──────────────────────────────
|
| 48 |
+
EXPOSE 7860
|
| 49 |
|
| 50 |
+
# Health check — longer start_period for model download on cold start
|
| 51 |
+
HEALTHCHECK --interval=30s --timeout=10s --start-period=120s --retries=5 \
|
| 52 |
+
CMD curl -f http://localhost:7860/health || exit 1
|
| 53 |
|
| 54 |
+
# Default env (override via HF Spaces Secrets or docker-compose)
|
| 55 |
ENV HOST=0.0.0.0 \
|
| 56 |
+
PORT=7860 \
|
| 57 |
MODEL_ID=nota-ai/bk-sdm-small \
|
| 58 |
MODEL_CACHE_DIR=/app/model_cache \
|
| 59 |
AUTO_LOAD_MODEL=true \
|
|
|
|
| 70 |
JOB_TTL_SECONDS=0
|
| 71 |
|
| 72 |
CMD ["python", "-m", "uvicorn", "main:app", \
|
| 73 |
+
"--host", "0.0.0.0", "--port", "7860", "--workers", "1"]
|
README.md
CHANGED
|
@@ -1,352 +1,59 @@
|
|
| 1 |
---
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
| 4 |
sdk: docker
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
colorTo: yellow
|
| 8 |
-
pinned: true
|
| 9 |
---
|
|
|
|
| 10 |
# HF CPU Image Generation API
|
| 11 |
|
| 12 |
-
A
|
| 13 |
|
| 14 |
-
--
|
| 15 |
|
| 16 |
-
##
|
| 17 |
|
| 18 |
```
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
│ GET /jobs/{id} → { status: "completed", download_url: "..." }
|
| 25 |
-
│
|
| 26 |
-
│ GET /jobs/{id}/download → image.png
|
| 27 |
-
│
|
| 28 |
-
│ DELETE /jobs/{id} → { ok: true }
|
| 29 |
-
│
|
| 30 |
-
▼
|
| 31 |
-
|
| 32 |
-
┌─────────────────────────────────────────────────────────────┐
|
| 33 |
-
│ FastAPI (main.py) │
|
| 34 |
-
│ ├── POST /generate → enqueue job, return job_id │
|
| 35 |
-
│ ├── GET /jobs → list / filter jobs │
|
| 36 |
-
│ ├── GET /jobs/{id} → status + progress │
|
| 37 |
-
│ ├── GET /jobs/{id}/download → FileResponse (PNG) │
|
| 38 |
-
│ ├── DELETE /jobs/{id} → delete job + image │
|
| 39 |
-
│ ├── GET /health → pipeline & queue status │
|
| 40 |
-
│ └── POST /models/load → hot-swap model │
|
| 41 |
-
│ │
|
| 42 |
-
│ job_store.py — thread-safe in-memory job registry │
|
| 43 |
-
│ worker.py — background daemon thread + FIFO queue │
|
| 44 |
-
│ pipeline_manager.py — HF Diffusers pipeline (CPU-tuned) │
|
| 45 |
-
└─────────────────────────────────────────────────────────────┘
|
| 46 |
-
│
|
| 47 |
-
┌────────▼────────┐
|
| 48 |
-
│ outputs/ │
|
| 49 |
-
│ (PNG files) │
|
| 50 |
-
└─────────────────┘
|
| 51 |
```
|
| 52 |
|
| 53 |
-
|
| 54 |
-
|
| 55 |
-
## Quick Start
|
| 56 |
-
|
| 57 |
-
### Prerequisites
|
| 58 |
-
- Python 3.9 or higher
|
| 59 |
-
- 4 GB+ RAM (8 GB recommended for SD v1.5)
|
| 60 |
-
- Internet connection on first run (to download model weights)
|
| 61 |
-
|
| 62 |
-
### 1. Install
|
| 63 |
|
| 64 |
-
|
| 65 |
-
|
| 66 |
-
|
| 67 |
-
|
| 68 |
-
|
| 69 |
-
|
| 70 |
-
|
| 71 |
-
|
| 72 |
-
|
| 73 |
-
