The Diffusers library is the Hugging Face standard for working with image generation models — Stable Diffusion, FLUX, and more.

Quick Start

pip install diffusers accelerate

from diffusers import StableDiffusionPipeline
import torch

pipe = StableDiffusionPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5",
    torch_dtype=torch.float16
).to("cuda")

image = pipe("A golden retriever on the moon, photorealistic").images[0]
image.save("output.png")

Supported Models

• Stable Diffusion 1.5, 2.1, XL
• FLUX.1 — state-of-the-art open image generation
• ControlNet — controlled image generation
• InstructPix2Pix — edit images with text instructions

Reference:

Diffusers documentation

https://huggingface.co/docs/diffusers