wyhsirius/lia – Run with an API on Replicate

wyhsirius / lia

Learning to Animate Images via Latent Space Navigation

Cold

Public
20.9K runs
T4
GitHub
Paper
License

Run with an API

Playground API Examples README Versions

Input

Run this model in Node.js with one line of code:

npx create-replicate --model=wyhsirius/lia

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run wyhsirius/lia using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "wyhsirius/lia:4ce4e4aff5bd28c6958b1e3e7628ea80718be56672d92ea8039039a3a152e67d",
  {
    input: {
      model: "vox",
      img_source: "https://replicate.delivery/mgxm/8140a5a9-16c5-42ee-90bb-cd755f8ca9bd/mona_lisa.png",
      driving_video: "https://replicate.delivery/mgxm/1724727e-d9ea-449b-9cca-2c39a9004350/driving2.mp4"
    }
  }
);

// To access the file URL:
console.log(output.url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run wyhsirius/lia using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "wyhsirius/lia:4ce4e4aff5bd28c6958b1e3e7628ea80718be56672d92ea8039039a3a152e67d",
    input={
        "model": "vox",
        "img_source": "https://replicate.delivery/mgxm/8140a5a9-16c5-42ee-90bb-cd755f8ca9bd/mona_lisa.png",
        "driving_video": "https://replicate.delivery/mgxm/1724727e-d9ea-449b-9cca-2c39a9004350/driving2.mp4"
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run wyhsirius/lia using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "wyhsirius/lia:4ce4e4aff5bd28c6958b1e3e7628ea80718be56672d92ea8039039a3a152e67d",
    "input": {
      "model": "vox",
      "img_source": "https://replicate.delivery/mgxm/8140a5a9-16c5-42ee-90bb-cd755f8ca9bd/mona_lisa.png",
      "driving_video": "https://replicate.delivery/mgxm/1724727e-d9ea-449b-9cca-2c39a9004350/driving2.mp4"
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2022-06-28T21:25:01.920262Z",
  "created_at": "2022-06-28T21:23:40.219631Z",
  "data_removed": false,
  "error": null,
  "id": "5pyjjnunwvdpdmohaxa43dzt3i",
  "input": {
    "model": "vox",
    "img_source": "https://replicate.delivery/mgxm/8140a5a9-16c5-42ee-90bb-cd755f8ca9bd/mona_lisa.png",
    "driving_video": "https://replicate.delivery/mgxm/1724727e-d9ea-449b-9cca-2c39a9004350/driving2.mp4"
  },
  "logs": "==> loading data\n\n  0%|          | 0/221 [00:00<?, ?it/s]/src/networks/styledecoder.py:439: UserWarning: torch.qr is deprecated in favor of torch.linalg.qr and will be removed in a future PyTorch release.\nThe boolean parameter 'some' has been replaced with a string parameter 'mode'.\nQ, R = torch.qr(A, some)\nshould be replaced with\nQ, R = torch.linalg.qr(A, 'reduced' if some else 'complete') (Triggered internally at  ../aten/src/ATen/native/BatchLinearAlgebra.cpp:1937.)\n  Q, R = torch.qr(weight)  # get eignvector, orthogonal [n1, n2, n3, n4]\n/root/.pyenv/versions/3.8.13/lib/python3.8/site-packages/torch/nn/functional.py:4003: UserWarning: Default grid_sample and affine_grid behavior has changed to align_corners=False since 1.3.0. Please specify align_corners=True if the old behavior is desired. See the documentation of grid_sample for details.