Diffusers documentation

Adapt a model to a new task

Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

Adapt a model to a new task

Many diffusion systems share the same components, allowing you to adapt a pretrained model for one task to an entirely different task.

This guide will show you how to adapt a pretrained text-to-image model for inpainting by initializing and modifying the architecture of a pretrained UNet2DConditionModel.

Configure UNet2DConditionModel parameters

A UNet2DConditionModel by default accepts 4 channels in the input sample. For example, load a pretrained text-to-image model like runwayml/stable-diffusion-v1-5 and take a look at the number of in_channels:

from diffusers import StableDiffusionPipeline

pipeline = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", use_safetensors=True)

Inpainting requires 9 channels in the input sample. You can check this value in a pretrained inpainting model like runwayml/stable-diffusion-inpainting:

from diffusers import StableDiffusionPipeline

pipeline = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-inpainting", use_safetensors=True)

To adapt your text-to-image model for inpainting, you’ll need to change the number of in_channels from 4 to 9.

Initialize a UNet2DConditionModel with the pretrained text-to-image model weights, and change in_channels to 9. Changing the number of in_channels means you need to set ignore_mismatched_sizes=True and low_cpu_mem_usage=False to avoid a size mismatch error because the shape is different now.

from diffusers import UNet2DConditionModel

model_id = "runwayml/stable-diffusion-v1-5"
unet = UNet2DConditionModel.from_pretrained(

The pretrained weights of the other components from the text-to-image model are initialized from their checkpoints, but the input channel weights (conv_in.weight) of the unet are randomly initialized. It is important to finetune the model for inpainting because otherwise the model returns noise.

< > Update on GitHub