README.md

---
library_name: sana
tags:
- text-to-image
- Sana
- 1024px_based_image_size
- Multi-language
- ControlNet
language:
- en
- zh
base_model:
- Efficient-Large-Model/Sana_1600M_1024px_BF16_ControlNet_HED
pipeline_tag: text-to-image
---

<p align="center" style="border-radius: 10px">
  <img src="https://raw.githubusercontent.com/NVlabs/Sana/refs/heads/main/asset/logo.png" width="35%" alt="logo"/>
</p>

<div style="display:flex;justify-content: center">
  <a href="https://huggingface.co/collections/Efficient-Large-Model/sana-673efba2a57ed99843f11f9e"><img src="https://img.shields.io/static/v1?label=Demo&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/"><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/abs/2410.10629"><img src="https://img.shields.io/static/v1?label=Arxiv&message=Sana&color=red&logo=arxiv"></a> &ensp;
  <a href="https://nv-sana.mit.edu/"><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>

# Model card

We incorporate a ControlNet-like(https://github.com/lllyasviel/ControlNet) module enables fine-grained control over text-to-image diffusion models. 
We implement a ControlNet-Transformer architecture, specifically tailored for Transformers, achieving explicit controllability alongside high-quality image generation.


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



<img src="https://nvlabs.github.io/Sana/asset/content/controlnet/sana_controlnet.jpg" width=640>

## How to Use

refer to [Sana-ControlNet Guidance](https://raw.githubusercontent.com/NVlabs/Sana/refs/heads/main/asset/controlnet/controlnet_app.jpg) for more details.

```python
import torch
from PIL import Image
from app.sana_controlnet_pipeline import SanaControlNetPipeline

device = "cuda" if torch.cuda.is_available() else "cpu"

pipe = SanaControlNetPipeline("configs/sana_controlnet_config/Sana_1600M_1024px_controlnet_bf16.yaml")
pipe.from_pretrained("hf://Efficient-Large-Model/Sana_1600M_1024px_BF16_ControlNet_HED/checkpoints/Sana_1600M_1024px_BF16_ControlNet_HED.pth")

ref_image = Image.open("asset/controlnet/ref_images/A transparent sculpture of a duck made out of glass. The sculpture is in front of a painting of a la.jpg")
prompt = "A transparent sculpture of a duck made out of glass. The sculpture is in front of a painting of a landscape."

images = pipe(
    prompt=prompt,
    ref_image=ref_image,
    guidance_scale=4.5,
    num_inference_steps=10,
    sketch_thickness=2,
    generator=torch.Generator(device=device).manual_seed(0),
)
```

### Model Description

- **Developed by:** NVIDIA, Sana
- **Model type:** Linear-Diffusion-Transformer-based text-to-image generative model, ControlNet
- **Model size:** 2B parameters
- **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)).
- **Special:** This model is fine-tuned from the base model [Efficient-Large-Model/Sana_1600M_1024px_BF16](https://huggingface.co/Efficient-Large-Model/Sana_1600M_1024px_BF16) and it supports HED ControlNet.
- **Resources for more information:** Check out our [GitHub Repository](https://github.com/NVlabs/Sana) and the [Sana report on arXiv](https://arxiv.org/abs/2410.10629).

### 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](https://nv-sana.mit.edu/) provides free Sana inference.
- **Repository:** ttps://github.com/NVlabs/Sana
- **Demo:** https://nv-sana.mit.edu/


## 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.