Instructions to use lilelife/SyntheOcc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use lilelife/SyntheOcc with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("lilelife/SyntheOcc", dtype=torch.bfloat16, device_map="cuda") prompt = "Turn this cat into a dog" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Add link to paper, pipeline tag
#1
by nielsr HF Staff - opened
README.md
CHANGED
|
@@ -1,10 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# SyntheOcc
|
| 2 |
|
| 3 |
> SyntheOcc: Synthesize Geometric-Controlled Street View Images through 3D Semantic MPIs <br>
|
| 4 |
> [Leheng Li](https://len-li.github.io), Weichao Qiu, Yingjie Cai, Xu Yan, Qing Lian, Bingbing Liu, Ying-Cong Chen
|
| 5 |
|
| 6 |
SyntheOcc is a project focused on synthesizing image data under geometry control (occupancy voxel). This repository provides tools and scripts to process, train, and generate synthetic image data in the nuScenes dataset, using occupancy control.
|
| 7 |
-
#### [Project Page](https://len-li.github.io/syntheocc-web) | [Paper](https://
|
| 8 |
|
| 9 |
Code: https://github.com/EnVision-Research/SyntheOcc
|
| 10 |
|
|
|
|
| 1 |
+
---
|
| 2 |
+
pipeline_tag: image-to-image
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
# SyntheOcc
|
| 6 |
|
| 7 |
> SyntheOcc: Synthesize Geometric-Controlled Street View Images through 3D Semantic MPIs <br>
|
| 8 |
> [Leheng Li](https://len-li.github.io), Weichao Qiu, Yingjie Cai, Xu Yan, Qing Lian, Bingbing Liu, Ying-Cong Chen
|
| 9 |
|
| 10 |
SyntheOcc is a project focused on synthesizing image data under geometry control (occupancy voxel). This repository provides tools and scripts to process, train, and generate synthetic image data in the nuScenes dataset, using occupancy control.
|
| 11 |
+
#### [Project Page](https://len-li.github.io/syntheocc-web) | [Paper](https://huggingface.co/papers/2410.00337) | [Video](https://len-li.github.io/syntheocc-web/videos/teaser-occedit.mp4) | [Checkpoint](https://huggingface.co/lilelife/SyntheOcc)
|
| 12 |
|
| 13 |
Code: https://github.com/EnVision-Research/SyntheOcc
|
| 14 |
|