Instructions to use sttkw/TAID-Models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use sttkw/TAID-Models with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("sttkw/TAID-Models", 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
Use renamed demo images in usage example
Browse files
README.md
CHANGED
|
@@ -34,8 +34,8 @@ The decomposition U-Net is loaded on top of the other components of
|
|
| 34 |
git clone https://github.com/sttkw/terrain-atmospheric-intrinsic-decomposition
|
| 35 |
cd terrain-atmospheric-intrinsic-decomposition
|
| 36 |
pip install -r requirements.txt
|
| 37 |
-
python demo.py --input_image demo_image/
|
| 38 |
-
--p_control 0 -3 0 --output_dir outputs/demo/
|
| 39 |
```
|
| 40 |
|
| 41 |
`demo.py` downloads these weights automatically.
|
|
|
|
| 34 |
git clone https://github.com/sttkw/terrain-atmospheric-intrinsic-decomposition
|
| 35 |
cd terrain-atmospheric-intrinsic-decomposition
|
| 36 |
pip install -r requirements.txt
|
| 37 |
+
python demo.py --input_image demo_image/test1.jpg --water_mask demo_image/test1.png \
|
| 38 |
+
--p_control 0 -3 0 --output_dir outputs/demo/test1
|
| 39 |
```
|
| 40 |
|
| 41 |
`demo.py` downloads these weights automatically.
|