\n  warnings.warn(\n\n  0%|          | 1/221 [00:00<00:24,  9.01it/s]\n  1%|▏         | 3/221 [00:00<00:19, 11.40it/s]\n  2%|▏         | 5/221 [00:00<00:16, 13.35it/s]\n  3%|▎         | 7/221 [00:00<00:14, 14.31it/s]\n  4%|▍         | 9/221 [00:00<00:14, 14.73it/s]\n  5%|▍         | 11/221 [00:00<00:13, 15.04it/s]\n  6%|▌         | 13/221 [00:00<00:13, 15.34it/s]\n  7%|▋         | 15/221 [00:01<00:13, 15.43it/s]\n  8%|▊         | 17/221 [00:01<00:13, 15.44it/s]\n  9%|▊         | 19/221 [00:01<00:12, 15.55it/s]\n 10%|▉         | 21/221 [00:01<00:12, 15.59it/s]\n 10%|█         | 23/221 [00:01<00:12, 15.57it/s]\n 11%|█▏        | 25/221 [00:01<00:12, 15.63it/s]\n 12%|█▏        | 27/221 [00:01<00:12, 15.64it/s]\n 13%|█▎        | 29/221 [00:01<00:12, 15.64it/s]\n 14%|█▍        | 31/221 [00:02<00:12, 15.66it/s]\n 15%|█▍        | 33/221 [00:02<00:11, 15.68it/s]\n 16%|█▌        | 35/221 [00:02<00:11, 15.63it/s]\n 17%|█▋        | 37/221 [00:02<00:11, 15.61it/s]\n 18%|█▊        | 39/221 [00:02<00:11, 15.63it/s]\n 19%|█▊        | 41/221 [00:02<00:11, 15.55it/s]\n 19%|█▉        | 43/221 [00:02<00:11, 15.63it/s]\n 20%|██        | 45/221 [00:02<00:11, 15.64it/s]\n 21%|██▏       | 47/221 [00:03<00:11, 15.55it/s]\n 22%|██▏       | 49/221 [00:03<00:11, 15.57it/s]\n 23%|██▎       | 51/221 [00:03<00:10, 15.61it/s]\n 24%|██▍       | 53/221 [00:03<00:10, 15.52it/s]\n 25%|██▍       | 55/221 [00:03<00:10, 15.59it/s]\n 26%|██▌       | 57/221 [00:03<00:10, 15.62it/s]\n 27%|██▋       | 59/221 [00:03<00:10, 15.56it/s]\n 28%|██▊       | 61/221 [00:03<00:10, 15.61it/s]\n 29%|██▊       | 63/221 [00:04<00:10, 15.61it/s]\n 29%|██▉       | 65/221 [00:04<00:10, 15.56it/s]\n 30%|███       | 67/221 [00:04<00:09, 15.60it/s]\n 31%|███       | 69/221 [00:04<00:09, 15.64it/s]\n 32%|███▏      | 71/221 [00:04<00:09, 15.58it/s]\n 33%|███▎      | 73/221 [00:04<00:09, 15.58it/s]\n 34%|███▍      | 75/221 [00:04<00:09, 15.59it/s]\n 35%|███▍      | 77/221 [00:05<00:09, 15.51it/s]\n 36%|███▌      | 79/221 [00:05<00:09, 15.53it/s]\n 37%|███▋      | 81/221 [00:05<00:09, 15.45it/s]\n 38%|███▊      | 83/221 [00:05<00:08, 15.45it/s]\n 38%|███▊      | 85/221 [00:05<00:08, 15.45it/s]\n 39%|███▉      | 87/221 [00:05<00:08, 15.45it/s]\n 40%|████      | 89/221 [00:05<00:08, 15.48it/s]\n 41%|████      | 91/221 [00:05<00:08, 15.46it/s]\n 42%|████▏     | 93/221 [00:06<00:08, 15.48it/s]\n 43%|████▎     | 95/221 [00:06<00:08, 15.52it/s]\n 44%|████▍     | 97/221 [00:06<00:08, 15.42it/s]\n 45%|████▍     | 99/221 [00:06<00:07, 15.47it/s]\n 46%|████▌     | 101/221 [00:06<00:07, 15.46it/s]\n 47%|████▋     | 103/221 [00:06<00:07, 15.48it/s]\n 48%|████▊     | 105/221 [00:06<00:07, 15.48it/s]\n 48%|████▊     | 107/221 [00:06<00:07, 15.37it/s]\n 49%|████▉     | 109/221 [00:07<00:07, 15.45it/s]\n 50%|█████     | 111/221 [00:07<00:07, 15.47it/s]\n 51%|█████     | 113/221 [00:07<00:06, 15.45it/s]\n 52%|█████▏    | 115/221 [00:07<00:06, 15.53it/s]\n 53%|█████▎    | 117/221 [00:07<00:06, 15.52it/s]\n 54%|█████▍    | 119/221 [00:07<00:06, 15.41it/s]\n 55%|█████▍    | 121/221 [00:07<00:06, 