We introduce
SANA-1.5
,an 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.
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
).
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.
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 SANA1.5_1.6B_1024px on huggingface.co
152
Total runs
-2
24-hour runs
0
3-day runs
-3
7-day runs
-863
30-day runs
More Information About SANA1.5_1.6B_1024px huggingface.co Model
SANA1.5_1.6B_1024px huggingface.co is an AI model on huggingface.co that provides SANA1.5_1.6B_1024px's model effect (), which can be used instantly with this Efficient-Large-Model SANA1.5_1.6B_1024px model. huggingface.co supports a free trial of the SANA1.5_1.6B_1024px model, and also provides paid use of the SANA1.5_1.6B_1024px. Support call SANA1.5_1.6B_1024px model through api, including Node.js, Python, http.
SANA1.5_1.6B_1024px huggingface.co is an online trial and call api platform, which integrates SANA1.5_1.6B_1024px's modeling effects, including api services, and provides a free online trial of SANA1.5_1.6B_1024px, you can try SANA1.5_1.6B_1024px online for free by clicking the link below.
Efficient-Large-Model SANA1.5_1.6B_1024px online free url in huggingface.co:
SANA1.5_1.6B_1024px is an open source model from GitHub that offers a free installation service, and any user can find SANA1.5_1.6B_1024px on GitHub to install. At the same time, huggingface.co provides the effect of SANA1.5_1.6B_1024px install, users can directly use SANA1.5_1.6B_1024px installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
SANA1.5_1.6B_1024px install url in huggingface.co: