gfx1151 invalid data cast
- Dominant language
- Python
- Stars
- 133k
- Forks
- 15.7k
- Avg merge
- 1d 6h
- Merged PRs (30d)
- 155
Description
The fox moving video using wan2.1, encounters invalid data cast in the process of vae.
Checkpoint files will always be loaded safely.
Total VRAM 98304 MB, total RAM 31719 MB
pytorch version: 2.7.0a0+rocm7.0.0rc20250715
AMD arch: gfx1151
ROCm version: (6, 5)
Set vram state to: NORMAL_VRAM
Device: cuda:0 AMD Radeon Graphics : native
Using pytorch attention
Python version: 3.12.11 | packaged by Anaconda, Inc. | (main, Jun 5 2025, 13:09:17) [GCC 11.2.0]
ComfyUI version: 0.3.45
ComfyUI frontend version: 1.23.4
[Prompt Server] web root: /home/rsj/miniconda3/envs/cmm/lib/python3.12/site-packages/comfyui_frontend_package/static
Import times for custom nodes:
0.0 seconds: /home/rsj/AI_Software/ComfyUI-0.3.45/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 split attention in VAE
Using split attention in VAE
VAE load device: cpu, offload device: cpu, dtype: torch.float32
Using scaled fp8: fp8 matrix mult: False, scale input: False
Requested to load WanTEModel
loaded completely 9.5367431640625e+25 6419.477203369141 True
CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cuda:0, dtype: torch.float16
model weight dtype torch.float16, manual cast: None
model_type FLOW
Requested to load WAN21
loaded completely 90162.3228296875 2706.1788330078125 True
100%|███████████████████████████████████████████| 10/10 [04:19<00:00, 25.92s/it]
Requested to load WanVAE
loaded completely 9.5367431640625e+25 484.05659103393555 True
/home/rsj/AI_Software/ComfyUI-0.3.45/comfy_extras/nodes_images.py:134: RuntimeWarning: invalid value encountered in cast
img = Image.fromarray(np.clip(i, 0, 255).astype(np.uint8))
Prompt executed in 391.90 seconds
Contributor guide
Assessment
This issue has not been assessed yet.