lllyasviel / lllyasviel/FramePack

pulsing every second with new F1 model

Open
#476 13 comments 4 reactions 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've noticed that for a lot of my generations there's a noticeable "pulse" every second in the movement and contrast since trying out F1. This was not an issue in the previous model. Does anyone know if there's anything that could be causing this?

I'm using a 4090 on Ubuntu with SageAttention2 compiled with Cuda 12.8.

I've tried with and without TeaCache - both produce the same artifacts.

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

The report names no file, test, or entry point. Start by reproducing a minimal F1 generation on the stated 4090/Ubuntu/SageAttention2 setup, comparing the previous model and both TeaCache variants. Done means the one-second pulse has a reproducible cause and a verified fix or documented limitation.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, ubuntu
Domain
computer-vision, machine-learning, performance
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.