Application
Fine-tuning & TrainingApps & UIs
kohya_ss
1Graphical 2trainer 3for 4Stable 5Diffusion 6LoRAs
the six Ws · specification
W1
Who
Artists and ML practitioners training custom LoRA and Dreambooth models for Stable Diffusion.
W2
What
A Gradio based graphical front end for the kohya sd-scripts training toolkit covering LoRA, Dreambooth and fine-tuning.
W3
Where
Self-hosted locally on a GPU workstation or a rented cloud GPU instance.
W4
When
Popular since 2023 during the Stable Diffusion LoRA training boom and still maintained in 2026.
W5
Why
Makes command-line diffusion model fine-tuning accessible through a point-and-click interface.
W6
With
Wraps kohya-ss/sd-scripts and requires Python, PyTorch and a CUDA GPU with sufficient VRAM.
W7
Watch
Open source under Apache-2.0, self-hosted, no credentials needed, widely used in the Stable Diffusion community, over 12k stars.
alternatives
works with