Unconditional image generation

Unconditional image generation

Unconditional image generation is a relatively straightforward task. The model only generates images - without any additional context like text or an image - resembling the training data it was trained on.

The DiffusionPipeline is the easiest way to use a pre-trained diffusion system for inference.

Start by creating an instance of DiffusionPipeline and specify which pipeline checkpoint you would like to download. You can use any of the 🧨 Diffusers checkpoints from the Hub (the checkpoint you’ll use generates images of butterflies).

💡 Want to train your own unconditional image generation model? Take a look at the training guide to learn how to generate your own images.

In this guide, you’ll use DiffusionPipeline for unconditional image generation with DDPM:

Copied

>>> from diffusers import DiffusionPipeline

>>> generator = DiffusionPipeline.from_pretrained("anton-l/ddpm-butterflies-128", use_safetensors=True)

The 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 to generate an image:

Copied

>>> image = generator().images[0]

The output is by default wrapped into a PIL.Image object.

You can save the image by calling:

Copied

>>> image.save("generated_image.png")

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

Unconditional butterflies

A DDPM scheduler and UNet model trained (from this checkpoint) on a subset of the Smithsonian Butterflies dataset for unconditional image generation

https://huggingface.co/spaces/stevhliu/ddpm-butterflies-128