lllyasviel / lllyasviel/stable-diffusion-webui-forge
[Bug]: Freshly trained SDXL Lora from Kohya_ss doesn't show up in Forge, but FOOOCUS can see, and use them
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13k
- Forks
- 1.7k
- PR merge metrics
- No merged PRs in 30d
Description
Checklist
- The issue exists after disabling all extensions
- The issue exists on a clean installation of webui
- The issue is caused by an extension, but I believe it is caused by a bug in the webui
- The issue exists in the current version of the webui
- The issue has not been reported before recently
- The issue has been reported before but has not been fixed yet
What happened?
I trained an SDXL lora from Kohya. Both a SD1.5 and an SDXL using the same image data set/captioning.
Forge does not see the SDXL Lora, but sees the SD1.5. Forge doesn't see it either, but FOOOCUS can see, and use the LoRA as intended.
Steps to reproduce the problem
Put an SDXL Lora trained with the current version of Kohya, into the LORA folder.
LORA doesn't show up in the GUI
What should have happened?
LORA should be visible, and usable in the GUI
What browsers do you use to access the UI ?
Google Chrome
Sysinfo
Console logs
Nothing of interest in console logs, as no action was performed
Additional information
No response
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reproducing the issue with an SDXL LoRA trained with Kohya and placed in the LORA folder, then compare Forge's visibility with Fooocus using the linked sysinfo. Done means the SDXL LoRA appears in the Forge GUI and can be used; the payload does not name a source file or test to inspect.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- machine-learning, python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 38/100