lllyasviel / lllyasviel/FramePack

I found that the consistency between the contents generated by Framepack and Framepack F1 and the input images is quite poor.

Open
#548 2 comments 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
17.3k
Forks
1.7k
PR merge metrics
No merged PRs in 30d

Description

I found that the consistency between the contents generated by Framepack and Framepack F1 and the input images is quite poor. Upon closer inspection, there are noticeable differences in details. Additionally, the last frame generated by Framepack F1 tends to become very similar to the input image, meaning that the first frame and the last frame are basically the same. Is there a way to avoid this by changing the inference strategy?

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reviewing the Framepack and Framepack F1 inference strategy, then reproduce the reported differences between the input image and generated content. Compare the first and last generated frames with the input image; done means improved detail consistency and no unintended duplication of the endpoints.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.