Stable Diffusion LoRA Fine-tuning

14 repos

Techniques and implementations for training Low-Rank Adaptation (LoRA) modules that efficiently fine-tune text-to-image diffusion models like Stable Diffusion, SDXL, and Flux. LoRA enables lightweight model customization by adapting only a small set of parameters rather than full model weights, making it practical for researchers and practitioners to create specialized image generation capabilities. Repositories in this cluster demonstrate various LoRA training approaches, optimization methods like LCM and TCD, and integration with popular diffusion frameworks.

Related clusters