[Bagel]Add image edit

[princepride]

Test Plan

from PIL import Image
from vllm_omni.entrypoints.omni_diffusion import OmniDiffusion

def main():
    image = Image.open("women.jpg")
    pipeline = OmniDiffusion(model="../models/BAGEL-7B-MoT")
    result = pipeline.generate("Let the woman wear a blue dress", pil_image=image, seed=52)
    result.images[0].save("bagel_i2i_output.png")

if __name__ == "__main__":
    main()

Test Result

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 9625752b51

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

[princepride]

@ZJY0516 Can you help review it😊

[hsliuustc0106]

update docs please for cachedit supports

[princepride]

update docs please for cachedit supports

But we can't support cache-dit now.🥹

[ZJY0516]

@hsliuustc0106 Do we need to add a test for this special model?

[hsliuustc0106]

@hsliuustc0106 Do we need to add a test for this special model?

yes, but the ci is refactoring now, maybe wait for a few days

[hsliuustc0106]

update docs please for cachedit supports

But we can't support cache-dit now.🥹

sorry, my fault

[hsliuustc0106]

do we have any examples for this model?

[hsliuustc0106]

lgtm