Instructions to use Efficient-Large-Model/Sana_1600M_2Kpx_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_2Kpx_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_2Kpx_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
Upload files with `sana-upload`.
Browse files- transformer/config.json +1 -0
transformer/config.json
CHANGED
|
@@ -8,6 +8,7 @@
|
|
| 8 |
"cross_attention_head_dim": 112,
|
| 9 |
"dropout": 0.0,
|
| 10 |
"in_channels": 32,
|
|
|
|
| 11 |
"mlp_ratio": 2.5,
|
| 12 |
"norm_elementwise_affine": false,
|
| 13 |
"norm_eps": 1e-06,
|
|
|
|
| 8 |
"cross_attention_head_dim": 112,
|
| 9 |
"dropout": 0.0,
|
| 10 |
"in_channels": 32,
|
| 11 |
+
"interpolation_scale": 1.0,
|
| 12 |
"mlp_ratio": 2.5,
|
| 13 |
"norm_elementwise_affine": false,
|
| 14 |
"norm_eps": 1e-06,
|