Instructions to use ntc-ai/model-glue-sd15-sana-text with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Sana
How to use ntc-ai/model-glue-sd15-sana-text 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://ntc-ai/model-glue-sd15-sana-text") 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
| { | |
| "source_dim": 768, | |
| "target_dim": 2304, | |
| "tokens": 77, | |
| "width": 384, | |
| "blocks": 4, | |
| "particle_dim": 4, | |
| "num_particles": 256, | |
| "learnable_particles": false, | |
| "source_residual": true, | |
| "native_unconditional": true, | |
| "output_head": "linear", | |
| "head_width": 0, | |
| "use_particles": true, | |
| "output_source_residual": false, | |
| "output_source_init_scale": 0.01 | |
| } | |