lllyasviel / lllyasviel/FramePack

对于“摘面具动作”生成的视频不正确

Open
#275 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
17.3k
Forks
1.7k
PR merge metrics
No merged PRs in 30d

Description

![Image](https://github.com/user-attachments/assets/1ca352e9-26c7-465c-a89f-fa47ad56ef6e)

![Image](https://github.com/user-attachments/assets/681c6cc9-6efd-412c-b783-ceb5c50811ab)
对于这个首尾帧,使用语句“First, raise your slender right hand without any clothes to cover it, and then slowly remove the mask with your hand. Don't let the mask disappear suddenly, show a smile.”生成的视频,面具直接消失

Contributor guide

No contributing guide indexed for this repository

Research direction

Reproduce the issue using the supplied first and last frames and the English prompt: the generated video should show the hand removing the mask rather than making it disappear suddenly. The payload names no files or tests, so begin by locating the video-generation entry point and add a regression check for this behavior.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.