Zengtudor/Wan2.1
1
0
Fork 0
mirror of https://github.com/Wan-Video/Wan2.1.git synced 2025-11-04 22:26:36 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Added troubleshooting info

Browse Source
This commit is contained in:
DeepBeepMeep 2025-03-04 22:33:00 +01:00
parent d200a54336
commit 18f3a31daf
1 changed files with 12 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
README.md
View File

@ -136,6 +136,18 @@ To run the application while loading entirely the diffusion model in VRAM (sligh
python gradio_server.py --profile 3 python gradio_server.py --profile 3
``` ```
**Trouble shooting**:\
If you have installed Sage attention, it may seem that it works because *pip install sageattention* didn't produce and error or because sage is offered as on option but in fact it doesnt work : in order to be fully operatioal Sage needs to compile its triton kernels the first time it is run (that is the first time you try to generate a video).
Sometime fixing Sage compilation is easy (clear the triton cache, check triton is properly installed) sometime it is simply not possible because Sage is not supported on some older GPUs
Therefore you may have no choice but to fallback to sdpa attention, to do so:
- In the configuration menu inside the application, switch "Attention mode" to "sdpa"
or
- Launch the application this way:
```bash
python gradio_server.py --attention sdpa
```
### Loras support ### Loras support