15.40it/s]\n 56%|█████▌    | 123/221 [00:07<00:06, 15.42it/s]\n 57%|█████▋    | 125/221 [00:08<00:06, 15.45it/s]\n 57%|█████▋    | 127/221 [00:08<00:06, 15.43it/s]\n 58%|█████▊    | 129/221 [00:08<00:05, 15.47it/s]\n 59%|█████▉    | 131/221 [00:08<00:05, 15.31it/s]\n 60%|██████    | 133/221 [00:08<00:05, 15.38it/s]\n 61%|██████    | 135/221 [00:08<00:05, 15.41it/s]\n 62%|██████▏   | 137/221 [00:08<00:05, 15.40it/s]\n 63%|██████▎   | 139/221 [00:09<00:05, 15.44it/s]\n 64%|██████▍   | 141/221 [00:09<00:05, 15.40it/s]\n 65%|██████▍   | 143/221 [00:09<00:05, 15.36it/s]\n 66%|██████▌   | 145/221 [00:09<00:04, 15.42it/s]\n 67%|██████▋   | 147/221 [00:09<00:04, 15.38it/s]\n 67%|██████▋   | 149/221 [00:09<00:04, 15.40it/s]\n 68%|██████▊   | 151/221 [00:09<00:04, 15.30it/s]\n 69%|██████▉   | 153/221 [00:09<00:04, 15.34it/s]\n 70%|███████   | 155/221 [00:10<00:04, 15.36it/s]\n 71%|███████   | 157/221 [00:10<00:04, 15.37it/s]\n 72%|███████▏  | 159/221 [00:10<00:04, 15.43it/s]\n 73%|███████▎  | 161/221 [00:10<00:03, 15.35it/s]\n 74%|███████▍  | 163/221 [00:10<00:03, 15.40it/s]\n 75%|███████▍  | 165/221 [00:10<00:03, 15.39it/s]\n 76%|███████▌  | 167/221 [00:10<00:03, 15.37it/s]\n 76%|███████▋  | 169/221 [00:10<00:03, 15.41it/s]\n 77%|███████▋  | 171/221 [00:11<00:03, 15.34it/s]\n 78%|███████▊  | 173/221 [00:11<00:03, 15.30it/s]\n 79%|███████▉  | 175/221 [00:11<00:03, 15.32it/s]\n 80%|████████  | 177/221 [00:11<00:02, 15.31it/s]\n 81%|████████  | 179/221 [00:11<00:02, 15.34it/s]\n 82%|████████▏ | 181/221 [00:11<00:02, 15.30it/s]\n 83%|████████▎ | 183/221 [00:11<00:02, 15.34it/s]\n 84%|████████▎ | 185/221 [00:12<00:02, 15.32it/s]\n 85%|████████▍ | 187/221 [00:12<00:02, 15.34it/s]\n 86%|████████▌ | 189/221 [00:12<00:02, 15.31it/s]\n 86%|████████▋ | 191/221 [00:12<00:01, 15.33it/s]\n 87%|████████▋ | 193/221 [00:12<00:01, 15.35it/s]\n 88%|████████▊ | 195/221 [00:12<00:01, 15.32it/s]\n 89%|████████▉ | 197/221 [00:12<00:01, 15.38it/s]\n 90%|█████████ | 199/221 [00:12<00:01, 15.30it/s]\n 91%|█████████ | 201/221 [00:13<00:01, 15.35it/s]\n 92%|█████████▏| 203/221 [00:13<00:01, 15.34it/s]\n 93%|█████████▎| 205/221 [00:13<00:01, 15.26it/s]\n 94%|█████████▎| 207/221 [00:13<00:00, 15.27it/s]\n 95%|█████████▍| 209/221 [00:13<00:00, 15.22it/s]\n 95%|█████████▌| 211/221 [00:13<00:00, 15.22it/s]\n 96%|█████████▋| 213/221 [00:13<00:00, 15.20it/s]\n 97%|█████████▋| 215/221 [00:13<00:00, 15.24it/s]\n 98%|█████████▊| 217/221 [00:14<00:00, 15.26it/s]\n 99%|█████████▉| 219/221 [00:14<00:00, 15.25it/s]\n100%|██████████| 221/221 [00:14<00:00, 15.17it/s]\n100%|██████████| 221/221 [00:14<00:00, 15.37it/s]",
  "metrics": {
    "predict_time": 17.6927,
    "total_time": 81.700631
  },
  "output": "https://replicate.delivery/mgxm/0b6e1c51-a019-480c-8729-67133a6b122e/output.mp4",
  "started_at": "2022-06-28T21:24:44.227562Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/5pyjjnunwvdpdmohaxa43dzt3i",
    "cancel": "https://api.replicate.com/v1/predictions/5pyjjnunwvdpdmohaxa43dzt3i/cancel"
  },
  "version": "4ce4e4aff5bd28c6958b1e3e7628ea80718be56672d92ea8039039a3a152e67d"
}

