kohya sd-scripts

sd-scripts

English / 日本語

Table of Contents

Click to expand

- Introduction
    - Supported Models
    - Features
    - Sponsors
    - Support the Project
- Documentation
    - Training Documentation (English and Japanese)
    - Other Documentation (English and Japanese)
- For Developers Using AI Coding Agents
- Windows Installation
    - Windows Required Dependencies
    - Installation Steps
    - About requirements.txt and PyTorch
    - xformers installation (optional)
- Linux/WSL2 Installation
    - DeepSpeed installation (experimental, Linux or WSL2 only)
- Upgrade
    - Upgrade PyTorch
- Credits
- License

Introduction

This repository contains training, generation and utility scripts for Stable Diffusion and other image generation models.

Sponsors

We are grateful to the following companies for their generous sponsorship:

Support the Project

If you find this project helpful, please consider supporting its development via GitHub Sponsors. Your support is greatly appreciated!

Change History

- Version 0.12.1 (2026-10-18):
    - Added support for LoRA training of MOSS-Image (OpenMOSS), a 5B DiT with the Qwen3.5-9B text encoder and the FLUX.2 VAE. PR #2458, PR #2459, PR #2460, PR #2461
        - moss_image_train_network.py trains LoRA (and LoHa / LoKr) for the DiT and optionally for the text encoder. The official diffusers-format shards and the ComfyUI single-file checkpoints can be loaded. For details, please refer to the documentation.
        - ConvRot INT8 quantization of the base weights (--convrot_int8 for the DiT, --convrot_int8_text_encoder for the text encoder, ported from Musubi Tuner) is available as an alternative to fp8. The ComfyUI pre-quantized *_int8_convrot.safetensors files are detected automatically. The fused int8 kernels require triton (triton-windows on Windows).
        - The DiT LoRA can be used in ComfyUI without conversion. moss_image_minimal_inference.py is also available for inference with LoRA.
        - tools/cache_latents.py and tools/cache_text_encoder_outputs.py support MOSS-Image with --moss_image.
        - The LoRA module is the new generic networks.lora_generic (regex-based module selection, network_reg_dims / network_reg_lrs, the same as networks.lora_anima). It is expected to be the base for other architectures in the future.
    - Added enable_multiline_caption subset option (--enable_multiline_caption) to use captions containing line breaks as they are, for models with LLM-based text encoders (Anima, Lumina, HunyuanImage, etc.).
        - Lines starting with multiline_caption_separator (default ---===---) separate multiple caption candidates for one image, and one candidate is chosen randomly at each step. In metadata files for fine tuning, caption can also be a list of strings. For details, please refer to the dataset config documentation.
        - In .txt sample prompt files, \n (backslash + n) is now converted to a line break.
        - Fixed caption_prefix / caption_suffix being added only to the first / last line of multi-line captions (with enable_wildcard, the prefix was attached only to the first line and the suffix only to the last line; without it, the suffix was lost).
    - Fixed c

……（后略，见原文）