Anatoly Belikov

Great! Could you please merge the PR?

Also there is code by @takuma104 https://gist.github.com/takuma104/43552b8ec70b63323c57dc9c6fcb9b90, perhaps there should be a community "utils" or "contrib" module, some code doesn't need it's own pipeline..

@bghira generated image changes a little depending on weights, but much less than i see with stable diffusion models. I'll test it with DeepFloyd ``` from diffusers import DiffusionPipeline from...

Kandinsky 2-2 works with lpw similar to 2-1, image changes a little bit ``` from diffusers import DiffusionPipeline from diffusers import utils import functools import types import torch generator =...

@yijinsheng no

@bghira it is possible to pass embeddings from encode_prompt function to deepfloyd pipeline, but picture quality got much worse: So from tests it looks like only SD pipelines can benefit...

@sarmientoj24 it doesn't support lora prompts. I would rather add this and other features in a separate PR.

@adhikjoshi btw there is already skip_weighting flag in get_weighted_text_embeddings, so we can reuse lpw implementation in StableDiffusionPipeline

@DN6 @yijinsheng do i need to do anything in this PR? Adding lora and hypernetworks as suggested above is a nice feature but this can be done in follow up...

@sayakpaul Maybe we could introduce a PromptEncoder class to pass it into pipeline constructor, or maybe a mixin class? Using types.MethodType is not the best possible way to change prompt...