modelscope / modelscope/DiffSynth-Studio

lora微调z-image报错q,k和v的dtype不同

Open
#1,212 0 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

Image

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

Start by reproducing the reported LoRA fine-tuning failure for z-image and inspect the attached screenshot for the exact q, k, and v dtype error. The issue names no files, tests, or entry points, so trace the failing attention path from the reproduction until the three dtypes are consistent, then rerun the same fine-tuning case to confirm the error is resolved.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.