Wan2.1 First-Last-Frame-to-Video Diffusers Integration#570
Open
ZVAXEROWS wants to merge 1 commit intoWan-Video:mainfrom
Open
Wan2.1 First-Last-Frame-to-Video Diffusers Integration#570ZVAXEROWS wants to merge 1 commit intoWan-Video:mainfrom
ZVAXEROWS wants to merge 1 commit intoWan-Video:mainfrom
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Implement a Diffusers-compatible pipeline for the First-Last-Frame-to-Video (FLF2V) task. This allows users to generate videos given a first and last frame + prompt using the standard diffusers library interface and schedulers, fulfilling the Todo item: "Wan2.1 First-Last-Frame-to-Video > Diffusers integration".
This pipeline will:
Load the WanModel
Accept first_frame (image), last_frame (image), and prompt (text) as inputs.
Encode the images and text.
Run the diffusion loop using diffusers schedulers (e.g., UniPCMultistepScheduler as used in T2V example).
Decode the result into video frames.