|
| 74 |
-
pip install torch torchvision --index-url https://download.pytorch.org/whl/cpu
|
| 75 |
-
pip install -r requirements.txt
|
| 76 |
-
copy .env.example .env
|
| 77 |
-
python -m uvicorn main:app --host 0.0.0.0 --port 8000 --workers 1
|
| 78 |
-
```
|
| 79 |
|
| 80 |
-
##
|
| 81 |
|
| 82 |
-
``
|
| 83 |
-
|
| 84 |
-
``
|
|
|
|
|
|
|
| 85 |
|
| 86 |
-
|
| 87 |
|
| 88 |
-
|
| 89 |
|
| 90 |
-
|
| 91 |
-
|---|---|---|---|
|
| 92 |
-
| `nota-ai/bk-sdm-small` | ~500 MB | **~60–120 s** | Best for CPU — default |
|
| 93 |
-
| `runwayml/stable-diffusion-v1-5` | ~4 GB | ~150–300 s | Standard quality |
|
| 94 |
-
| `stabilityai/stable-diffusion-2-1-base` | ~5 GB | ~200–400 s | Highest quality |
|
| 95 |
|
| 96 |
-
|
| 97 |
|
| 98 |
-
|
|
| 99 |
|---|---|
|
| 100 |
-
| `
|
| 101 |
-
| `
|
| 102 |
-
| `enable_attention_slicing(1)` | Lowers peak RAM ~30 %, minimal speed cost |
|
| 103 |
-
| `DPMSolverMultistepScheduler` + Karras sigmas | Converges well at 15–20 steps |
|
| 104 |
-
| `safety_checker=None` | Skips NSFW classifier, saves ~300 MB RAM |
|
| 105 |
-
| `torch.set_num_threads(N)` | Saturates all logical CPU cores |
|
| 106 |
-
| `torch.inference_mode()` | Disables autograd, reduces overhead |
|
| 107 |
-
|
| 108 |
-
### Tips to speed up CPU generation
|
| 109 |
-
- Use **`nota-ai/bk-sdm-small`** — it is specifically distilled for speed
|
| 110 |
-
- Keep images at **512×512** (larger = much slower on SD v1.x)
|
| 111 |
-
- Use **20 steps with DPM++** (better than 50 steps with PNDM)
|
| 112 |
-
- Set `CPU_THREADS=0` in `.env` to use all logical cores
|
| 113 |
-
- Avoid running other CPU-heavy workloads during generation
|
| 114 |
-
|
| 115 |
-
---
|
| 116 |
-
|
| 117 |
-
## API Reference
|
| 118 |
-
|
| 119 |
-
### Submit a generation job
|
| 120 |
-
|
| 121 |
-
```
|
| 122 |
-
POST /generate
|
| 123 |
-
```
|
| 124 |
-
|
| 125 |
-
**Request body:**
|
| 126 |
-
```json
|
| 127 |
-
{
|
| 128 |
-
"prompt": "a photorealistic mountain landscape at golden hour",
|
| 129 |
-
"negative_prompt": "blurry, low quality, watermark",
|
| 130 |
-
"width": 512,
|
| 131 |
-
"height": 512,
|
| 132 |
-
"num_inference_steps": 20,
|
| 133 |
-
"guidance_scale": 7.5,
|
| 134 |
-
"seed": -1,
|
| 135 |
-
"scheduler": "dpm++"
|
| 136 |
-
}
|
| 137 |
-
```
|
| 138 |
-
|
| 139 |
-
**Schedulers:** `dpm++` (best), `euler_a`, `euler`, `pndm`
|
| 140 |
-
|
| 141 |
-
**Response `202 Accepted`:**
|
| 142 |
-
```json
|
| 143 |
-
{
|
| 144 |
-
"job_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
|
| 145 |
-
"status": "queued",
|
| 146 |
-
"created_at": "2024-06-01T12:00:00Z",
|
| 147 |
-
"queue_position": 1,
|
| 148 |
-
"message": "Job is next in queue and will start immediately."
