aigc-apps / aigc-apps/VideoX-Fun

CogVideoX 1.1 may have improved motion, but quality is behind I2v/Interpolation

Open
#43 0 comments 1 reaction 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

I2V and the latest https://github.com/feizc/CogvideX-Interpolation models which is a fine-tune of the official I2V are just better at coherent motion provided a frame. However, these models have significant limitations with resolution and frame length... things CogVideoX-Fun solves.

What is the process of creating a "fun" version of a CogVideoX model like Interpolation? May you guys please consider doing a "Fun" version of the https://github.com/feizc/CogvideX-Interpolation finetune please?

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

No project files, tests, or training entry points are identified in the issue. Start by reviewing VideoX-Fun's documented model-training process and compare it with the CogVideoX-Interpolation models; done would mean establishing a feasible process or delivering a compatible Fun fine-tune with its limitations documented.

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.