qwen-image-2.1 edit 模式lora训练速度太慢，疑似有问题

Open
#1,704 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

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

Research direction

No file or test is named. First reproduce the Qwen-Image 2.1 edit-mode LoRA training run on an H100 using the reported 1048576-pixel setting, then compare its step time with qwen-image-edit-2511. Done means identifying whether the slowdown is expected or a defect and documenting a verified fix or explanation.

Written by the indexing model from the issue text.

Description

显卡h100, 像素默认1048576 ， 每个step要20多秒， 远大于qwen-image-edit-2511
10/5349 [04:24<39:15:12, 26.47s/it]

Dominant language
Python
Stars
13.1k
Forks
1.3k
Avg merge
13h 15m
Merged PRs (30d)
46

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.

More from modelscope/DiffSynth-Studio

All issues in modelscope/DiffSynth-Studio

Similar issues

More Python issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.