|
| 149 |
-
}
|
| 150 |
-
```
|
| 151 |
-
|
| 152 |
-
---
|
| 153 |
-
|
| 154 |
-
### Check job status
|
| 155 |
-
|
| 156 |
-
```
|
| 157 |
-
GET /jobs/{job_id}
|
| 158 |
-
```
|
| 159 |
-
|
| 160 |
-
**While processing:**
|
| 161 |
-
```json
|
| 162 |
-
{
|
| 163 |
-
"job_id": "3fa85f64-...",
|
| 164 |
-
"status": "processing",
|
| 165 |
-
"progress": 45,
|
| 166 |
-
"current_step": 9,
|
| 167 |
-
"total_steps": 20,
|
| 168 |
-
"started_at": "2024-06-01T12:00:01Z"
|
| 169 |
-
}
|
| 170 |
-
```
|
| 171 |
-
|
| 172 |
-
**When completed:**
|
| 173 |
-
```json
|
| 174 |
-
{
|
| 175 |
-
"job_id": "3fa85f64-...",
|
| 176 |
-
"status": "completed",
|
| 177 |
-
"progress": 100,
|
| 178 |
-
"download_url": "/jobs/3fa85f64-.../download",
|
| 179 |
-
"image_filename": "20240601_120045_3fa85f64_42.png",
|
| 180 |
-
"duration_seconds": 87.3,
|
| 181 |
-
"completed_at": "2024-06-01T12:01:28Z"
|
| 182 |
-
}
|
| 183 |
-
```
|
| 184 |
-
|
| 185 |
-
---
|
| 186 |
-
|
| 187 |
-
### Download the image
|
| 188 |
-
|
| 189 |
-
```
|
| 190 |
-
GET /jobs/{job_id}/download
|
| 191 |
-
```
|
| 192 |
-
|
| 193 |
-
Returns the PNG as a file attachment. Returns `202` if still processing.
|
| 194 |
-
|
| 195 |
-
---
|
| 196 |
-
|
| 197 |
-
### Delete a job and its image
|
| 198 |
-
|
| 199 |
-
```
|
| 200 |
-
DELETE /jobs/{job_id}
|
| 201 |
-
```
|
| 202 |
-
|
| 203 |
-
Removes the job record and deletes the PNG from disk.
|
| 204 |
-
|
| 205 |
-
```json
|
| 206 |
-
{
|
| 207 |
-
"ok": true,
|
| 208 |
-
"job_id": "3fa85f64-...",
|
| 209 |
-
"image_deleted": true,
|
| 210 |
-
"message": "Job deleted. Image file removed from disk."
