Efficient-Large-Model / Sana_1600M_512px_MultiLing

huggingface.co
Total runs: 41
24-hour runs: 0
7-day runs: 2
30-day runs: 31
Model's Last Updated: July 31 2026
text-to-image

Introduction of Sana_1600M_512px_MultiLing

Model Details of Sana_1600M_512px_MultiLing

logo

Model card

We introduce Sana , a text-to-image framework that can efficiently generate images up to 4096 × 4096 resolution. Sana can synthesize high-resolution, high-quality images with strong text-image alignment at a remarkably fast speed, deployable on laptop GPU.

Source code is available at https://github.com/NVlabs/Sana .

Compare with base model
Model Language
Sana_1600M_512px English
Sana_1600M_512px_MultiLing English, Chinese, Emoji
Model Sample-1 Sample-2 Sample-3 Sample-4
Sana_1600M_512px
Sana_1600M_512px_MultiLing
Prompt 🐯 穿着 👕 吹 🎷 猫 Wearing 🕶 flying on the 彩虹 with 🌹 in the ❄️ 🦁 teaching 🐯 to catch 🦋 金色 🌅 下的长城, traditional Chinese style
Model Description
  • 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 512px based images with multi-scale heigh and width.
  • License: CC BY-NC-SA 4.0 License
  • 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 ) and one 32x spatial-compressed latent feature encoder ( DC-AE ).
  • Special: This model is fine-tuned from the base model Efficient-Large-Model/Sana_1600M_512px and it supports Emoji, Chinese and English and all mixed prompts.
  • 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.

🧨 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.

Runs of Efficient-Large-Model Sana_1600M_512px_MultiLing on huggingface.co

41
Total runs
0
24-hour runs
0
3-day runs
2
7-day runs
31
30-day runs

More Information About Sana_1600M_512px_MultiLing huggingface.co Model

More Sana_1600M_512px_MultiLing license Visit here:

https://choosealicense.com/licenses/apache-2.0

Sana_1600M_512px_MultiLing huggingface.co

Sana_1600M_512px_MultiLing huggingface.co is an AI model on huggingface.co that provides Sana_1600M_512px_MultiLing's model effect (), which can be used instantly with this Efficient-Large-Model Sana_1600M_512px_MultiLing model. huggingface.co supports a free trial of the Sana_1600M_512px_MultiLing model, and also provides paid use of the Sana_1600M_512px_MultiLing. Support call Sana_1600M_512px_MultiLing model through api, including Node.js, Python, http.

Efficient-Large-Model Sana_1600M_512px_MultiLing online free

Sana_1600M_512px_MultiLing huggingface.co is an online trial and call api platform, which integrates Sana_1600M_512px_MultiLing's modeling effects, including api services, and provides a free online trial of Sana_1600M_512px_MultiLing, you can try Sana_1600M_512px_MultiLing online for free by clicking the link below.

Efficient-Large-Model Sana_1600M_512px_MultiLing online free url in huggingface.co:

https://huggingface.co/Efficient-Large-Model/Sana_1600M_512px_MultiLing

Sana_1600M_512px_MultiLing install

Sana_1600M_512px_MultiLing is an open source model from GitHub that offers a free installation service, and any user can find Sana_1600M_512px_MultiLing on GitHub to install. At the same time, huggingface.co provides the effect of Sana_1600M_512px_MultiLing install, users can directly use Sana_1600M_512px_MultiLing installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

Sana_1600M_512px_MultiLing install url in huggingface.co:

https://huggingface.co/Efficient-Large-Model/Sana_1600M_512px_MultiLing

Url of Sana_1600M_512px_MultiLing

Provider of Sana_1600M_512px_MultiLing huggingface.co

Efficient-Large-Model
ORGANIZATIONS

Other API from Efficient-Large-Model