v6: launcher scripts + current tag
Browse files
README.md
CHANGED
|
@@ -1,13 +1,15 @@
|
|
| 1 |
# comfyui-qwen
|
| 2 |
|
| 3 |
RunPod image for ComfyUI with Qwen/Flux workflows. Docker image: `plx1029/comfyui-qwen`
|
| 4 |
-
(current: `
|
| 5 |
|
| 6 |
```
|
| 7 |
/workspace/
|
| 8 |
├── ComfyUI/ # ComfyUI itself (models under ComfyUI/models/)
|
| 9 |
├── workflows/ # workflow JSONs used by the download script
|
| 10 |
├── download_missing_models.sh
|
|
|
|
|
|
|
| 11 |
└── README.md
|
| 12 |
```
|
| 13 |
|
|
@@ -16,12 +18,16 @@ RunPod image for ComfyUI with Qwen/Flux workflows. Docker image: `plx1029/comfyu
|
|
| 16 |
ComfyUI does **not** auto-start (since v4) — start it yourself:
|
| 17 |
|
| 18 |
```bash
|
|
|
|
| 19 |
comfy # wrapper: runs ComfyUI on port $COMFY_PORT (default 7865)
|
| 20 |
comfy --enable-manager # extra args are passed through to main.py
|
| 21 |
# or directly:
|
| 22 |
cd /workspace/ComfyUI && python main.py --listen 0.0.0.0 --port 7865 --enable-manager
|
| 23 |
```
|
| 24 |
|
|
|
|
|
|
|
|
|
|
| 25 |
Set `COMFY_AUTOSTART=true` on the pod to re-enable auto-start at boot.
|
| 26 |
|
| 27 |
## Models + custom-node dependencies
|
|
@@ -47,9 +53,10 @@ neither is set.
|
|
| 47 |
|
| 48 |
## How this stays up to date
|
| 49 |
|
| 50 |
-
The source of truth for `download_missing_models.sh`
|
| 51 |
-
|
| 52 |
-
|
|
|
|
| 53 |
|
| 54 |
- **script/README changes** → push to the HF repo, no image rebuild needed;
|
| 55 |
- **anything else** (start scripts, ComfyUI, system deps) → rebuild and push
|
|
|
|
| 1 |
# comfyui-qwen
|
| 2 |
|
| 3 |
RunPod image for ComfyUI with Qwen/Flux workflows. Docker image: `plx1029/comfyui-qwen`
|
| 4 |
+
(current: `v6`). Everything lives in `/workspace` — do not move files around:
|
| 5 |
|
| 6 |
```
|
| 7 |
/workspace/
|
| 8 |
├── ComfyUI/ # ComfyUI itself (models under ComfyUI/models/)
|
| 9 |
├── workflows/ # workflow JSONs used by the download script
|
| 10 |
├── download_missing_models.sh
|
| 11 |
+
├── start_comfy # free port 7865, then start ComfyUI (+manager)
|
| 12 |
+
├── claude_start.sh # IS_SANDBOX=1 claude --dangerously-skip-permissions
|
| 13 |
└── README.md
|
| 14 |
```
|
| 15 |
|
|
|
|
| 18 |
ComfyUI does **not** auto-start (since v4) — start it yourself:
|
| 19 |
|
| 20 |
```bash
|
| 21 |
+
./start_comfy # free port 7865, then run ComfyUI with the manager
|
| 22 |
comfy # wrapper: runs ComfyUI on port $COMFY_PORT (default 7865)
|
| 23 |
comfy --enable-manager # extra args are passed through to main.py
|
| 24 |
# or directly:
|
| 25 |
cd /workspace/ComfyUI && python main.py --listen 0.0.0.0 --port 7865 --enable-manager
|
| 26 |
```
|
| 27 |
|
| 28 |
+
`./claude_start.sh` launches Claude Code sandboxed
|
| 29 |
+
(`IS_SANDBOX=1 claude --dangerously-skip-permissions`).
|
| 30 |
+
|
| 31 |
Set `COMFY_AUTOSTART=true` on the pod to re-enable auto-start at boot.
|
| 32 |
|
| 33 |
## Models + custom-node dependencies
|
|
|
|
| 53 |
|
| 54 |
## How this stays up to date
|
| 55 |
|
| 56 |
+
The source of truth for `download_missing_models.sh`, `start_comfy`,
|
| 57 |
+
`claude_start.sh`, and this README is the HF repo `aleph65/ComfyUI`. At
|
| 58 |
+
container boot, `/start-comfy.sh` pulls the latest versions from there
|
| 59 |
+
(best-effort; keeps the baked-in copies if offline). So:
|
| 60 |
|
| 61 |
- **script/README changes** → push to the HF repo, no image rebuild needed;
|
| 62 |
- **anything else** (start scripts, ComfyUI, system deps) → rebuild and push
|