Instructions to use google/ncsnpp-ffhq-1024 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use google/ncsnpp-ffhq-1024 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("google/ncsnpp-ffhq-1024", 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
Fix a typo
#3
by shirayu - opened
README.md
CHANGED
|
@@ -18,7 +18,7 @@ tags:
|
|
| 18 |
|
| 19 |
## Inference
|
| 20 |
|
| 21 |
-
*SDE* models can use **
|
| 22 |
|
| 23 |
- [scheduling_sde_ve](https://github.com/huggingface/diffusers/blob/main/src/diffusers/schedulers/scheduling_sde_ve.py)
|
| 24 |
|
|
|
|
| 18 |
|
| 19 |
## Inference
|
| 20 |
|
| 21 |
+
*SDE* models can use **continuous** noise schedulers such as:
|
| 22 |
|
| 23 |
- [scheduling_sde_ve](https://github.com/huggingface/diffusers/blob/main/src/diffusers/schedulers/scheduling_sde_ve.py)
|
| 24 |
|