feat: add diffusers loader for OpenAI-compatible image generation#6
Merged
feat: add diffusers loader for OpenAI-compatible image generation#6
Conversation
added 2 commits
April 6, 2026 04:03
Add a new `diffusers` loader for plug-and-play image generation models via HuggingFace Diffusers' AutoPipelineForText2Image. Exposes a new POST /v1/images/generations endpoint returning base64-encoded PNGs. - Add `image` usecase and `diffusers` loader to config enums - Add DiffusersConfig (torch_dtype, num_inference_steps, guidance_scale) - Add DiffusersInfer backend following TransformersInfer pattern - Add OpenAIServingImage serving layer with run_in_executor for GPU calls - Add ImageGenerationRequest/Response protocol models - Add create_image_generation stubs to vllm/transformers/custom backends - Make model and loader mandatory fields in YashaModelConfig - Return all models in /v1/models regardless of usecase - Add accelerate and diffusers dependencies - Update docs and README
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Add a new
diffusersloader for plug-and-play image generation models via HuggingFace Diffusers' AutoPipelineForText2Image. Exposes a new POST /v1/images/generations endpoint returning base64-encoded PNGs.Why
Fixes lack of support for image generation
How to Test
Run tests
Checklist
ruff check .passesruff format --check .passespyrightpasses