eleazhong/strotss 🖼️🔢 → 🖼️

▶️ 8.9K runs 📅 Dec 2021 ⚙️ Cog 0.4.4 🔗 GitHub

image-to-image strotss style-transfer

About

image to image style transfer using STROTSS loss

Example Output

Output

[object Object]

Performance Metrics

93.99s Prediction Time

97.28s Total Time

All Input Parameters

{
  "style": "https://replicate.delivery/mgxm/9d51a899-ceac-4b05-98fb-10c6c356fa7e/margarita-aivazian-dh8.jpg",
  "content": "https://replicate.delivery/mgxm/fb40f17f-0c54-4eb0-bab9-304f5c6f4439/aa.jpg",
  "content_weight": "1.0"
}

Input Parameters

style (required) Type: string: style image
content (required) Type: string: content image
content_weight Type: numberDefault: 1: how much the content is preserved (high->more close to original)

Output Schema

Output

Type: string • Format: uri

Example Execution Logs

Transferring Style :)
starting running the strotss algorithm
Optimizing at resoluton [64, 60]
/root/.pyenv/versions/3.7.12/lib/python3.7/site-packages/torch/nn/functional.py:718: UserWarning: Named tensors and all their associated APIs are an experimental feature and subject to change. Please do not use them for anything important until they are released as stable. (Triggered internally at  /pytorch/c10/core/TensorImpl.h:1156.)
  return torch.max_pool2d(input, kernel_size, stride, padding, dilation, ceil_mode)
Optimizing at resoluton [128, 121]
Optimizing at resoluton [256, 242]
Optimizing at resoluton [512, 485]
Done in 93.776s

Version Details

Version ID: 0823798ef38918f7688f226ed756c2ebf3e96438f51f6be65c997191f29a4b58
Version Created: October 7, 2022

Run on Replicate →