Update README.md
Browse files
README.md
CHANGED
|
@@ -69,6 +69,18 @@ pip install -r requirements.txt
|
|
| 69 |
- Ubuntu 20.04
|
| 70 |
- NVIDIA A6000 GPU
|
| 71 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 72 |
### Checkpoint Structure
|
| 73 |
|
| 74 |
After downloading, your checkpoint directory should look like:
|
|
@@ -90,18 +102,6 @@ checkpoints/
|
|
| 90 |
|
| 91 |
```
|
| 92 |
|
| 93 |
-
### Required Pretrained Models
|
| 94 |
-
|
| 95 |
-
This model requires additional pretrained components:
|
| 96 |
-
|
| 97 |
-
1. **Image Encoder** from [lambdalabs/sd-image-variations-diffusers](https://huggingface.co/lambdalabs/sd-image-variations-diffusers)
|
| 98 |
-
2. **VGGT Integration** from [VGGT](https://github.com/facebookresearch/vggt):
|
| 99 |
-
|
| 100 |
-
```bash
|
| 101 |
-
git clone https://github.com/facebookresearch/vggt.git
|
| 102 |
-
pip install -r requirements_dev.txt
|
| 103 |
-
```
|
| 104 |
-
|
| 105 |
## Usage
|
| 106 |
|
| 107 |
### Basic Inference
|
|
|
|
| 69 |
- Ubuntu 20.04
|
| 70 |
- NVIDIA A6000 GPU
|
| 71 |
|
| 72 |
+
### Required Pretrained Models
|
| 73 |
+
|
| 74 |
+
This model requires additional pretrained components:
|
| 75 |
+
|
| 76 |
+
1. **Image Encoder** from [lambdalabs/sd-image-variations-diffusers](https://huggingface.co/lambdalabs/sd-image-variations-diffusers):
|
| 77 |
+
2. **VGGT Integration** from [VGGT](https://github.com/facebookresearch/vggt):
|
| 78 |
+
|
| 79 |
+
```bash
|
| 80 |
+
git clone https://github.com/facebookresearch/vggt.git
|
| 81 |
+
pip install -r requirements_dev.txt
|
| 82 |
+
```
|
| 83 |
+
|
| 84 |
### Checkpoint Structure
|
| 85 |
|
| 86 |
After downloading, your checkpoint directory should look like:
|
|
|
|
| 102 |
|
| 103 |
```
|
| 104 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 105 |
## Usage
|
| 106 |
|
| 107 |
### Basic Inference
|