Diffusers

Diffusers

Diffusers is the leading open-source library for running and fine-tuning diffusion models. It provides a modular, batteries-included API covering Stable Diffusion, FLUX, PixArt, Kandinsky, and dozens more — for text-to-image, image-to-image, inpainting, video generation, and audio synthesis.

Key Features

• Model zoo: 50,000+ pretrained checkpoints on the Hugging Face Hub, loadable in one line
• Pipelines: high-level DiffusionPipeline API for immediate inference; mix-and-match schedulers (DDPM, DDIM, DPM-Solver, etc.)
• Training scripts: LoRA, DreamBooth, textual inversion, full fine-tuning examples for all major architectures
• ControlNet & IP-Adapter: structural conditioning and reference-image style transfer built in
• Memory efficiency: FP16, BF16, 8-bit quantisation, sequential CPU offload, and enable_xformers_memory_efficient_attention
• Multi-modal: text-to-image, image-to-video, text-to-video, text-to-audio, depth-to-image, and more

Quick Start

pip install diffusers transformers accelerate

from diffusers import DiffusionPipeline
import torch

pipe = DiffusionPipeline.from_pretrained(
    "black-forest-labs/FLUX.1-schnell",
    torch_dtype=torch.bfloat16
).to("cuda")

image = pipe("A photorealistic cat astronaut on the moon").images[0]
image.save("output.png")

npx ai-supply add diffusers-image-generation

Curated mirror of the open-source Diffusers (Apache-2.0). Get it from the source.