Instructions to use InstantX/InstantIR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use InstantX/InstantIR 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("InstantX/InstantIR", 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
|
@@ -79,8 +79,8 @@ pretrained_state_dict = torch.load(instantir_path)
|
|
| 79 |
pipe.aggregator.load_state_dict(pretrained_state_dict)
|
| 80 |
|
| 81 |
# send to GPU and fp16
|
| 82 |
-
pipe.to(dtype=torch.float16)
|
| 83 |
-
pipe.to('cuda')
|
| 84 |
```
|
| 85 |
|
| 86 |
Then, you can restore your broken images with:
|
|
|
|
| 79 |
pipe.aggregator.load_state_dict(pretrained_state_dict)
|
| 80 |
|
| 81 |
# send to GPU and fp16
|
| 82 |
+
pipe.to(device='cuda', dtype=torch.float16)
|
| 83 |
+
pipe.aggregator.to(device='cuda', dtype=torch.float16)
|
| 84 |
```
|
| 85 |
|
| 86 |
Then, you can restore your broken images with:
|