Use /runpod-volume mount point for RunPod network volumes
All checks were successful
Build and Push Docker Image / build (push) Successful in 3m47s
All checks were successful
Build and Push Docker Image / build (push) Successful in 3m47s
RunPod mounts network volumes at /runpod-volume, not /userdata. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
@@ -11,7 +11,7 @@ ComfyUI-based image-to-video generation service deployed on RunPod Serverless. A
|
||||
```
|
||||
RunPod API Request → handler.py → ComfyUI Server (port 8188) → GPU Inference → Response
|
||||
↓
|
||||
Network Volume (/userdata) for models
|
||||
Network Volume (/runpod-volume) for models
|
||||
```
|
||||
|
||||
**Key flow in handler.py:**
|
||||
@@ -38,7 +38,7 @@ CI/CD via Gitea Actions triggers on push to `main` branch.
|
||||
|
||||
```bash
|
||||
docker run --gpus all -p 8188:8188 \
|
||||
-v /path/to/models:/userdata/models \
|
||||
-v /path/to/models:/runpod-volume/models \
|
||||
comfyui-runpod:latest
|
||||
```
|
||||
|
||||
@@ -77,7 +77,7 @@ docker run --gpus all -p 8188:8188 \
|
||||
|
||||
## Key Considerations
|
||||
|
||||
- Models stored on RunPod Network Volume at `/userdata/models/`
|
||||
- Models stored on RunPod Network Volume at `/runpod-volume/models/`
|
||||
- Cold start ~30-60s for ComfyUI initialization
|
||||
- Large outputs (>10MB) returned as file paths, not base64
|
||||
- Workflow files in `workflows/` directory (API format)
|
||||
|
||||
Reference in New Issue
Block a user