Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -22,19 +22,20 @@ WaLa-MVDream-DM6 is a fine-tuned version of the MVDream model, adapted to genera
|
|
| 22 |
- **Model type:** Text-to-Depth Map Generative Model
|
| 23 |
- **License:** Autodesk Non-Commercial (3D Generative) v1.0
|
| 24 |
|
| 25 |
-
For more information please look at the [Project
|
| 26 |
|
| 27 |
### Model Sources
|
| 28 |
|
|
|
|
| 29 |
- **Repository:** [Github](https://github.com/AutodeskAILab/WaLa)
|
| 30 |
- **Paper:** [ArXiv:TBD](TBD)
|
| 31 |
-
- **Demo:** [
|
| 32 |
|
| 33 |
## Uses
|
| 34 |
|
| 35 |
### Direct Use
|
| 36 |
|
| 37 |
-
This model is released by Autodesk and intended for academic and research purposes only for the theoretical exploration and demonstration of the WaLa 3D generative framework. It is designed to be used in conjunction with WaLa-DM6-1B for text-to-3D generation. Please see [here](
|
| 38 |
|
| 39 |
### Out-of-Scope Use
|
| 40 |
|
|
@@ -58,7 +59,7 @@ The model should not be used for:
|
|
| 58 |
|
| 59 |
## How to Get Started with the Model
|
| 60 |
|
| 61 |
-
Please refer to the instructions [here](
|
| 62 |
|
| 63 |
## Training Details
|
| 64 |
|
|
@@ -76,19 +77,6 @@ Captions were generated for each 3D object in the dataset using four renderings
|
|
| 76 |
|
| 77 |
- **Training regime:** Please refer to the paper.
|
| 78 |
|
| 79 |
-
#### Speeds, Sizes, Times
|
| 80 |
-
|
| 81 |
-
[Information not provided in the paper]
|
| 82 |
-
|
| 83 |
-
## Evaluation
|
| 84 |
-
|
| 85 |
-
### Testing Data, Factors & Metrics
|
| 86 |
-
|
| 87 |
-
[Specific evaluation details for this model are not provided in the paper]
|
| 88 |
-
|
| 89 |
-
### Results
|
| 90 |
-
|
| 91 |
-
[Specific results for this model are not provided in the paper]
|
| 92 |
|
| 93 |
## Technical Specifications
|
| 94 |
|
|
@@ -100,7 +88,7 @@ The model is based on the MVDream architecture, fine-tuned to generate six-view
|
|
| 100 |
|
| 101 |
#### Hardware
|
| 102 |
|
| 103 |
-
|
| 104 |
|
| 105 |
## Citation
|
| 106 |
|
|
|
|
| 22 |
- **Model type:** Text-to-Depth Map Generative Model
|
| 23 |
- **License:** Autodesk Non-Commercial (3D Generative) v1.0
|
| 24 |
|
| 25 |
+
For more information please look at the [Project Page](https://autodeskailab.github.io/WaLaProject) and [the paper](TBD).
|
| 26 |
|
| 27 |
### Model Sources
|
| 28 |
|
| 29 |
+
- **Project Page:** [WaLa](https://autodeskailab.github.io/WaLaProject)
|
| 30 |
- **Repository:** [Github](https://github.com/AutodeskAILab/WaLa)
|
| 31 |
- **Paper:** [ArXiv:TBD](TBD)
|
| 32 |
+
- **Demo:** [Colab](https://colab.research.google.com/drive/1W5zPXw9xWNpLTlU5rnq7g3jtIA2BX6aC?usp=sharing)
|
| 33 |
|
| 34 |
## Uses
|
| 35 |
|
| 36 |
### Direct Use
|
| 37 |
|
| 38 |
+
This model is released by Autodesk and intended for academic and research purposes only for the theoretical exploration and demonstration of the WaLa 3D generative framework. It is designed to be used in conjunction with WaLa-DM6-1B for text-to-3D generation. Please see [here](https://github.com/AutodeskAILab/WaLa?tab=readme-ov-file#getting-started) for inferencing instructions.
|
| 39 |
|
| 40 |
### Out-of-Scope Use
|
| 41 |
|
|
|
|
| 59 |
|
| 60 |
## How to Get Started with the Model
|
| 61 |
|
| 62 |
+
Please refer to the instructions [here](https://github.com/AutodeskAILab/WaLa?tab=readme-ov-file#getting-started)
|
| 63 |
|
| 64 |
## Training Details
|
| 65 |
|
|
|
|
| 77 |
|
| 78 |
- **Training regime:** Please refer to the paper.
|
| 79 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 80 |
|
| 81 |
## Technical Specifications
|
| 82 |
|
|
|
|
| 88 |
|
| 89 |
#### Hardware
|
| 90 |
|
| 91 |
+
The model was trained on NVIDIA H100 GPUs.
|
| 92 |
|
| 93 |
## Citation
|
| 94 |
|