Diffusers

Join the Hugging Face community

and get access to the augmented documentation experience

Collaborate on models, datasets and Spaces

Faster examples with accelerated inference

Switch between documentation themes

to get started

AutoencoderKLMochi

The 3D variational autoencoder (VAE) model with KL loss used in Mochi was introduced in Mochi 1 Preview by Tsinghua University & ZhipuAI.

The model can be loaded with the following code snippet.

from diffusers import AutoencoderKLMochi

vae = AutoencoderKLMochi.from_pretrained("genmo/mochi-1-preview", subfolder="vae", torch_dtype=torch.float32).to("cuda")

AutoencoderKLMochi

class diffusers.AutoencoderKLMochi

< source >

( in_channels: int = 15 out_channels: int = 3 encoder_block_out_channels: typing.Tuple[int] = (64, 128, 256, 384) decoder_block_out_channels: typing.Tuple[int] = (128, 256, 512, 768) latent_channels: int = 12 layers_per_block: typing.Tuple[int, ...] = (3, 3, 4, 6, 3) act_fn: str = 'silu' temporal_expansions: typing.Tuple[int, ...] = (1, 2, 3) spatial_expansions: typing.Tuple[int, ...] = (2, 2, 2) add_attention_block: typing.Tuple[bool, ...] = (False, True, True, True, True) latents_mean: typing.Tuple[float, ...] = (-0.06730895953510081, -0.038011381506090416, -0.07477820912866141, -0.05565264470995561, 0.012767231469026969, -0.04703542746246419, 0.043896967884726704, -0.09346305707025976, -0.09918314763016893, -0.008729793427399178, -0.011931556316503654, -0.0321993391887285) latents_std: typing.Tuple[float, ...] = (0.9263795028493863, 0.9248894543193766, 0.9393059390890617, 0.959253732819592, 0.8244560132752793, 0.917259975397747, 0.9294154431013696, 1.3720942357788521, 0.881393668867029, 0.9168315692124348, 0.9185249279345552, 0.9274757570805041) scaling_factor: float = 1.0 )

Parameters

in_channels (int, optional, defaults to 3) — Number of channels in the input image.
out_channels (int, optional, defaults to 3) — Number of channels in the output.
block_out_channels (Tuple[int], optional, defaults to (64,)) — Tuple of block output channels.
act_fn (str, optional, defaults to "silu") — The activation function to use.
scaling_factor (float, optional, defaults to 1.15258426) — The component-wise standard deviation of the trained latent space computed using the first batch of the training set. This is used to scale the latent space to have unit variance when training the diffusion model. The latents are scaled with the formula z = z * scaling_factor before being passed to the diffusion model. When decoding, the latents are scaled back to the original scale with the formula: z = 1 / scaling_factor * z. For more details, refer to sections 4.3.2 and D.1 of the High-Resolution Image Synthesis with Latent Diffusion Models paper.

A VAE model with KL loss for encoding images into latents and decoding latent representations into images. Used in Mochi 1 preview.

This model inherits from ModelMixin. Check the superclass documentation for it’s generic methods implemented for all models (such as downloading or saving).

wrapper

< source >

( *args **kwargs )

disable_slicing

< source >

( )

Disable sliced VAE decoding. If enable_slicing was previously enabled, this method will go back to computing decoding in one step.

disable_tiling

< source >

( )

Disable tiled VAE decoding. If enable_tiling was previously enabled, this method will go back to computing decoding in one step.

enable_slicing

< source >

( )

Enable sliced VAE decoding. When this option is enabled, the VAE will split the input tensor in slices to compute decoding in several steps. This is useful to save some memory and allow larger batch sizes.

enable_tiling

< source >

( tile_sample_min_height: typing.Optional[int] = None tile_sample_min_width: typing.Optional[int] = None tile_sample_stride_height: typing.Optional[float] = None tile_sample_stride_width: typing.Optional[float] = None )

Parameters

tile_sample_min_height (int, optional) — The minimum height required for a sample to be separated into tiles across the height dimension.
tile_sample_min_width (int, optional) — The minimum width required for a sample to be separated into tiles across the width dimension.
tile_sample_stride_height (int, optional) — The minimum amount of overlap between two consecutive vertical tiles. This is to ensure that there are no tiling artifacts produced across the height dimension.
tile_sample_stride_width (int, optional) — The stride between two consecutive horizontal tiles. This is to ensure that there are no tiling artifacts produced across the width dimension.

Enable tiled VAE decoding. When this option is enabled, the VAE will split the input tensor into tiles to compute decoding and encoding in several steps. This is useful for saving a large amount of memory and to allow processing larger images.

tiled_decode

< source >

( z: Tensor return_dict: bool = True ) → ~models.vae.DecoderOutput or tuple

Parameters

z (torch.Tensor) — Input batch of latent vectors.
return_dict (bool, optional, defaults to True) — Whether or not to return a ~models.vae.DecoderOutput instead of a plain tuple.