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.

Note

• Weakness in Complex Scene Creation: Due to limitation of data, our model has limited capabilities in generating complex scenes, text, and human hands.
• Enhancing Capabilities: The model’s performance can be improved by increasing the complexity and length of prompts. Below are some examples of prompts and samples.

4K samples

Images
prompt	A hot air balloon in the shape of a heart. Grand Canyon	a melting apple	A middle-aged woman of Asian descent, her dark hair streaked with silver , appears fractured and splintered, intricately embedded within a sea of broken porcelain. The porcelain glistens with splatter paint patterns in a harmonious blend of glossy and matte blues, greens, oranges, and reds, capturing her dance in a surreal juxtaposition of movement and stillness. Her skin tone, a light hue like the porcelain, adds an almost mystical quality to her form.	Modern luxury contemporary luxury home interiors house , in the style of mimicking ruined materials, ray tracing, haunting houses, and stone, capture the essence of nature, gray and bronze, dynamic outdoor shots.

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 4Kpx based images with multi-scale heigh and width.
• License: Apache License 2.0. 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_1600M_1024px_BF16 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.

• Repository: https://github.com/NVlabs/Sana

🧨 Diffusers

1. How to use SanaPipeline with 🧨diffusers

[!IMPORTANT] Make sure to specify pipe.transformer to default torch_dtype and variant according to Model Card.

Set pipe.text_encoder to BF16 and pipe.vae to FP32 or BF16. For more info, docs are here.

# run `pip install git+https://github.com/huggingface/diffusers` before use Sana in diffusers
import torch
from diffusers import SanaPipeline

pipe = SanaPipeline.from_pretrained(
    "Efficient-Large-Model/Sana_1600M_4Kpx_BF16_diffusers",
    variant="bf16",
    torch_dtype=torch.bfloat16,
)
pipe.to("cuda")

pipe.vae.to(torch.bfloat16)
pipe.text_encoder.to(torch.bfloat16)

# for 4096x4096 image generation OOM issue
if pipe.transformer.config.sample_size == 128:
    from patch_conv import convert_model
    pipe.vae = convert_model(pipe.vae, splits=32)

prompt = 'A cute 🐼 eating 🎋, ink drawing style'
image = pipe(
    prompt=prompt,
    height=4096,
    width=4096,
    guidance_scale=5.0,
    num_inference_steps=20,
    generator=torch.Generator(device="cuda").manual_seed(42),
)[0]

image[0].save("sana.png")

2. How to use SanaPAGPipeline with 🧨diffusers

# run `pip install git+https://github.com/huggingface/diffusers` before use Sana in diffusers
import torch
from diffusers import SanaPAGPipeline

pipe = SanaPAGPipeline.from_pretrained(
  "Efficient-Large-Model/Sana_1600M_4Kpx_BF16_diffusers",
  variant="bf16",
  torch_dtype=torch.bfloat16,
  pag_applied_layers="transformer_blocks.8",
)
pipe.to("cuda")

pipe.text_encoder.to(torch.bfloat16)
pipe.vae.to(torch.bfloat16)

# for 4096x4096 image generation OOM issue
if pipe.transformer.config.sample_size == 128:
    from patch_conv import convert_model
    pipe.vae = convert_model(pipe.vae, splits=32)

prompt = 'A cute 🐼 eating 🎋, ink drawing style'
image = pipe(
    prompt=prompt,
    height=4096,
    width=4096,
    guidance_scale=5.0,
    pag_scale=2.0,
    num_inference_steps=20,
    generator=torch.Generator(device="cuda").manual_seed(42),
)[0]
image[0].save('sana.png')

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.