Does this work like lpw_stable_diffusion?
sarmientoj24 opened this issue · comments
I can see that it is designed for weighted prompts. However, how does it deal with long prompts?
https://github.com/huggingface/diffusers/blob/main/examples/community/lpw_stable_diffusion.py
idk how lpw_stable_diffusion works but if you pass truncate_long_prompts=False
then it subdivides the prompt blindly into 75-token chunks. todo is better logic that splits on ,
or .
or ;