Diffusers

You are viewing main version, which requires installation from source. If you'd like regular pip install, checkout the latest stable version (v0.35.1).

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

SanaVideoTransformer3DModel

A Diffusion Transformer model for 3D data (video) from SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer from NVIDIA and MIT HAN Lab, by Junsong Chen, Yuyang Zhao, Jincheng Yu, Ruihang Chu, Junyu Chen, Shuai Yang, Xianbang Wang, Yicheng Pan, Daquan Zhou, Huan Ling, Haozhe Liu, Hongwei Yi, Hao Zhang, Muyang Li, Yukang Chen, Han Cai, Sanja Fidler, Ping Luo, Song Han, Enze Xie.

The abstract from the paper is:

We introduce SANA-Video, a small diffusion model that can efficiently generate videos up to 720x1280 resolution and minute-length duration. SANA-Video synthesizes high-resolution, high-quality and long videos with strong text-video alignment at a remarkably fast speed, deployable on RTX 5090 GPU. Two core designs ensure our efficient, effective and long video generation: (1) Linear DiT: We leverage linear attention as the core operation, which is more efficient than vanilla attention given the large number of tokens processed in video generation. (2) Constant-Memory KV cache for Block Linear Attention: we design block-wise autoregressive approach for long video generation by employing a constant-memory state, derived from the cumulative properties of linear attention. This KV cache provides the Linear DiT with global context at a fixed memory cost, eliminating the need for a traditional KV cache and enabling efficient, minute-long video generation. In addition, we explore effective data filters and model training strategies, narrowing the training cost to 12 days on 64 H100 GPUs, which is only 1% of the cost of MovieGen. Given its low cost, SANA-Video achieves competitive performance compared to modern state-of-the-art small diffusion models (e.g., Wan 2.1-1.3B and SkyReel-V2-1.3B) while being 16x faster in measured latency. Moreover, SANA-Video can be deployed on RTX 5090 GPUs with NVFP4 precision, accelerating the inference speed of generating a 5-second 720p video from 71s to 29s (2.4x speedup). In summary, SANA-Video enables low-cost, high-quality video generation.

The model can be loaded with the following code snippet.

from diffusers import SanaVideoTransformer3DModel
import torch

transformer = SanaVideoTransformer3DModel.from_pretrained("Efficient-Large-Model/SANA-Video_2B_480p_diffusers", subfolder="transformer", torch_dtype=torch.bfloat16)

SanaVideoTransformer3DModel

class diffusers.SanaVideoTransformer3DModel

< source >

( in_channels: int = 16 out_channels: typing.Optional[int] = 16 num_attention_heads: int = 20 attention_head_dim: int = 112 num_layers: int = 20 num_cross_attention_heads: typing.Optional[int] = 20 cross_attention_head_dim: typing.Optional[int] = 112 cross_attention_dim: typing.Optional[int] = 2240 caption_channels: int = 2304 mlp_ratio: float = 2.5 dropout: float = 0.0 attention_bias: bool = False sample_size: int = 30 patch_size: typing.Tuple[int, int, int] = (1, 2, 2) norm_elementwise_affine: bool = False norm_eps: float = 1e-06 interpolation_scale: typing.Optional[int] = None guidance_embeds: bool = False guidance_embeds_scale: float = 0.1 qk_norm: typing.Optional[str] = 'rms_norm_across_heads' rope_max_seq_len: int = 1024 )

Parameters

in_channels (int, defaults to 16) — The number of channels in the input.
out_channels (int, optional, defaults to 16) — The number of channels in the output.
num_attention_heads (int, defaults to 20) — The number of heads to use for multi-head attention.
attention_head_dim (int, defaults to 112) — The number of channels in each head.
num_layers (int, defaults to 20) — The number of layers of Transformer blocks to use.
num_cross_attention_heads (int, optional, defaults to 20) — The number of heads to use for cross-attention.
cross_attention_head_dim (int, optional, defaults to 112) — The number of channels in each head for cross-attention.
cross_attention_dim (int, optional, defaults to 2240) — The number of channels in the cross-attention output.
caption_channels (int, defaults to 2304) — The number of channels in the caption embeddings.
mlp_ratio (float, defaults to 2.5) — The expansion ratio to use in the GLUMBConv layer.
dropout (float, defaults to 0.0) — The dropout probability.
attention_bias (bool, defaults to False) — Whether to use bias in the attention layer.
sample_size (int, defaults to 32) — The base size of the input latent.
patch_size (int, defaults to 1) — The size of the patches to use in the patch embedding layer.
norm_elementwise_affine (bool, defaults to False) — Whether to use elementwise affinity in the normalization layer.
norm_eps (float, defaults to 1e-6) — The epsilon value for the normalization layer.
qk_norm (str, optional, defaults to None) — The normalization to use for the query and key.

A 3D Transformer model introduced in Sana-Video family of models.

Transformer2DModelOutput

class diffusers.models.modeling_outputs.Transformer2DModelOutput

< source >

( sample: torch.Tensor )

Parameters

sample (torch.Tensor of shape (batch_size, num_channels, height, width) or (batch size, num_vector_embeds - 1, num_latent_pixels) if Transformer2DModel is discrete) — The hidden states output conditioned on the encoder_hidden_states input. If discrete, returns probability distributions for the unnoised latent pixels.

The output of Transformer2DModel.

Update on GitHub

←SanaTransformer2DModel SD3Transformer2DModel→