Instructions to use h94/IP-Adapter-FaceID with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use h94/IP-Adapter-FaceID with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("h94/IP-Adapter-FaceID", 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
- Local Apps
- Draw Things
- DiffusionBee
Update README.md
Browse files"Deep in the forest, in dazzling greenery, a wild tiger approaches the camera lens. While the grass bends slightly with each step, the tiger's strong muscles and wild eyes are clearly visible when viewed through the camera lens. The mysterious atmosphere of the forest adds a natural wildness to every movement of the tiger."
README.md
CHANGED
|
@@ -316,7 +316,7 @@ images = ip_model.generate(
|
|
| 316 |
## Limitations and Bias
|
| 317 |
- The model does not achieve perfect photorealism and ID consistency.
|
| 318 |
- The generalization of the model is limited due to limitations of the training data, base model and face recognition model.
|
| 319 |
-
|
| 320 |
|
| 321 |
|
| 322 |
## Non-commercial use
|
|
|
|
| 316 |
## Limitations and Bias
|
| 317 |
- The model does not achieve perfect photorealism and ID consistency.
|
| 318 |
- The generalization of the model is limited due to limitations of the training data, base model and face recognition model.
|
| 319 |
+
-
|
| 320 |
|
| 321 |
|
| 322 |
## Non-commercial use
|