metadata

library_name: sana
tags:
  - text-to-image
  - Sana
  - 1024px_based_image_size
  - Multi-language
  - ControlNet
language:
  - en
  - zh
base_model:
  - Efficient-Large-Model/Sana_600M_1024px_ControlNet_HED
pipeline_tag: text-to-image

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.

How to Use

refer to Sana-ControlNet Guidance for more details.

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_600M_img1024_controlnet.yaml")
pipe.from_pretrained("hf://Efficient-Large-Model/Sana_600M_1024px_ControlNet_HED/checkpoints/Sana_600M_1024px_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: 900M parameters
Model resolution: This model is developed to generate 1024px based images with multi-scale heigh and width.
License: 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.
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_600M_1024px and it supports HED ControlNet.
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: 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.