mkurman Overview
HuggingFace Diffusers provides diffusion models for text-to-image, image-to-image, inpainting, and super-resolution. Supports Stable Diffusion, Flux, and SDXL with full pipeline customization.
Installation
uv pip install diffusers transformers accelerate
Text-to-Image
from diffusers import StableDiffusionPipeline
import torch
pipe = StableDiffusionPipeline.from_pretrained(
"runwayml/stable-diffusion-v1-5",
torch_dtype=torch.float16,
).to("cuda")
image = pipe("a photo of a cat wearing a space suit").images[0]
image.save("cat_astronaut.png")
SDXL
from diffusers import DiffusionPipeline
pipe = DiffusionPipeline.from_pretrained(
"stabilityai/stable-diffusion-xl-base-1.0",
torch_dtype=torch.float16,
).to("cuda")
image = pipe(prompt="a cinematic shot of a mountain", num_inference_steps=30).images[0]
Inpainting
from diffusers import StableDiffusionInpaintPipeline
pipe = StableDiffusionInpaintPipeline.from_pretrained(
"runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16,
).to("cuda")
image = pipe(prompt="cat", image=init_image, mask_image=mask_image).images[0]
Workflow
- Install with uv pip install diffusers
- Choose pipeline: StableDiffusionPipeline, StableDiffusionXLPipeline, FluxPipeline
- Load model with .from_pretrained(model_id)
- Generate with pipe(prompt).images[0]
- Customize: num_inference_steps, guidance_scale, negative_prompt
- Save with .save() or convert to PIL for further processing