This model serves as the
Teacher
in the figure below. It's not a few-step generative model but a fine-tuned diffusion model with
(1)
Dense Timestep Embedding
and (2)
QK Normalization
discussed in the
SANA-Sprint paper
.
Few-step generative models can be found in
HF repo
.
Source code is available at
https://github.com/NVlabs/Sana
.
Training Pipeline
Model Description
Developed by:
NVIDIA, Sana
Model type:
Teacher model for One-Step Diffusion with Continuous-Time Consistency Distillation
Model size:
0.6B parameters
Model precision:
torch.bfloat16 (BF16)
Model resolution:
This model is developed to generate 1024px based images with multi-scale heigh and width.
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
MIT Han-Lab
provides free SANA-Sprint 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 Sana_Sprint_0.6B_1024px_teacher on huggingface.co
25
Total runs
1
24-hour runs
0
3-day runs
-1
7-day runs
16
30-day runs
More Information About Sana_Sprint_0.6B_1024px_teacher huggingface.co Model
More Sana_Sprint_0.6B_1024px_teacher license Visit here:
Sana_Sprint_0.6B_1024px_teacher huggingface.co is an AI model on huggingface.co that provides Sana_Sprint_0.6B_1024px_teacher's model effect (), which can be used instantly with this Efficient-Large-Model Sana_Sprint_0.6B_1024px_teacher model. huggingface.co supports a free trial of the Sana_Sprint_0.6B_1024px_teacher model, and also provides paid use of the Sana_Sprint_0.6B_1024px_teacher. Support call Sana_Sprint_0.6B_1024px_teacher model through api, including Node.js, Python, http.
Sana_Sprint_0.6B_1024px_teacher huggingface.co is an online trial and call api platform, which integrates Sana_Sprint_0.6B_1024px_teacher's modeling effects, including api services, and provides a free online trial of Sana_Sprint_0.6B_1024px_teacher, you can try Sana_Sprint_0.6B_1024px_teacher online for free by clicking the link below.
Efficient-Large-Model Sana_Sprint_0.6B_1024px_teacher online free url in huggingface.co:
Sana_Sprint_0.6B_1024px_teacher is an open source model from GitHub that offers a free installation service, and any user can find Sana_Sprint_0.6B_1024px_teacher on GitHub to install. At the same time, huggingface.co provides the effect of Sana_Sprint_0.6B_1024px_teacher install, users can directly use Sana_Sprint_0.6B_1024px_teacher installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
Sana_Sprint_0.6B_1024px_teacher install url in huggingface.co: