WAN 2.1 very weird output using T2V 14B model gguf model with native workflow
Open
- Dominant language
- Python
- Stars
- 133k
- Forks
- 15.7k
- Avg merge
- 1d 7h
- Merged PRs (30d)
- 158
Description
It never generates what you actually prompt. Instead, it always creates deformed things—like creatures with multiple hands or something so weird I can’t even describe it.
The Prompt : A woman sits in a decorated room, with the camera focused on her upper body and face. Behind her, the living room is blurred.
The I2V model works perfectly tho
Contributor guide
Assessment
This issue has not been assessed yet.