lllyasviel / lllyasviel/stable-diffusion-webui-forge

LORAs not working with flux1-dev-Q8-0.gguf

Open
#1,501 7 comments 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
13k
Forks
1.7k
PR merge metrics
No merged PRs in 30d

Description

Since commit 13d6f8ed900b0857e9872e67befb02f7ed54da35 LORAs don't seem to work with the flux1-dev-Q8-0.gguf checkpoint.

Generating without a LORA seems fine, but adding one causes the error in the attached txt file.

Tried all LORAs I have and none work, all error.

Trying the same thing with flux1-dev-fp8.safetensors seems fine and does not error.

Issue does not occur when rolling back to ba01ad3

flux1-dev-Q8-0 gguf error.txt

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

Reproduce the failure with flux1-dev-Q8-0.gguf and a LORA, then compare it with flux1-dev-fp8.safetensors and the ba01ad3 revision. Start by examining the attached error output and the changes introduced by commit 13d6f8ed900b0857e9872e67befb02f7ed54da35. Done means LORAs load successfully with the GGUF checkpoint without breaking the working cases.

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
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.