Violación de segmento (`core' generado)

### 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

Generate without issues an image

### Actual Behavior

When start to do the step, ComfyUI crash with the next message: "Violación de segmento (`core' generado)"

### Steps to Reproduce

1. Activate venv
2. Execute with the next command line: python -m main --auto-launch --preview-method latent2rgb --disable-api-nodes --disable-all-custom-nodes
3. Load Flux Kontext tamplate
4. Run Workflow.

### Debug Logs

```powershell
Checkpoint files will always be loaded safely.
Total VRAM 11901 MB, total RAM 31997 MB
pytorch version: 2.10.0.dev20250910+cu130
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 3060 : native
Using pytorch attention
Python version: 3.12.3 (main, Aug 14 2025, 17:47:21) [GCC 13.3.0]
ComfyUI version: 0.3.59
ComfyUI frontend version: 1.26.11
[Prompt Server] web root: /home/rodrigo/AI_tools/ComfyUI/venv/lib/python3.12/site-packages/comfyui_frontend_package/static
Skipping loading of custom nodes
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 AutoencodingEngine
loaded completely 6954.0576171875 159.87335777282715 True
Using scaled fp8: fp8 matrix mult: False, scale input: False
CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cpu, dtype: torch.float16
clip missing: ['text_projection.weight']
Requested to load FluxClipModel_
loaded completely 9436.41669921875 4903.231597900391 True
Using scaled fp8: fp8 matrix mult: False, scale input: True
model weight dtype torch.bfloat16, manual cast: None
model_type FLUX
Requested to load Flux
loaded partially 8387.592011718749 8385.255348205566 0
0%| | 0/20 [00:00

Start by reproducing the crash with `python -m main --auto-launch --preview-method latent2rgb --disable-api-nodes --disable-all-custom-nodes` and the Flux Kontext template. Compare the default attention path with the reported `--use-sage-attention` workaround, using the supplied PyTorch, CUDA, GPU, and ComfyUI versions; done means identifying a confirmed cause or a reproducible, actionable diagnosis.

Written by the indexing model from the issue text.