sd-scripts
Local image model training scripts support Stable Diffusion, FLUX.1 and Anima, with LoRA training and image generation on Windows and Linux.
sd-scripts is a collection of Python scripts for people who want to train image models on their own hardware. It suits users comfortable working with scripts who need to adapt a model to their own images or subjects.
- Model training: Train LoRAs for Stable Diffusion 1.x and 2.x, SDXL, SD3 and SD3.5, FLUX.1, LUMINA, HunyuanImage-2.1 and Anima.
- Fine-tuning methods: Use full fine-tuning or DreamBooth with supported models except HunyuanImage-2.1, or train Textual Inversion embeddings for Stable Diffusion and SDXL.
- Inpainting and conditioning: Train inpainting models for SD1.5 and SDXL, and use ControlNet-LLLite training to customize image conditioning.
- Image generation and utilities: Generate images, convert models, tag training images with WD14 Tagger and merge LoRA weights.
The scripts run locally on Windows, Linux and WSL2 using PyTorch. Windows ARM64 is supported, including NVIDIA RTX Spark PCs. NVIDIA GPU use depends on CUDA. The project is open source under the Apache 2.0 license.
Logotyper
