SANA-1.5
Collection
SANA-1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer β’ 6 items β’ Updated β’ 11
β
β
β
β
β
β
π± Sana Model Card
Model
We introduce SANA-1.5οΌan efficient model with scaling of training-time and inference time techniques. SANA-1.5 delivers: efficient model growth from 1.6B Sana-1.0 model to 4.8B, achieving similar or better performance than training from scratch and saving 60% training cost; efficient model depth pruning, slimming any model size as you want; powerful VLM selection based inference scaling, smaller model+inference scaling > larger model; Top-notch GenEval & DPGBench results. Detailed results are shown in the below table.
Source code is available at https://github.com/NVlabs/Sana.
Model Description
- Developed by: NVIDIA, Sana
- Model type: Scalable Linear-Diffusion-Transformer-based text-to-image generative model
- Model size: 1.6B parameters
- Model precision: torch.bfloat16 (BF16)
- Model resolution: This model is developed to generate 1024px 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).
- Resources for more information: Check out our GitHub Repository and the SANA-1.5 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/
𧨠Diffusers
Developing
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.
- Downloads last month
- 894
Model tree for Efficient-Large-Model/SANA1.5_1.6B_1024px
Unable to build the model tree, the base model loops to the model itself. Learn more.
# Load the model and infer image from text import torch from app.sana_pipeline import SanaPipeline from torchvision.utils import save_image sana = SanaPipeline("configs/sana_config/1024ms/Sana_1600M_img1024.yaml") sana.from_pretrained("hf://Efficient-Large-Model/SANA1.5_1.6B_1024px") image = sana( prompt='a cyberpunk cat with a neon sign that says "Sana"', height=1024, width=1024, guidance_scale=5.0, pag_guidance_scale=2.0, num_inference_steps=18, )