lllyasviel / lllyasviel/FramePack

Using FramePack to achieve T2V

Open
#568 3 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

Fantastic work! I'm wondering if I can use FramePack to achieve T2V. It seems that FramePack needs an image as input. However, both Wan and HunYuan provide T2V models.

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by reviewing FramePack's current image-input requirement, then compare it with the T2V capabilities of the Wan and HunYuan models mentioned in the issue. Determine the scope needed for text-only video generation and define completion as a documented, working T2V path or a clear explanation of why it is unsupported.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
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.