Instructions to use Efficient-Large-Model/SANA1.5_1.6B_1024px with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Sana
How to use Efficient-Large-Model/SANA1.5_1.6B_1024px 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/SANA1.5_1.6B_1024px") 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, ) - Inference
- Notebooks
- Google Colab
- Kaggle
Upload files with `sana-upload`.
Browse filesUpload config.json
Upload checkpoints/Sana1-5_1600M_1024px.pth
- checkpoints/Sana1-5_1600M_1024px.pth +3 -0
- config.json +3 -0
checkpoints/Sana1-5_1600M_1024px.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e09953e952956c14570820e39abef8ac7483b88ff3abb406a8612f1dac3a2b4
|
| 3 |
+
size 6430666040
|
config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"modle_name": "SANA-1.5-1600M-1024px-bf16"
|
| 3 |
+
}
|