ComfyUI just stops after queuing a prompt for SDXL 0.9
- Dominant language
- Python
- Stars
- 133k
- Forks
- 15.7k
- Avg merge
- 1d 10h
- Merged PRs (30d)
- 153
Description
Using the Windows standalone ComfyUI, after launching `run_nvidia_gpu.bat`, the app is opened in my browser, I enter a positive prompt, hit "Queue Prompt" and then nothing happens. If I look in the terminal, I just get this "got prompt" line end the program stops.
```
G:\Documents\Mes_documents\IA\ComfyUI_windows_portable>.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build
Total VRAM 8192 MB, total RAM 16318 MB
xformers version: 0.0.20
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 2080
Using xformers cross attention
Starting server
To see the GUI go to: http://127.0.0.1:8188
got prompt
G:\Documents\Mes_documents\IA\ComfyUI_windows_portable>pause
Appuyez sur une touche pour continuer...
```
Shortly after, the UI displays "reconnecting..." in red.

I tried with two checkpoint combinations but got the same results : `sd_xl_base_0.9.safetensors` + `sd_xl_refiner_0.9.safetensors` and then `sdxl_base_pruned_no-ema.safetensors` + `sdxl_refiner_pruned_no-ema.safetensors`
These files are placed in the folder `ComfyUI\models\checkpoints`, as requested.
I also tried `run_cpu.bat`, but got the same result.
Contributor guide
Assessment
This issue has not been assessed yet.