|
| 211 |
-
}
|
| 212 |
-
```
|
| 213 |
-
|
| 214 |
-
---
|
| 215 |
-
|
| 216 |
-
### List all jobs
|
| 217 |
-
|
| 218 |
-
```
|
| 219 |
-
GET /jobs?status=completed&limit=50&offset=0
|
| 220 |
-
```
|
| 221 |
-
|
| 222 |
-
Status filter options: `queued`, `processing`, `completed`, `failed`
|
| 223 |
-
|
| 224 |
-
---
|
| 225 |
-
|
| 226 |
-
### Health check
|
| 227 |
-
|
| 228 |
-
```
|
| 229 |
-
GET /health
|
| 230 |
-
```
|
| 231 |
-
|
| 232 |
-
```json
|
| 233 |
-
{
|
| 234 |
-
"status": "ok",
|
| 235 |
-
"model_id": "nota-ai/bk-sdm-small",
|
| 236 |
-
"pipeline_loaded": true,
|
| 237 |
-
"loading": false,
|
| 238 |
-
"queue_size": 2,
|
| 239 |
-
"jobs_total": 15,
|
| 240 |
-
"jobs_by_status": {
|
| 241 |
-
"queued": 2,
|
| 242 |
-
"processing": 1,
|
| 243 |
-
"completed": 11,
|
| 244 |
-
"failed": 1
|
| 245 |
-
},
|
| 246 |
-
"cpu_threads": 8
|
| 247 |
-
}
|
| 248 |
-
```
|
| 249 |
-
|
| 250 |
-
---
|
| 251 |
-
|
| 252 |
-
### Hot-swap model
|
| 253 |
-
|
| 254 |
-
```
|
| 255 |
-
POST /models/load
|
| 256 |
-
Content-Type: application/json
|
| 257 |
-
|
| 258 |
-
{ "model_id": "runwayml/stable-diffusion-v1-5" }
|
| 259 |
-
```
|
| 260 |
-
|
| 261 |
-
Loads the new model in the background. Poll `GET /health` to confirm `pipeline_loaded: true`.
|
| 262 |
-
|
| 263 |
-
---
|
| 264 |
-
|
| 265 |
-
## Example: Full workflow with curl
|
| 266 |
-
|
| 267 |
-
```bash
|
| 268 |
-
# 1. Check service is ready
|
| 269 |
-
curl http://localhost:8000/health | jq .pipeline_loaded
|
| 270 |
-
|
| 271 |
-
# 2. Submit a generation job
|
| 272 |
-
JOB=$(curl -s -X POST http://localhost:8000/generate \
|
| 273 |
-
-H "Content-Type: application/json" \
|
| 274 |
-
-d '{
|
| 275 |
-
"prompt": "a serene Japanese garden with koi pond, watercolor style",
|
| 276 |
-
"negative_prompt": "low quality, blurry, cartoon",
|
| 277 |
-
"width": 512,
|
| 278 |
-
"height": 512,
|
| 279 |
-
"num_inference_steps": 20,
|
| 280 |
-
"guidance_scale": 7.5,
|
| 281 |
-
"seed": 42,
|
| 282 |
-
"scheduler": "dpm++"
|
| 283 |
-
}')
|
| 284 |
-
echo $JOB | jq .
|
| 285 |
-
|
| 286 |
-
JOB_ID=$(echo $JOB | jq -r .job_id)
|
| 287 |
-
|
| 288 |
-
# 3. Poll until completed
|
| 289 |
-
while true; do
|
| 290 |
-
STATUS=$(curl -s http://localhost:8000/jobs/$JOB_ID | jq -r .status)
|
| 291 |
-
PROGRESS=$(curl -s http://localhost:8000/jobs/$JOB_ID | jq -r .progress)
|
| 292 |
-
echo "Status: $STATUS Progress: $PROGRESS%"
|
| 293 |
-
[ "$STATUS" = "completed" ] || [ "$STATUS" = "failed" ] && break
|
| 294 |
-
sleep 5
|
| 295 |
-
done
|
| 296 |
-
|
| 297 |
-
# 4. Download the image
|
| 298 |
-
curl -s http://localhost:8000/jobs/$JOB_ID/download -o output.png
|
| 299 |
-
echo "Saved to output.png"
|
| 300 |
-
|
| 301 |
-
# 5. Delete the job + image
|
| 302 |
-
curl -s -X DELETE http://localhost:8000/jobs/$JOB_ID | jq .
