modelscope / modelscope/DiffSynth-Studio

Question about optimal hyper parameters for training Qwen-Image-Edit-2509

Open
#994 12 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

DiffSynth is great. I am trying to train Qwen-Image-Edit-2509. I have a dataset of 5.4k examples. I'm curious if full parameter fine-tuning could be feasible with this dataset size, and if so at what hyperparameters? I've tried 1e-5 and 5e-6 at a 128 effective batch size and the model degrades when I evaluate it.

The next thing I'll try is LoRA, but I'm just confused how I couldn't get the training to have any positive impact on the model at any point across a variety of training runs. Curious if anyone, besides the Qwen team, knows how to successfully fine-tune this model. Thanks!

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 file, test, or entry point is identified in the issue. Start by reviewing the reported full-parameter training runs, dataset size, learning rates, and effective batch size, then compare them with the proposed LoRA approach; done would require an agreed, reproducible fine-tuning configuration that improves evaluation results.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.