aigc-apps / aigc-apps/VideoX-Fun

How to train a customized Cogvideox-fun-v1.1-5b-control model based on CogVideoX-Fun-V1.1-5b-InP weights?

Open
#98 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
2.3k
Forks
188
Avg merge
2d 22h
Merged PRs (30d)
3

Description

Hi! I am looking to train a customized controlled video generation model using specific control data types (e.g., normal maps or optical flow).
The released pre-trained model has been trained on non-target control types. I aim to leverage CogVideoX-Fun-V1.1-5b-InP model's weights and perform training based on the framework of CogVideoX-Fun-V1.1-5b-Control.
How can I achieve this using the provided training code? Any advice would be greatly appreciated.

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 with the provided training code and the CogVideoX-Fun-V1.1-5b-Control and CogVideoX-Fun-V1.1-5b-InP weights named in the issue. Trace how the training code loads weights and handles control data types such as normal maps or optical flow. Done means a documented, reproducible procedure for training the customized model.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Documentation
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.