๐ Sana Model
Sana is a text - to - image framework. It can efficiently generate high - resolution (up to 4096 ร 4096) and high - quality images with strong text - image alignment at a fast speed, and can be deployed on laptop GPUs.
๐ Quick Start
The source code of Sana is available at https://github.com/NVlabs/Sana. For research purposes, we recommend using the generative - models
Github repository (https://github.com/NVlabs/Sana) for training and inference, which integrates advanced diffusion samplers like Flow - DPM - Solver. MIT Han - Lab provides free Sana inference.
โจ Features
- High - resolution Image Generation: Can generate images up to 4096 ร 4096 resolution.
- Fast Generation Speed: Capable of generating high - quality images with strong text - image alignment at a remarkably fast speed, and can be deployed on laptop GPUs.
๐ Documentation
Model
Model Description
Property |
Details |
Developed by |
NVIDIA, Sana |
Model Type |
Linear - Diffusion - Transformer - based text - to - image generative model |
Model Size |
1648M parameters |
Model Resolution |
This model is developed to generate 1024px based images with multi - scale height and width. |
License |
NSCL v2 - custom. Governing Terms: NVIDIA License. Additional Information: [Gemma Terms of Use |
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 and the Sana report on arXiv. |
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 and for which most advanced diffusion sampler like Flow - DPM - Solver is integrated. MIT Han - Lab provides free Sana inference.
- Repository: https://github.com/NVlabs/Sana
- Demo: https://nv-sana.mit.edu/
๐งจ Diffusers
PR developing: Sana and DC - AE
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.