eladrich/pixel2style2pixel 🖼️❓ → 🖼️

▶️ 31.9K runs 📅 Sep 2021 ⚙️ Cog 0.4.1 🔗 GitHub 📄 Paper ⚖️ License

image-style-transfer image-to-image sketch-to-image

About

a StyleGAN Encoder for Image-to-Image Translation

Example Output

Output

[object Object]

Performance Metrics

9.87s Total Time

All Input Parameters

{
  "image": "https://replicate.delivery/mgxm/7935db96-ae91-440f-8c75-b94bd6315d79/input_img.jpg",
  "model": "toonify"
}

Input Parameters

image (required) Type: string: input image
model (required): choose model type

Output Schema

Output

Type: string • Format: uri

Example Execution Logs

Namespace(batch_size=8, board_interval=50, checkpoint_path='pretrained_models/psp_ffhq_toonify.pt', dataset_type='ffhq_encode', device='cuda:0', encoder_type='GradualStyleEncoder', exp_dir='', id_lambda=1.0, image_interval=100, input_nc=3, l2_lambda=1.0, l2_lambda_crop=0, label_nc=0, learn_in_w=False, learning_rate=0.0001, lpips_lambda=0.8, lpips_lambda_crop=0, max_steps='10000', optim_name='ranger', output_size=1024, resize_factors=None, save_interval=1000, start_from_latent_avg=True, stylegan_weights='', test_batch_size=8, test_workers=8, train_decoder=False, val_interval=1000, w_norm_lambda=0.025, workers=8)
Loading pSp from checkpoint: pretrained_models/psp_ffhq_toonify.pt
Model successfully loaded!
Aligned image has shape: (256, 256)

Version Details

Version ID: 919ed2f7b6c5c24f3a53207842b61b6eba515136bd7bb9ffa75e01e970609cc4
Version Created: September 29, 2022

Run on Replicate →