invoke-ai / invoke-ai/invoke-training

Bad Results with Example Config

Open
#149 2 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
206
Forks
35
PR merge metrics
No merged PRs in 30d

Description

The default example [here](https://github.com/invoke-ai/invoke-training/blob/main/src/invoke_training/sample_configs/sdxl_lora_masks_gnome_1x24gb.yaml#L30) gives me very bad and mangled results. Replacing the linked sdxl model to [this one](https://civitai.com/models/101055?modelVersionId=128078) fixes the issue for me.
Does it need the commented out vae enabled or is the base model this links to bad?

I noticed this when i tried to learn to make a lora and eventually plugged in a different sdxl model because i tried everything else to get a good result and it worked immediately.

Can i also make a more complex and involved example and donate it to this repo? The current examples are very bare bones and i would like to share a more real project to help others learn. And also something anyone can take and just run for training to get a good known working example to work off of. I, of course, will take the images myself of a real world object and base the lora on that to not have any licensing issues.

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.