Directory
Published directory entries matching your search.
Swift Core ML Diffusers is a native Swift UI application demonstrating how to integrate Apple's Core ML Stable Diffusion implementation. On first launch it downloads a Core ML version of Stability AI's Stable Diffusion v2 base from the Hugging Face Hub. It uses the DPM-Solver++ scheduler for inference and supports models quantized with coremltools version 7 or better. The repository has been archived and is read-only.
deep-floyd/IF is a GitHub repository for the IF image generation model developed by DeepFloyd Lab at StabilityAI. It provides documentation for minimum model requirements, quick start guides, local notebook support, and integration with the Hugging Face Diffusers library for model use.
Materials for the Hugging Face Diffusion Models Course, a free course on diffusion models. It covers theory, generating images and audio with Diffusers, training and fine-tuning models, and conditional generation. Prerequisites include Python skills and basics in deep learning and PyTorch.
Lora is a repository applying low-rank adaptation to fine-tune diffusion models. It offers fine-tuning that produces small end results of 1MB to 6MB, compatibility with diffusers, support for inpainting, merging checkpoints, and CLIP, Unet and token fine-tuning pipelines.
PEFT is a library of parameter-efficient fine-tuning methods from Hugging Face. It adapts large pretrained models by fine-tuning only a small number of extra parameters instead of all model parameters, which decreases computational and storage costs. It is integrated with Transformers, Diffusers and Accelerate.
