Text-to-Image
Sana
Diffusers
Safetensors
English
Chinese
Sana
1024px_based_image_size
Multi-language
Instructions to use Efficient-Large-Model/Sana_1600M_1024px_BF16_diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Sana
How to use Efficient-Large-Model/Sana_1600M_1024px_BF16_diffusers 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_1024px_BF16_diffusers") 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
Download model_index.json from Efficient-Large-Model/Sana_1600M_1024px_BF16_diffusers: direct link, hf CLI and curl.
- Browser
- Download file 401 Bytes
-
https://huggingface.co/Efficient-Large-Model/Sana_1600M_1024px_BF16_diffusers/resolve/main/model_index.json
- Command line
-
hf download hf://Efficient-Large-Model/Sana_1600M_1024px_BF16_diffusers/model_index.json
-
curl -L -o model_index.json https://huggingface.co/Efficient-Large-Model/Sana_1600M_1024px_BF16_diffusers/resolve/main/model_index.json
401 Bytes
| { | |
| "_class_name": "SanaPipeline", | |
| "_diffusers_version": "0.32.0.dev0", | |
| "scheduler": [ | |
| "diffusers", | |
| "DPMSolverMultistepScheduler" | |
| ], | |
| "text_encoder": [ | |
| "transformers", | |
| "Gemma2Model" | |
| ], | |
| "tokenizer": [ | |
| "transformers", | |
| "GemmaTokenizerFast" | |
| ], | |
| "transformer": [ | |
| "diffusers", | |
| "SanaTransformer2DModel" | |
| ], | |
| "vae": [ | |
| "diffusers", | |
| "AutoencoderDC" | |
| ] | |
| } | |