crash on generation

### Custom Node Testing

- [x] I have tried disabling custom nodes and the issue persists (see [how to disable custom nodes](https://docs.comfy.org/troubleshooting/custom-node-issues#step-1%3A-test-with-all-custom-nodes-disabled) if you need help)

### Expected Behavior

generating a photo

### Actual Behavior

crash

### Steps to Reproduce

go templates select flux pro download required stuff then do a photo gen

yeah nothing else just straight that

### Debug Logs

```powershell
C:\Users\Administrator\Downloads\ComfyUI_windows_portable>.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build --fast fp16_accumulation Checkpoint files will always be loaded safely. Total VRAM 8188 MB, total RAM 16177 MB pytorch version: 2.9.1+cu130 Enabled fp16 accumulation. Set vram state to: NORMAL_VRAM Device: cuda:0 NVIDIA GeForce RTX 4060 : cudaMallocAsync Using async weight offloading with 2 streams Enabled pinned memory 7279.0 working around nvidia conv3d memory bug. Using pytorch attention Python version: 3.13.9 (tags/v3.13.9:8183fa5, Oct 14 2025, 14:09:13) [MSC v.1944 64 bit (AMD64)] ComfyUI version: 0.3.76 ComfyUI frontend version: 1.32.10 [Prompt Server] web root: C:\Users\Administrator\Downloads\ComfyUI_windows_portable\python_embeded\Lib\site-packages\comfyui_frontend_package\static Total VRAM 8188 MB, total RAM 16177 MB pytorch version: 2.9.1+cu130 Enabled fp16 accumulation. Set vram state to: NORMAL_VRAM Device: cuda:0 NVIDIA GeForce RTX 4060 : cudaMallocAsync Using async weight offloading with 2 streams Enabled pinned memory 7279.0 Import times for custom nodes: 0.0 seconds: C:\Users\Administrator\Downloads\ComfyUI_windows_portable\ComfyUI\custom_nodes\websocket_image_save.py Context impl SQLiteImpl. Will assume non-transactional DDL. No target revision found. Starting server To see the GUI go to: http://127.0.0.1:8188 got prompt Using pytorch attention in VAE Using pytorch attention in VAE VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16 Requested to load AutoencoderKL loaded completely; 3032.89 MB usable, 160.31 MB loaded, full load: True C:\Users\Administrator\Downloads\ComfyUI_windows_portable>echo If you see this and ComfyUI did not start try updating your Nvidia Drivers to the latest. If you see this and ComfyUI did not start try updating your Nvidia Drivers to the latest. C:\Users\Administrator\Downloads\ComfyUI_windows_portable>pause
```

### Other

its working if i try z image gen but ain working for flux maybe bcs my computer not enough ?

edit: its same for qwen image edit