Instructions to use Overworld/Waypoint-1-Small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Overworld/Waypoint-1-Small with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Overworld/Waypoint-1-Small", 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
Update README.md
Browse filesRemove broken link
README.md
CHANGED
|
@@ -19,7 +19,7 @@ Can be prompted with any number of starting frames and controls
|
|
| 19 |
|
| 20 |
# Usage:
|
| 21 |
|
| 22 |
-
In order to simply use Waypoint-1-Small, we recommend [Biome](https://github.com/Overworldai/Biome) for local, the [Overworld streaming client](https://www.overworld.stream/)
|
| 23 |
|
| 24 |
To run the model locally, we recommend an NVIDIA RTX 5090, which should achieve 20-30 FPS, or an RTX 6000 Pro Blackwell, which should achieve ~35 FPS.
|
| 25 |
|
|
|
|
| 19 |
|
| 20 |
# Usage:
|
| 21 |
|
| 22 |
+
In order to simply use Waypoint-1-Small, we recommend [Biome](https://github.com/Overworldai/Biome) for local, or the [Overworld streaming client](https://www.overworld.stream/).
|
| 23 |
|
| 24 |
To run the model locally, we recommend an NVIDIA RTX 5090, which should achieve 20-30 FPS, or an RTX 6000 Pro Blackwell, which should achieve ~35 FPS.
|
| 25 |
|