Text-to-Image
Sana
Diffusers
Safetensors
English
Chinese
Sana
1024px_based_image_size
Multi-language
Instructions to use Efficient-Large-Model/Sana_1600M_1024px_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_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_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
update scheduler_config.json with FlowDPMSolverMultistepScheduler
#2
by bghira - opened
scheduler/scheduler_config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_class_name": "
|
| 3 |
"_diffusers_version": "0.32.0.dev0",
|
| 4 |
"algorithm_type": "dpmsolver++",
|
| 5 |
"beta_end": 0.02,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_class_name": "FlowDPMSolverMultistepScheduler",
|
| 3 |
"_diffusers_version": "0.32.0.dev0",
|
| 4 |
"algorithm_type": "dpmsolver++",
|
| 5 |
"beta_end": 0.02,
|