7942bb8dc2
* Fix typos, improve, update; kandinsky doesn't want fp16 due to deprecation; ogkalu and kohbanye don't have safetensor; add make_image_grid for better visualization * Update inpaint.md * Remove erronous Space * Update docs/source/en/using-diffusers/conditional_image_generation.md Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com> * Update img2img.md * load_image() already converts to RGB * Update depth2img.md * Update img2img.md * Update inpaint.md --------- Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
2.6 KiB
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:
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:
generator.to("cuda")
Now you can use the generator to generate an image:
image = generator().images[0]
image
The output is by default wrapped into a PIL.Image object.
You can save the image by calling:
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!