Instructions to use kvablack/ddpo-alignment with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use kvablack/ddpo-alignment with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("kvablack/ddpo-alignment", dtype=torch.bfloat16, device_map="cuda") prompt = "a horse playing chess" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Add example inputs to the widget
#1
by mishig HF Staff - opened
README.md
CHANGED
|
@@ -13,6 +13,13 @@ inference:
|
|
| 13 |
num_inference_steps: 50
|
| 14 |
guidance_scale: 5.0
|
| 15 |
eta: 1.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
---
|
| 17 |
|
| 18 |
# ddpo-alignment
|
|
|
|
| 13 |
num_inference_steps: 50
|
| 14 |
guidance_scale: 5.0
|
| 15 |
eta: 1.0
|
| 16 |
+
widget:
|
| 17 |
+
- text: "a horse playing chess"
|
| 18 |
+
example_title: horse + chess
|
| 19 |
+
- text: "a lion washing dishes"
|
| 20 |
+
example_title: lion + dishes
|
| 21 |
+
- text: "a goat riding a bike"
|
| 22 |
+
example_title: goat + bike
|
| 23 |
---
|
| 24 |
|
| 25 |
# ddpo-alignment
|