zai-org / zai-org/SCAIL-2

Question about training code and character lora

Open
#28 4 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
1.2k
Forks
90
Avg merge
19h 19m
Merged PRs (30d)
1

Description

First of all thank you so much for your willing to open the training code. Is there any chance to know how the progress going with that? I don't mean to pressure, but I'd love to know if it's about months or weeks?

Also can you provide informations about training character lora - do we need to train on videos or we can put just images in dataset? Images works very well on ltx and used to work on wan. Not sure how it will be with scail-2
Maybe it's good to put this in documentation since many people who decide to train lora wants to do a character lora.

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

The issue names no files, tests, or entry points. Start by locating the training documentation and current character-LoRA guidance, then verify the training-code status and whether image or video datasets are supported. Done means documenting those answers clearly for users who want to train character LoRAs.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
documentation, machine-learning
Issue type
Documentation
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.