Generated in

17.7 seconds

Tweak itReport

==> loading data

  0%|          | 0/221 [00:00<?, ?it/s]/src/networks/styledecoder.py:439: UserWarning: torch.qr is deprecated in favor of torch.linalg.qr and will be removed in a future PyTorch release.
The boolean parameter 'some' has been replaced with a string parameter 'mode'.
Q, R = torch.qr(A, some)
should be replaced with
Q, R = torch.linalg.qr(A, 'reduced' if some else 'complete') (Triggered internally at  ../aten/src/ATen/native/BatchLinearAlgebra.cpp:1937.)
  Q, R = torch.qr(weight)  # get eignvector, orthogonal [n1, n2, n3, n4]
/root/.pyenv/versions/3.8.13/lib/python3.8/site-packages/torch/nn/functional.py:4003: UserWarning: Default grid_sample and affine_grid behavior has changed to align_corners=False since 1.3.0. Please specify align_corners=True if the old behavior is desired. See the documentation of grid_sample for details.
  warnings.warn(

  0%|          | 1/221 [00:00<00:24,  9.01it/s]
  1%|▏         | 3/221 [00:00<00:19, 11.40it/s]
  2%|▏         | 5/221 [00:00<00:16, 13.35it/s]
  3%|▎         | 7/221 [00:00<00:14, 14.31it/s]
  4%|▍         | 9/221 [00:00<00:14, 14.73it/s]
  5%|▍         | 11/221 [00:00<00:13, 15.04it/s]
  6%|▌         | 13/221 [00:00<00:13, 15.34it/s]
  7%|▋         | 15/221 [00:01<00:13, 15.43it/s]
  8%|▊         | 17/221 [00:01<00:13, 15.44it/s]
  9%|▊         | 19/221 [00:01<00:12, 15.55it/s]
 10%|▉         | 21/221 [00:01<00:12, 15.59it/s]
 10%|█         | 23/221 [00:01<00:12, 15.57it/s]
 11%|█▏        | 25/221 [00:01<00:12, 15.63it/s]
 12%|█▏        | 27/221 [00:01<00:12, 15.64it/s]
 13%|█▎        | 29/221 [00:01<00:12, 15.64it/s]
 14%|█▍        | 31/221 [00:02<00:12, 15.66it/s]
 15%|█▍        | 33/221 [00:02<00:11, 15.68it/s]
 16%|█▌        | 35/221 [00:02<00:11, 15.63it/s]
 17%|█▋        | 37/221 [00:02<00:11, 15.61it/s]
 18%|█▊        | 39/221 [00:02<00:11, 15.63it/s]
 19%|█▊        | 41/221 [00:02<00:11, 15.55it/s]
 19%|█▉        | 43/221 [00:02<00:11, 15.63it/s]
 20%|██        | 45/221 [00:02<00:11, 15.64it/s]
 21%|██▏       | 47/221 [00:03<00:11, 15.55it/s]
 22%|██▏       | 49/221 [00:03<00:11, 15.57it/s]
 23%|██▎       | 51/221 [00:03<00:10, 15.61it/s]
 24%|██▍       | 53/221 [00:03<00:10, 15.52it/s]
 25%|██▍       | 55/221 [00:03<00:10, 15.59it/s]
 26%|██▌       | 57/221 [00:03<00:10, 15.62it/s]
 27%|██▋       | 59/221 [00:03<00:10, 15.56it/s]
 28%|██▊       | 61/221 [00:03<00:10, 15.61it/s]
