File size: 1,084 Bytes
9b25486 6463f84 9b25486 6463f84 9b25486 6463f84 9b25486 6463f84 9b25486 6463f84 9b25486 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 |
---
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)
``` |