Improve model card with pipeline tag, library name, and project page link
Browse filesThis PR improves the model card by:
- Adding the `pipeline_tag: text-to-3d` to improve searchability on the Hugging Face Hub.
- Specifying the `library_name: diffusers`.
- Ensuring a clear link to the project page is present.
README.md
CHANGED
|
@@ -1,8 +1,9 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
| 3 |
---
|
| 4 |
|
| 5 |
-
|
| 6 |
<h1 align="center"> Step1X-3D: Towards High-Fidelity and Controllable<br>Generation of Textured 3D Assets</h1>
|
| 7 |
|
| 8 |
<p align="center">
|
|
@@ -21,9 +22,9 @@ license: apache-2.0
|
|
| 21 |
## π₯π₯π₯ Latest News!!
|
| 22 |
* May 13, 2025: π Step1X-3D online demo is available on huggingface-enjoy yourself with generated 3D assets! [Huggingface web live](https://huggingface.co/spaces/stepfun-ai/Step1X-3D)
|
| 23 |
* May 13, 2025: π We release the 800K uids of high quality 3D assets (excluding self-collected assets) obtained with our rigorous data curation pipeline for both training 3D geometry and synthesis. [Huggingface dataset](https://huggingface.co/datasets/stepfun-ai/Step1X-3D-obj-data/tree/main)
|
| 24 |
-
* May 13, 2025: π We have also
|
| 25 |
* May 13, 2025: π We have released the inference code and model weights of Step1X-3D geometry and Step1X-3D texture.
|
| 26 |
-
* May 13, 2025: π We have released Step1X-3D [technical report]() as open source.
|
| 27 |
|
| 28 |
## Introduction
|
| 29 |
While generative artificial intelligence has advanced significantly across text, image, audio, and video domains, 3D generation remains comparatively underdeveloped due to fundamental challenges such as data scarcity, algorithmic limitations, and ecosystem fragmentation.
|
|
@@ -82,6 +83,8 @@ textured_mesh = texture_pipeline(input_image_path, untexture_mesh)
|
|
| 82 |
textured_mesh.export("textured_mesh.glb")
|
| 83 |
```
|
| 84 |
|
|
|
|
|
|
|
| 85 |
## Citation
|
| 86 |
If you find our work helpful, please cite us
|
| 87 |
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
library_name: diffusers
|
| 4 |
+
pipeline_tag: text-to-3d
|
| 5 |
---
|
| 6 |
|
|
|
|
| 7 |
<h1 align="center"> Step1X-3D: Towards High-Fidelity and Controllable<br>Generation of Textured 3D Assets</h1>
|
| 8 |
|
| 9 |
<p align="center">
|
|
|
|
| 22 |
## π₯π₯π₯ Latest News!!
|
| 23 |
* May 13, 2025: π Step1X-3D online demo is available on huggingface-enjoy yourself with generated 3D assets! [Huggingface web live](https://huggingface.co/spaces/stepfun-ai/Step1X-3D)
|
| 24 |
* May 13, 2025: π We release the 800K uids of high quality 3D assets (excluding self-collected assets) obtained with our rigorous data curation pipeline for both training 3D geometry and synthesis. [Huggingface dataset](https://huggingface.co/datasets/stepfun-ai/Step1X-3D-obj-data/tree/main)
|
| 25 |
+
* May 13, 2025: π We have also released the training code of both Step1X-3D geometry generation and texture synthesis.
|
| 26 |
* May 13, 2025: π We have released the inference code and model weights of Step1X-3D geometry and Step1X-3D texture.
|
| 27 |
+
* May 13, 2025: π We have released Step1X-3D [technical report](https://arxiv.org/abs/2505.07747) as open source.
|
| 28 |
|
| 29 |
## Introduction
|
| 30 |
While generative artificial intelligence has advanced significantly across text, image, audio, and video domains, 3D generation remains comparatively underdeveloped due to fundamental challenges such as data scarcity, algorithmic limitations, and ecosystem fragmentation.
|
|
|
|
| 83 |
textured_mesh.export("textured_mesh.glb")
|
| 84 |
```
|
| 85 |
|
| 86 |
+
## Project Page: https://stepfun-ai.github.io/Step1X-3D/
|
| 87 |
+
|
| 88 |
## Citation
|
| 89 |
If you find our work helpful, please cite us
|
| 90 |
|