kabachuha / sd-webui-text2video

Auto1111 extension implementing text2video diffusion models (like ModelScope or VideoCrafter) using only Auto1111 webui dependencies
Other
1.28k stars 107 forks source link

Add prompt weighting #11

Closed kabachuha closed 1 year ago

kabachuha commented 1 year ago

At the moment the script just passes the prompt and the negative prompt into the diffusion model. To harness all the power of attention control, it's needed to use the same mechanism as Auto does with the regular CLIP embedder in the hijack section