Instructions to use BioMike/classical_portrait_vae with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BioMike/classical_portrait_vae with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="BioMike/classical_portrait_vae")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("BioMike/classical_portrait_vae", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -185,5 +185,4 @@ The model was trained on the [Portrait Dataset](https://www.kaggle.com/datasets/
|
|
| 185 |
The model was trained into two steps, in the first the model vgg16 was employed in the perceptual loss, to train our model to extract general features, and the model vggface2 was used to train VAE to decode faces accurately.
|
| 186 |
|
| 187 |
## Model Card Authors
|
| 188 |
-
[Mykhailo Shtopko](https://huggingface.co/BioMike)
|
| 189 |
-
[werent4](https://huggingface.co/werent4)
|
|
|
|
| 185 |
The model was trained into two steps, in the first the model vgg16 was employed in the perceptual loss, to train our model to extract general features, and the model vggface2 was used to train VAE to decode faces accurately.
|
| 186 |
|
| 187 |
## Model Card Authors
|
| 188 |
+
[Mykhailo Shtopko](https://huggingface.co/BioMike), [werent4](https://huggingface.co/werent4)
|
|
|