|
| 303 |
-
```
|
| 304 |
-
|
| 305 |
-
---
|
| 306 |
-
|
| 307 |
-
## Configuration (`.env`)
|
| 308 |
-
|
| 309 |
-
| Variable | Default | Description |
|
| 310 |
-
|---|---|---|
|
| 311 |
-
| `MODEL_ID` | `nota-ai/bk-sdm-small` | Hugging Face model repo ID |
|
| 312 |
-
| `MODEL_CACHE_DIR` | `./model_cache` | Where weights are cached |
|
| 313 |
-
| `AUTO_LOAD_MODEL` | `true` | Load model at startup |
|
| 314 |
-
| `CPU_THREADS` | `0` (all cores) | PyTorch thread count |
|
| 315 |
-
| `ENABLE_ATTENTION_SLICING` | `true` | Lower peak RAM usage |
|
| 316 |
-
| `DEFAULT_STEPS` | `20` | Default inference steps |
|
| 317 |
-
| `MAX_STEPS` | `50` | Request cap |
|
| 318 |
-
| `DEFAULT_WIDTH/HEIGHT` | `512` | Default image dimensions |
|
| 319 |
-
| `MAX_WIDTH/HEIGHT` | `768` | Request cap |
|
| 320 |
-
| `OUTPUTS_DIR` | `./outputs` | Where PNGs are saved |
|
| 321 |
-
| `PORT` | `8000` | HTTP port |
|
| 322 |
-
| `DEBUG` | `false` | Verbose logging + auto-reload |
|
| 323 |
-
|
| 324 |
-
---
|
| 325 |
-
|
| 326 |
-
## File Structure
|
| 327 |
-
|
| 328 |
-
```
|
| 329 |
-
hf-image-api/
|
| 330 |
-
├── main.py # FastAPI app + lifespan (startup/shutdown)
|
| 331 |
-
├── config.py # Settings from environment / .env
|
| 332 |
-
├── schemas.py # All Pydantic request & response models
|
| 333 |
-
├── job_store.py # Thread-safe in-memory job registry
|
| 334 |
-
├── pipeline_manager.py # HuggingFace Diffusers pipeline (CPU-tuned)
|
| 335 |
-
├── worker.py # Background worker thread + FIFO job queue
|
| 336 |
-
├── routes/
|
| 337 |
-
│ ├── generate.py # POST /generate
|
| 338 |
-
│ ├── jobs.py # GET/DELETE /jobs and /jobs/{id}/download
|
| 339 |
-
│ └── health.py # GET /health, GET /models, POST /models/load
|
| 340 |
-
├── outputs/ # Generated PNG files (auto-created)
|
| 341 |
-
├── model_cache/ # HuggingFace model weights cache (auto-created)
|
| 342 |
-
├── requirements.txt
|
| 343 |
-
├── .env.example
|
| 344 |
-
├── start.sh
|
| 345 |
-
└── README.md
|
| 346 |
-
```
|
| 347 |
-
|
| 348 |
-
---
|
| 349 |
-
|
| 350 |
-
## License
|
| 351 |
-
|
| 352 |
-
MIT — free to use and modify.
|
|
|
|
| 1 |
---
|
| 2 |
+
title: HF Image API
|
| 3 |
+
emoji: 🖼️
|
| 4 |
+
colorFrom: blue
|
| 5 |
+
colorTo: purple
|
| 6 |
sdk: docker
|
| 7 |
+
pinned: false
|
| 8 |
+
app_port: 7860
|
|
|
|
|
|
|
| 9 |
---
|
| 10 |
+
|
| 11 |
# HF CPU Image Generation API
|
| 12 |
|
| 13 |
+
A job-queue REST API for Stable Diffusion image generation on CPU using Hugging Face Diffusers.
