Instructions to use Efficient-Large-Model/Sana_1600M_512px with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Sana
How to use Efficient-Large-Model/Sana_1600M_512px with Sana:
# 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/Sana_1600M_512px") 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, ) - Notebooks
- Google Colab
- Kaggle
Model license
#2
by ysharma - opened
Hi @Lawrence-cj Congratulations on the release of Sana!
I'm actually seeking clarification on something that has been confusing me regarding the Sana model weights. I've noticed that the license listed on Sana's GitHub repository is Apache 2.0, whereas the model page on the Hugging Face Hub indicates that the license is NSCL v2-custom. Could you help clarify this for me?