modelscope / modelscope/DiffSynth-Studio

qwen image lora may get bad result when cfg is 4

Open
#832 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

I train a qwen image lora, however, sometimes when the CFG is set to 4, it tends to produce results of relatively low quality. Reducing the CFG value can improve image quality, but the adherence to the instructions will decrease.

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, entry points, or tests are identified in the report. First reproduce Qwen image LoRA generation at CFG 4 and at lower CFG values, then trace the relevant training and inference paths; done means identifying the cause of the quality regression and validating a fix against both image quality and instruction adherence.

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
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.