|
| 14 |
|
| 15 |
+
**Swagger UI:** `https://your-space-url.hf.space/docs`
|
| 16 |
|
| 17 |
+
## Job flow
|
| 18 |
|
| 19 |
```
|
| 20 |
+
POST /generate → { job_id, status: "queued" }
|
| 21 |
+
GET /jobs/{id} → { status: "processing", progress: 45 }
|
| 22 |
+
GET /jobs/{id} → { status: "completed", download_url: "..." }
|
| 23 |
+
GET /jobs/{id}/download → image.png
|
| 24 |
+
DELETE /jobs/{id} → removes job + image
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
```
|
| 26 |
|
| 27 |
+
## API endpoints
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
|
| 29 |
+
| Method | Path | Description |
|
| 30 |
+
|---|---|---|
|
| 31 |
+
| `POST` | `/generate` | Submit a generation job |
|
| 32 |
+
| `GET` | `/jobs` | List all jobs |
|
| 33 |
+
| `GET` | `/jobs/{id}` | Poll job status & progress |
|
| 34 |
+
| `GET` | `/jobs/{id}/download` | Download the PNG |
|
| 35 |
+
| `DELETE` | `/jobs/{id}` | Delete job + image |
|
| 36 |
+
| `GET` | `/health` | Pipeline & queue status |
|
| 37 |
+
| `GET` | `/models` | List supported models |
|
| 38 |
+
| `POST` | `/models/load` | Hot-swap model |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
|
| 40 |
+
## CPU optimisations
|
| 41 |
|
| 42 |
+
- `torch.float32` (mandatory for CPU)
|
| 43 |
+
- `DPMSolverMultistepScheduler` — converges at 20 steps
|
| 44 |
+
- `enable_attention_slicing` — lower peak RAM
|
| 45 |
+
- `low_cpu_mem_usage=True` — no double-buffering
|
| 46 |
+
- `safety_checker=None` — saves ~300 MB RAM
|
| 47 |
|
| 48 |
+
## Default model
|
| 49 |
|
| 50 |
+
`nota-ai/bk-sdm-small` (~500 MB) — fastest on CPU, ~60–120s per 512×512 image.
|
| 51 |
|
| 52 |
+
## HF Spaces Secrets
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
|
| 54 |
+
Set these under **Settings → Secrets** in your Space:
|
| 55 |
|
| 56 |
+
| Secret | Description |
|
| 57 |
|---|---|
|
| 58 |
+
| `HF_TOKEN` | Your HuggingFace token (faster downloads) |
|
| 59 |
+
| `MODEL_ID` | Override model (e.g. `runwayml/stable-diffusion-v1-5`) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docker-compose.yml
CHANGED
|
@@ -9,7 +9,7 @@ services:
|
|
| 9 |
container_name: hf-image-api
|
| 10 |
|
| 11 |
ports:
|
| 12 |
-
- "8000:
|
| 13 |
|
| 14 |
# ── Persistent volumes ─────────────────────────────────────────────────────
|
| 15 |
volumes:
|
|
@@ -50,7 +50,7 @@ services:
|
|
| 50 |
restart: unless-stopped
|
| 51 |
|
| 52 |
healthcheck:
|
| 53 |
-
test: ["CMD", "curl", "-f", "http://localhost:
|
| 54 |
interval: 30s
|
| 55 |
timeout: 10s
|
| 56 |
retries: 3
|
|
@@ -59,4 +59,4 @@ services:
|
|
| 59 |
# ── Named volumes ──────────────────────────────────────────────────────────────
|
| 60 |
volumes:
|
| 61 |
model_cache:
|
| 62 |
-
driver: local
|
|
|
|
| 9 |
container_name: hf-image-api
|
| 10 |
|
| 11 |
ports:
|
| 12 |
+
- "8000:7860"
|
| 13 |
|
| 14 |
# ── Persistent volumes ─────────────────────────────────────────────────────
|
| 15 |
volumes:
|
|
|
|
| 50 |
restart: unless-stopped
|
| 51 |
|
| 52 |
healthcheck:
|
| 53 |
+
test: ["CMD", "curl", "-f", "http://localhost:7860/health"]
|
| 54 |
interval: 30s
|
| 55 |
timeout: 10s
|
| 56 |
retries: 3
|
|
|
|
| 59 |
# ── Named volumes ──────────────────────────────────────────────────────────────
|
| 60 |
volumes:
|
| 61 |
model_cache:
|
| 62 |
+
driver: local
|