> For the complete documentation index, see [llms.txt](https://boinc-ai.gitbook.io/diffusers/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://boinc-ai.gitbook.io/diffusers/using-diffusers/tasks/text-to-image.md).

# Text-to-image

## Conditional image generation

![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)![Open In Studio Lab](https://studiolab.sagemaker.aws/studiolab.svg)

Conditional image generation allows you to generate images from a text prompt. The text is converted into embeddings which are used to condition the model to generate an image from noise.

The [DiffusionPipeline](https://huggingface.co/docs/diffusers/v0.21.0/en/api/pipelines/overview#diffusers.DiffusionPipeline) is the easiest way to use a pre-trained diffusion system for inference.

Start by creating an instance of [DiffusionPipeline](https://huggingface.co/docs/diffusers/v0.21.0/en/api/pipelines/overview#diffusers.DiffusionPipeline) and specify which pipeline [checkpoint](https://huggingface.co/models?library=diffusers\&sort=downloads) you would like to download.

In this guide, you’ll use [DiffusionPipeline](https://huggingface.co/docs/diffusers/v0.21.0/en/api/pipelines/overview#diffusers.DiffusionPipeline) for text-to-image generation with [`runwayml/stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5):

Copied

```
>>> from diffusers import DiffusionPipeline

>>> generator = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", use_safetensors=True)
```

The [DiffusionPipeline](https://huggingface.co/docs/diffusers/v0.21.0/en/api/pipelines/overview#diffusers.DiffusionPipeline) downloads and caches all modeling, tokenization, and scheduling components. Because the model consists of roughly 1.4 billion parameters, we strongly recommend running it on a GPU. You can move the generator object to a GPU, just like you would in PyTorch:

Copied

```
>>> generator.to("cuda")
```

Now you can use the `generator` on your text prompt:

Copied

```
>>> image = generator("An image of a squirrel in Picasso style").images[0]
```

The output is by default wrapped into a [`PIL.Image`](https://pillow.readthedocs.io/en/stable/reference/Image.html?highlight=image#the-image-class) object.

You can save the image by calling:

Copied

```
>>> image.save("image_of_squirrel_painting.png")
```

Try out the Spaces below, and feel free to play around with the guidance scale parameter to see how it affects the image quality!

## Stable Diffusion 2.1 Demo

Stable Diffusion 2.1 is the latest text-to-image model from StabilityAI. [Access Stable Diffusion 1 Space here](https://huggingface.co/spaces/stabilityai/stable-diffusion-1)\
For faster generation and API access you can try [DreamStudio Beta](http://beta.dreamstudio.ai/).

Model by [StabilityAI](https://huggingface.co/stabilityai) - backend running JAX on TPUs due to generous support of [Google TRC program](https://sites.research.google/trc/about/) - Gradio Demo by 🤗 Hugging Face

<br>