kohya-ss / kohya-ss/sd-scripts

Flux dataset training higher than 1024 pixel images = bad results

Open
#1,521 4 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
7.2k
Forks
1.2k
Avg merge
11m
Merged PRs (30d)
2

Description

When my images in my dataset are higher than 1024, like 2048 or 2536 the likeness in my training is gone. is there any way to fix this or is it better to train on lower res images?

Contributor guide

No contributing guide indexed for this repository

Research direction

The report names no source files, entry points, or tests. First clarify the expected behavior, dataset and training configuration, and a reproducible comparison between resolutions; done would require an agreed fix or documented guidance supported by a regression check.

Written by the indexing model from the issue text.

Assessment

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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.