Repository navigation
add modular pipeline for qwen-image 2.1 - #14976
Open
akshan-main wants to merge 1 commit into
Open
akshan-main wants to merge 1 commit into
akshan-main wants to merge 1 commit into
Conversation
Contributor
|
Hi @akshan-main, thanks for the PR! It does not appear to link an issue it fixes. If this PR addresses an existing issue, please add a closing keyword (e.g. Please note that PRs without a linked issue are likely to be automatically closed 10 days after this notice. Once the PR links an issue (or gets the |
This branch has not been deployed
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 does this PR do?
Adds a modular pipeline for Qwen-Image 2.1:
QwenImage21AutoBlocks+QwenImage21ModularPipeline, covering text-to-image and image-conditioned generation with one or more condition images. Same shape as flux2 (text_encoder/vae_encoder/denoise/decode, with the image-conditioned variants selected onimageandimage_latents). The denoiser is shared by both workflows and keeps one prefix KV cache per guidance branch, so the cache also works when the guider starts or stops mid-run.sample_sigmasis a pipeline config, so the checkpoint's grid loads frommodel_index.jsonas inQwenImage21Pipeline.Outputs match
QwenImage21Pipelineexactly with shared components and seed, on the tiny components and onQwen/Qwen-Image-2.1in bf16 (text-to-image, edit, two-image edit, with and without guidance and the KV cache). Test components live in akshan-main/tiny-qwenimage21-modular-pipe.Also registers
QwenImage21Pipelinein the auto text-to-image mapping soModularPipeline.from_pretrained("Qwen/Qwen-Image-2.1")resolves the modular class, and makes the test helper that readsmodular_model_index.jsonskipnullconfig values.Before submitting
Who can review?
@yiyixuxu @sayakpaul