Instructions to use hustvl/Moebius with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use hustvl/Moebius with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("hustvl/Moebius", 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 files
README.md
CHANGED
|
@@ -1,5 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
| 1 |
《Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance》
|
| 2 |
Project Page: https://hustvl.github.io/Moebius
|
| 3 |
Paper: https://arxiv.org/abs/2606.19195
|
| 4 |
Code: https://github.com/hustvl/Moebius
|
| 5 |
-
weight: https://huggingface.co/hustvl/Moebius/tree/main
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
---
|
| 4 |
《Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance》
|
| 5 |
Project Page: https://hustvl.github.io/Moebius
|
| 6 |
Paper: https://arxiv.org/abs/2606.19195
|
| 7 |
Code: https://github.com/hustvl/Moebius
|
| 8 |
+
weight: https://huggingface.co/hustvl/Moebius/tree/main
|