Instructions to use eurecom-ds/mnist_conditional with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use eurecom-ds/mnist_conditional with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("eurecom-ds/mnist_conditional", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Create model_index.json
Browse files- model_index.json +14 -0
model_index.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": [
|
| 3 |
+
"conditional_pipeline",
|
| 4 |
+
"ScoreSdeVePipelineConditioned"
|
| 5 |
+
],
|
| 6 |
+
"scheduler": [
|
| 7 |
+
"sde_ve_scheduler",
|
| 8 |
+
"ScoreSdeVeScheduler"
|
| 9 |
+
],
|
| 10 |
+
"unet": [
|
| 11 |
+
"conditional_unet_model",
|
| 12 |
+
"UNet2DModel"
|
| 13 |
+
]
|
| 14 |
+
}
|