SANA-Video is a small, ultra-efficient diffusion model designed for rapid generation of high-quality, minute-long videos at resolutions up to 720×1280.
Key innovations and efficiency drivers include:
(1)
Linear DiT
: Leverages linear attention as the core operation, offering significantly more efficiency than vanilla attention when processing the massive number of tokens required for video generation.
(2)
Constant-Memory KV Cache for Block Linear Attention
: Implements a block-wise autoregressive approach that uses the cumulative properties of linear attention to maintain global context at a fixed memory cost, eliminating the traditional KV cache bottleneck and enabling efficient, minute-long video synthesis.
SANA-Video achieves exceptional efficiency and cost savings: its training cost is only
1%
of MovieGen's (
12 days on 64 H100 GPUs
). Compared to modern state-of-the-art small diffusion models (e.g., Wan 2.1 and SkyReel-V2), SANA-Video maintains competitive performance while being
16×
faster in measured latency.
SANA-Video is deployable on RTX 5090 GPUs, accelerating the inference speed for a 5-second 720p video from 71s down to 29s (2.4× speedup), setting a new standard for low-cost, high-quality video generation.
Model type:
Efficient Video Generation with Block Linear Diffusion Transformer
Model size:
2B parameters
Model precision:
torch.bfloat16 (BF16)
Model resolution:
This model is developed to generate 720p resolution 81(5s) frames videos with multi-scale heigh and width.
Model Description:
This is a model that can be used to generate and modify videos based on text prompts.
It is a Linear Diffusion Transformer that uses LTX2-vae one 32x32x8 spatial-temporal-compressed latent feature encoder (
LTX2
).
For research purposes, we recommend our
generative-models
Github repository (
https://github.com/NVlabs/Sana
), which is more suitable for both training and inference
The model is intended for research purposes only. Possible research areas and tasks include
Generation of artworks and use in design and other artistic processes.
Applications in educational or creative tools.
Research on generative models.
Safe deployment of models which have the potential to generate harmful content.
Probing and understanding the limitations and biases of generative models.
Excluded uses are described below.
Out-of-Scope Use
The model was not trained to be factual or true representations of people or events, and therefore using the model to generate such content is out-of-scope for the abilities of this model.
Limitations and Bias
Limitations
The model does not achieve perfect photorealism
The model cannot render complex legible text
fingers, .etc in general may not be generated properly.
The autoencoding part of the model is lossy.
Bias
While the capabilities of video generation models are impressive, they can also reinforce or exacerbate social biases.
Runs of Efficient-Large-Model SANA-Video_2B_720p on huggingface.co
23
Total runs
-1
24-hour runs
-1
3-day runs
-2
7-day runs
7
30-day runs
More Information About SANA-Video_2B_720p huggingface.co Model
SANA-Video_2B_720p huggingface.co is an AI model on huggingface.co that provides SANA-Video_2B_720p's model effect (), which can be used instantly with this Efficient-Large-Model SANA-Video_2B_720p model. huggingface.co supports a free trial of the SANA-Video_2B_720p model, and also provides paid use of the SANA-Video_2B_720p. Support call SANA-Video_2B_720p model through api, including Node.js, Python, http.
SANA-Video_2B_720p huggingface.co is an online trial and call api platform, which integrates SANA-Video_2B_720p's modeling effects, including api services, and provides a free online trial of SANA-Video_2B_720p, you can try SANA-Video_2B_720p online for free by clicking the link below.
Efficient-Large-Model SANA-Video_2B_720p online free url in huggingface.co:
SANA-Video_2B_720p is an open source model from GitHub that offers a free installation service, and any user can find SANA-Video_2B_720p on GitHub to install. At the same time, huggingface.co provides the effect of SANA-Video_2B_720p install, users can directly use SANA-Video_2B_720p installed effect in huggingface.co for debugging and trial. It also supports api for free installation.