47 lines
1.8 KiB
Plaintext
47 lines
1.8 KiB
Plaintext
<!--Copyright 2022 The HuggingFace Team. All rights reserved.
|
|
|
|
Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
|
|
the License. You may obtain a copy of the License at
|
|
|
|
http://www.apache.org/licenses/LICENSE-2.0
|
|
|
|
Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
|
|
an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
|
|
specific language governing permissions and limitations under the License.
|
|
-->
|
|
|
|
# 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.
|
|
|
|
```python
|
|
from torch import autocast
|
|
import requests
|
|
from PIL import Image
|
|
from io import BytesIO
|
|
|
|
from diffusers import StableDiffusionImg2ImgPipeline
|
|
|
|
# load the pipeline
|
|
device = "cuda"
|
|
pipe = StableDiffusionImg2ImgPipeline.from_pretrained(
|
|
"CompVis/stable-diffusion-v1-4", 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 = init_image.resize((768, 512))
|
|
|
|
prompt = "A fantasy landscape, trending on artstation"
|
|
|
|
with autocast("cuda"):
|
|
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 [](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/image_2_image_using_diffusers.ipynb)
|
|
|