kohya-ss / kohya-ss/sd-scripts

[Feature] update sdxl sample image creation

Open
#940 0 comments 0 reactions 0 assignees View on GitHub
enhancement
Dominant language
Python
Stars
7.2k
Forks
1.2k
Avg merge
11m
Merged PRs (30d)
2

Description

In order to create sdxl sample images with separated prompt inputs update to the current version of
https://github.com/huggingface/diffusers/blob/main/examples/community/lpw_stable_diffusion_xl.py

![1](https://github.com/kohya-ss/sd-scripts/assets/71378654/eb916b55-b52b-4a4c-aaf4-5bcf4640269d)

Contributor guide

No contributing guide indexed for this repository

Research direction

Compare the repository's SDXL sample-image creation entry point with Hugging Face's examples/community/lpw_stable_diffusion_xl.py. Trace how prompts are currently passed, then update the integration to support separated prompt inputs and match the current upstream behavior. Done means SDXL sample images can be created with separated prompts.

Written by the indexing model from the issue text.

Assessment

Tech stack
huggingface, python
Domain
machine-learning
Issue type
Feature
Difficulty
3/5
Estimated time
1-2 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.