Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

Text-Guided Image-to-Image Generation

The StableDiffusionImg2ImgPipeline lets you pass a text prompt and an initial image to condition the generation of new images.

import torch
import requests
from PIL import Image
from io import BytesIO

from diffusers import StableDiffusionImg2ImgPipeline

# load the pipeline
device = "cuda"
pipe = StableDiffusionImg2ImgPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5", revision="fp16", torch_dtype=torch.float16
).to(device)

# let's download an initial image
url = "https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg"

response = requests.get(url)
init_image = Image.open(BytesIO(response.content)).convert("RGB")
init_image.thumbnail((768, 768))

prompt = "A fantasy landscape, trending on artstation"

images = pipe(prompt=prompt, init_image=init_image, strength=0.75, guidance_scale=7.5).images

images[0].save("fantasy_landscape.png")

You can also run this example on colab Open In Colab