kitaef/mytestmodel 🖼️ → 🖼️

▶️ 122 runs 📅 May 2024 ⚙️ Cog 0.9.6
anime image-style-transfer image-to-image

About

The img2img pipeline that makes an anime-style image of a person. It uses one of sd1.5 models as a base, depth-estimation as a ControleNet and IPadapter model for face consistency.

Example Output

Output

Example output

Performance Metrics

18.18s Prediction Time
136.75s Total Time
Input Parameters
input_image (required) Type: string
An image with a person
Output Schema

Output

Type: stringFormat: uri

Example Execution Logs
0%|          | 0/20 [00:00<?, ?it/s]/root/.pyenv/versions/3.11.9/lib/python3.11/site-packages/torch/nn/modules/conv.py:456: UserWarning: Plan failed with a cudnnException: CUDNN_BACKEND_EXECUTION_PLAN_DESCRIPTOR: cudnnFinalize Descriptor Failed cudnn_status: CUDNN_STATUS_NOT_SUPPORTED (Triggered internally at ../aten/src/ATen/native/cudnn/Conv_v8.cpp:919.)
return F.conv2d(input, weight, bias, self.stride,
  5%|▌         | 1/20 [00:02<00:41,  2.19s/it]
 10%|█         | 2/20 [00:02<00:20,  1.16s/it]
 15%|█▌        | 3/20 [00:03<00:14,  1.20it/s]
 20%|██        | 4/20 [00:03<00:10,  1.48it/s]
 25%|██▌       | 5/20 [00:03<00:08,  1.70it/s]
 30%|███       | 6/20 [00:04<00:07,  1.86it/s]
 35%|███▌      | 7/20 [00:04<00:06,  1.98it/s]
 40%|████      | 8/20 [00:05<00:05,  2.07it/s]
 45%|████▌     | 9/20 [00:05<00:05,  2.14it/s]
 50%|█████     | 10/20 [00:06<00:04,  2.18it/s]
 55%|█████▌    | 11/20 [00:06<00:04,  2.21it/s]
 60%|██████    | 12/20 [00:06<00:03,  2.24it/s]
 65%|██████▌   | 13/20 [00:07<00:03,  2.25it/s]
 70%|███████   | 14/20 [00:07<00:02,  2.26it/s]
 75%|███████▌  | 15/20 [00:08<00:02,  2.27it/s]
 80%|████████  | 16/20 [00:08<00:01,  2.28it/s]
 85%|████████▌ | 17/20 [00:09<00:01,  2.28it/s]
 90%|█████████ | 18/20 [00:09<00:00,  2.28it/s]
 95%|█████████▌| 19/20 [00:10<00:00,  2.29it/s]
100%|██████████| 20/20 [00:10<00:00,  2.29it/s]
100%|██████████| 20/20 [00:10<00:00,  1.91it/s]
Version Details
Version ID
a0ebe82aad0744fbc8f6964143760ed306af3864daa4b62a776b656636c1f191
Version Created
May 5, 2024
Run on Replicate →