modelscope / modelscope/DiffSynth-Studio

No metadata in trained lora? no images validation?

Open
#1,155 1 comment 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

Hello Team, I am training a Qwen dit 2509 Lora, and the logic is so confusing. Where can I see the total number of steps during the training? it only shows the number of iterations.

Why is there no metadata in the trained LoRA?

Why is there no option so after a lora is trained, let's say at 250 steps, then first it shows some samples or saves samples somewhere and then proceeds from step 251.

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 files, tests, or entry points are named. Start by locating the Qwen DiT 2509 LoRA training entry point and its iteration, checkpoint, and sample-handling paths; done would require an agreed scope covering total-step visibility, LoRA metadata, and post-checkpoint samples or validation.

Written by the indexing model from the issue text.

Assessment

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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.