modelscope / modelscope/DiffSynth-Studio

wan2.1 vae finetuning script

Open
#650 5 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
13.1k
Forks
1.3k
Avg merge
13h 12m
Merged PRs (30d)
45

Description

Hi,
I finetuned wan2.1-1.3b-t2v on my own dataset. I use vae to encode/decode the original video and compare the original video with reconstructed video. I found that psnr is around 26, which is not very satisfying. I guess I need to finetune vae on my own datasets for few steps. But I can't find the finetuning script for wan2.1 vae.

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 by locating the Wan2.1 VAE implementation and any existing training or finetuning entry points in the repository. Determine the expected dataset, training objectives, configuration, and validation workflow before defining what a complete finetuning script should provide; the issue does not name files or tests.

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
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.