Instructions to use dilightnet/DiLightNet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use dilightnet/DiLightNet 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("dilightnet/DiLightNet", 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
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,4 +1,31 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
library_name: diffusers
|
| 4 |
-
--
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
library_name: diffusers
|
| 4 |
+
pipeline_tag: image-to-image
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
+
# DiLightNet: Fine-grained Lighting Control for Diffusion-based Image Generation
|
| 8 |
+
|
| 9 |
+
SIGGRAPH 2024
|
| 10 |
+
|
| 11 |
+
- Project Page: https://dilightnet.github.io/
|
| 12 |
+
- Paper: https://arxiv.org/abs/2402.11929
|
| 13 |
+
- Full Usage: please check https://github.com/iamNCJ/DiLightNet
|
| 14 |
+
|
| 15 |
+
Example Usage:
|
| 16 |
+
|
| 17 |
+
```python
|
| 18 |
+
from diffusers.utils import get_class_from_dynamic_module
|
| 19 |
+
NeuralTextureControlNetModel = get_class_from_dynamic_module(
|
| 20 |
+
"dilightnet/model_helpers",
|
| 21 |
+
"neuraltexture_controlnet.py",
|
| 22 |
+
"NeuralTextureControlNetModel"
|
| 23 |
+
)
|
| 24 |
+
neuraltexture_controlnet = NeuralTextureControlNetModel.from_pretrained("DiLightNet/DiLightNet")
|
| 25 |
+
|
| 26 |
+
pipe = StableDiffusionControlNetPipeline.from_pretrained(
|
| 27 |
+
"stabilityai/stable-diffusion-2-1", controlnet=neuraltexture_controlnet,
|
| 28 |
+
)
|
| 29 |
+
cond_image = torch.randn((1, 16, 512, 512))
|
| 30 |
+
image = pipe("some text prompt", image=cond_image).images[0]
|
| 31 |
+
```
|