Using LoRA for Efficient Stable Diffusion Fine-Tuning

Understanding LoRA Rank Trade-offs in Diffusion Model Fine-Tuning

The study investigates how the rank of Low‑Rank Adaptation (LoRA) affects diffusion model fine‑tuning on CIFAR‑10 using a DDPM U‑Net. Experiments with ranks 2, 4, 8, 16, and 32 show that moderate ranks—particularly rank 4—yield the best FID scores while keeping trainable parameters, runtime, and GPU memory low. Higher ranks offer only marginal improvements at a higher computational cost, suggesting that small‑to‑moderate ranks are efficient defaults for fixed training budgets.

Finetune Stable Diffusion Models with DDPO via TRL

Fine-tuning Stable Diffusion models on Intel CPUs

Stable Diffusion with 🧨 Diffusers

Diffusers welcomes Stable Diffusion 3

FourTune: Towards Fully 4-Bit Efficient Post-Training for Diffusion Models

arXiv:2607. 05711v1 Announce Type: new Abstract: Diffusion models have become a dominant paradigm for high-quality generative modeling, while post-training is essential for adapting them to diverse downstream applications.

Beyond LoRA: Can you beat the most popular fine-tuning technique?

Diffusers welcomes Stable Diffusion 3.5 Large

Faster Stable Diffusion with Core ML on iPhone, iPad, and Mac

Accelerating Stable Diffusion Inference on Intel CPUs

(LoRA) Fine-Tuning FLUX.1-dev on Consumer Hardware

Instruction-tuning Stable Diffusion with InstructPix2Pix