Diffusers contains pretrained models for popular algorithms and modules for creating the next set of diffusion models. The primary function of these models is to denoise an input sample, by modeling the distribution $p_\theta(\mathbf{x}_{t-1}|\mathbf{x}_t)$. The models are built on the base class ['ModelMixin'] that is a torch.nn.module with basic functionality for saving and loading models both locally and from the HuggingFace hub.

[[autodoc]] ModelMixin

[[autodoc]] models.unet_2d.UNet2DOutput

[[autodoc]] UNet2DModel

[[autodoc]] models.unet_1d.UNet1DOutput

[[autodoc]] UNet1DModel

[[autodoc]] models.unet_2d_condition.UNet2DConditionOutput

[[autodoc]] UNet2DConditionModel

[[autodoc]] models.vae.DecoderOutput

[[autodoc]] models.vae.VQEncoderOutput

[[autodoc]] VQModel

[[autodoc]] models.vae.AutoencoderKLOutput

[[autodoc]] AutoencoderKL

[[autodoc]] Transformer2DModel

[[autodoc]] models.attention.Transformer2DModelOutput

[[autodoc]] FlaxModelMixin

[[autodoc]] models.unet_2d_condition_flax.FlaxUNet2DConditionOutput

[[autodoc]] FlaxUNet2DConditionModel

[[autodoc]] models.vae_flax.FlaxDecoderOutput

[[autodoc]] models.vae_flax.FlaxAutoencoderKLOutput

[[autodoc]] FlaxAutoencoderKL