Instructions to use xishushu/SyncHuman with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use xishushu/SyncHuman with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("xishushu/SyncHuman", torch_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
|
@@ -2,8 +2,13 @@
|
|
| 2 |
license: mit
|
| 3 |
base_model:
|
| 4 |
- microsoft/TRELLIS-image-large
|
|
|
|
| 5 |
---
|
| 6 |
|
| 7 |
Model card of SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction.
|
| 8 |
|
| 9 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
license: mit
|
| 3 |
base_model:
|
| 4 |
- microsoft/TRELLIS-image-large
|
| 5 |
+
pipeline_tag: image-to-3d
|
| 6 |
---
|
| 7 |
|
| 8 |
Model card of SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction.
|
| 9 |
|
| 10 |
+
We introduce SyncHuman, a full-body human reconstruction model using synchronized 2D and 3D generative model. Given a single image of a clothed person, our method generates detailed geometry and lifelike 3D human appearances across diverse poses.
|
| 11 |
+
|
| 12 |
+
[[Project Page]](https://xishuxishu.github.io/SyncHuman.github.io/)
|
| 13 |
+
|
| 14 |
+
[[Code]](https://github.com/IGL-HKUST/SyncHuman/)
|