Sana Sprint 1.6B 1024px

🚀 Sana, Sana-Sprint

Sana and Sana-Sprint are ultra - efficient text - to - image diffusion models, achieving state - of - the - art performance with significantly reduced inference steps.

🚀 Quick Start

This README provides a detailed introduction to the Sana and Sana - Sprint models, including their features, efficiency, model description, uses, limitations, and biases.

✨ Features

• Ultra - efficient Diffusion: Reduces inference steps from 20 to 1 - 4 while achieving state - of - the - art performance.
• Training - free Approach: Utilizes a training - free approach for continuous - time consistency distillation (sCM), eliminating costly retraining.
• Unified Step - adaptive Model: A unified step - adaptive model for high - quality generation in 1 - 4 steps.
• ControlNet Integration: Enables real - time interactive image generation through ControlNet integration.

📦 Installation

The source code is available at GitHub Repository. You can refer to the repository for installation and usage instructions.

💻 Usage Examples

No specific code examples are provided in the original README. If you want to use the model, you can refer to the source code on the GitHub Repository and the SANA - Sprint report on arXiv.

📚 Documentation

Model Description

Model Sources

• Repository: https://github.com/NVlabs/Sana
• Demo: https://nv - sana.mit.edu/sprint
• Guidance: https://github.com/NVlabs/Sana/asset/docs/sana_sprint.md

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.

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.

Visuals

           

Model Efficiency

SANA - Sprint is an ultra - efficient diffusion model for text - to - image (T2I) generation, reducing inference steps from 20 to 1 - 4 while achieving state - of - the - art performance. Key innovations include: (1) A training - free approach for continuous - time consistency distillation (sCM), eliminating costly retraining; (2) A unified step - adaptive model for high - quality generation in 1 - 4 steps; and (3) ControlNet integration for real - time interactive image generation. SANA - Sprint achieves 7.59 FID and 0.74 GenEval in just 1 step — outperforming FLUX - schnell (7.94 FID / 0.71 GenEval) while being 10× faster (0.1s vs 1.1s on H100). With latencies of 0.1s (T2I) and 0.25s (ControlNet) for 1024×1024 images on H100, and 0.31s (T2I) on an RTX 4090, SANA - Sprint is ideal for AI - powered consumer applications (AIPC).

License

The model is licensed under NSCL v2 - custom. Governing Terms: NVIDIA License. Additional Information: Gemma Terms of Use | Google AI for Developers for Gemma - 2 - 2B - IT, Gemma Prohibited Use Policy | Google AI for Developers.