ModelsLab / diffusers_plus_plus

Diffusers++: State-of-the-art diffusion models for image and audio generation in PyTorch
https://huggingface.co/docs/diffusers
Apache License 2.0
9 stars 2 forks source link

image-clothing-repoclone-integrate #3

Closed Tanmaypatil123 closed 2 months ago

Tanmaypatil123 commented 2 months ago

What does this PR do?

Adds Oms_pipeline support and a cloth adapter.

Fixes # (issue)

Before submitting

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag members/contributors who may be interested in your PR.

@shauray8

shauray8 commented 2 months ago

the code looks good, the only thing I would do is to migrate all of it to src/diffusers_plus_plus/ that way we can have diffusers separate from diffusers_plus_plus, and also move all the helper functions either to oms_diffusion_pipeline or if the stuff is reusable like the attention processor move it to /src/pipeline_utils

also this can you migrate things to diffusers_plus_plus in order to keep things separate from diffusers