|
--- |
|
license: mit |
|
datasets: |
|
- tomg-group-umd/ContraStyles |
|
library_name: transformers |
|
--- |
|
An unofficial implementation of [CSD](https://github.com/learn2phoenix/CSD) |
|
|
|
Inspired by [vvmatorin/CSD](https://huggingface.co./vvmatorin/CSD), the difference in this implementation is that the CLIP backbone is not the openai clip class but an instance of `CLIPVisionModel`. |
|
|
|
Inference: |
|
|
|
```python |
|
import torch |
|
import requests |
|
from PIL import Image |
|
from transformers import AutoModel, AutoConfig, AutoProcessor |
|
|
|
image_url = "https://midjourneysref.com/cdn-cgi/image/format=webp,quality=80,fit=cover/https://explore.midjourneysref.com/1541138391-4-219d8b0b" |
|
def load_image(url): |
|
im = Image.open(requests.get(url, stream=True).raw) |
|
return im |
|
|
|
processor = AutoProcessor.from_pretrained('NagaSaiAbhinay/CSD') |
|
model = AutoModel.from_pretrained('NagaSaiAbhinay/CSD', trust_remote_code=True).to("cuda") |
|
|
|
im = load_image(image_url) |
|
processed_image = processor(images=im, return_tensors='pt').to('cuda') |
|
processed_image = processed_image['pixel_values'] |
|
_, style_vector, _ = model(processed_image) |
|
``` |
