---
library_name: sana, sana-sprint
tags:
- text-to-image
- SANA-Sprint
- 1024px_based_image_size
- BF16
- One-step diffusion
language:
- en
- zh
base_model:
- Efficient-Large-Model/Sana_Sprint_1.6B_1024px_teacher
pipeline_tag: text-to-image
---
<p align="center" style="border-radius: 10px">
  <img src="https://nvlabs.github.io/Sana/Sprint/asset/SANA-Sprint.png" width="50%" alt="logo"/>
</p>

<div style="display:flex;justify-content: center">
  <a href="https://huggingface.co/collections/Efficient-Large-Model/sana-sprint-67d6810d65235085b3b17c76"><img src="https://img.shields.io/static/v1?label=Weights&message=Huggingface&color=yellow"></a> &ensp;
  <a href="https://github.com/NVlabs/Sana"><img src="https://img.shields.io/static/v1?label=Code&message=Github&color=blue&logo=github"></a> &ensp;
  <a href="https://nvlabs.github.io/Sana/Sprint/"><img src="https://img.shields.io/static/v1?label=Project&message=Github&color=blue&logo=github-pages"></a> &ensp;
  <!-- <a href="https://hanlab.mit.edu/projects/sana/"><img src="https://img.shields.io/static/v1?label=Page&message=MIT&color=darkred&logo=github-pages"></a> &ensp; -->
  <a href="https://arxiv.org/pdf/2503.09641"><img src="https://img.shields.io/static/v1?label=Arxiv&message=SANA-Sprint&color=red&logo=arxiv"></a> &ensp;
  <a href="https://nv-sana.mit.edu/sprint"><img src="https://img.shields.io/static/v1?label=Demo&message=MIT&color=yellow"></a> &ensp;
  <a href="https://discord.gg/rde6eaE5Ta"><img src="https://img.shields.io/static/v1?label=Discuss&message=Discord&color=purple&logo=discord"></a> &ensp;
</div>

# 🐱 Sana Model Card

This model serves as the **Teacher** in the figure below. It's not a few-step generative model but a fine-tuned diffusion model with 
(1) **Dense Timestep Embedding** and (2) **QK Normalization** discussed in the [SANA-Sprint paper](https://arxiv.org/pdf/2503.09641). 
Few-step generative models can be found in [HF repo](https://huggingface.co/collections/Efficient-Large-Model/sana-sprint-67d6810d65235085b3b17c76).
Source code is available at https://github.com/NVlabs/Sana.

## Training Pipeline

<p align="center" border-raduis="10px">
  <img src="https://nvlabs.github.io/Sana/Sprint/asset/content/paradigm.png" width="85%" alt="teaser_page1"/>
</p>


### Model Description

- **Developed by:** NVIDIA, Sana
- **Model type:** Teacher model for One-Step Diffusion with Continuous-Time Consistency Distillation
- **Model size:** 1.6B parameters
- **Model precision:** torch.bfloat16 (BF16)
- **Model resolution:** This model is developed to generate 1024px based images with multi-scale heigh and width.
- **License:** [NSCL v2-custom](./LICENSE.txt). Governing Terms:  NVIDIA License.  Additional Information:  [Gemma Terms of Use  |  Google AI for Developers](https://ai.google.dev/gemma/terms) for Gemma-2-2B-IT, [Gemma Prohibited Use Policy  |  Google AI for Developers](https://ai.google.dev/gemma/prohibited_use_policy).
- **Model Description:** This is a model that can be used to generate and modify images based on text prompts. 
It is a Linear Diffusion Transformer that uses one fixed, pretrained text encoders ([Gemma2-2B-IT](https://huggingface.co/google/gemma-2-2b-it))
and one 32x spatial-compressed latent feature encoder ([DC-AE](https://hanlab.mit.edu/projects/dc-ae)).
- **Resources for more information:** Check out our [GitHub Repository](https://github.com/NVlabs/Sana) and the [SANA-Sprint report on arXiv](https://arxiv.org/pdf/2503.09641).

### Model Sources

For research purposes, we recommend our `generative-models` Github repository (https://github.com/NVlabs/Sana), which is more suitable for both training and inference
[MIT Han-Lab](https://nv-sana.mit.edu/sprint) provides free SANA-Sprint inference.
- **Repository:** https://github.com/NVlabs/Sana
- **Demo:** https://nv-sana.mit.edu/sprint


## Uses

### Direct Use

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 image generation models are impressive, they can also reinforce or exacerbate social biases.