 29%|██▊       | 63/221 [00:04<00:10, 15.61it/s]
 29%|██▉       | 65/221 [00:04<00:10, 15.56it/s]
 30%|███       | 67/221 [00:04<00:09, 15.60it/s]
 31%|███       | 69/221 [00:04<00:09, 15.64it/s]
 32%|███▏      | 71/221 [00:04<00:09, 15.58it/s]
 33%|███▎      | 73/221 [00:04<00:09, 15.58it/s]
 34%|███▍      | 75/221 [00:04<00:09, 15.59it/s]
 35%|███▍      | 77/221 [00:05<00:09, 15.51it/s]
 36%|███▌      | 79/221 [00:05<00:09, 15.53it/s]
 37%|███▋      | 81/221 [00:05<00:09, 15.45it/s]
 38%|███▊      | 83/221 [00:05<00:08, 15.45it/s]
 38%|███▊      | 85/221 [00:05<00:08, 15.45it/s]
 39%|███▉      | 87/221 [00:05<00:08, 15.45it/s]
 40%|████      | 89/221 [00:05<00:08, 15.48it/s]
 41%|████      | 91/221 [00:05<00:08, 15.46it/s]
 42%|████▏     | 93/221 [00:06<00:08, 15.48it/s]
 43%|████▎     | 95/221 [00:06<00:08, 15.52it/s]
 44%|████▍     | 97/221 [00:06<00:08, 15.42it/s]
 45%|████▍     | 99/221 [00:06<00:07, 15.47it/s]
 46%|████▌     | 101/221 [00:06<00:07, 15.46it/s]
 47%|████▋     | 103/221 [00:06<00:07, 15.48it/s]
 48%|████▊     | 105/221 [00:06<00:07, 15.48it/s]
 48%|████▊     | 107/221 [00:06<00:07, 15.37it/s]
 49%|████▉     | 109/221 [00:07<00:07, 15.45it/s]
 50%|█████     | 111/221 [00:07<00:07, 15.47it/s]
 51%|█████     | 113/221 [00:07<00:06, 15.45it/s]
 52%|█████▏    | 115/221 [00:07<00:06, 15.53it/s]
 53%|█████▎    | 117/221 [00:07<00:06, 15.52it/s]
 54%|█████▍    | 119/221 [00:07<00:06, 15.41it/s]
 55%|█████▍    | 121/221 [00:07<00:06, 15.40it/s]
 56%|█████▌    | 123/221 [00:07<00:06, 15.42it/s]
 57%|█████▋    | 125/221 [00:08<00:06, 15.45it/s]
 57%|█████▋    | 127/221 [00:08<00:06, 15.43it/s]
 58%|█████▊    | 129/221 [00:08<00:05, 15.47it/s]
 59%|█████▉    | 131/221 [00:08<00:05, 15.31it/s]
 60%|██████    | 133/221 [00:08<00:05, 15.38it/s]
 61%|██████    | 135/221 [00:08<00:05, 15.41it/s]
 62%|██████▏   | 137/221 [00:08<00:05, 15.40it/s]
 63%|██████▎   | 139/221 [00:09<00:05, 15.44it/s]
 64%|██████▍   | 141/221 [00:09<00:05, 15.40it/s]
 65%|██████▍   | 143/221 [00:09<00:05, 15.36it/s]
 66%|██████▌   | 145/221 [00:09<00:04, 15.42it/s]
 67%|██████▋   | 147/221 [00:09<00:04, 15.38it/s]
 67%|██████▋   | 149/221 [00:09<00:04, 15.40it/s]
 68%|██████▊   | 151/221 [00:09<00:04, 15.30it/s]
 69%|██████▉   | 153/221 [00:09<00:04, 15.34it/s]
 70%|███████   | 155/221 [00:10<00:04, 15.36it/s]
 71%|███████   | 157/221 [00:10<00:04, 15.37it/s]
 72%|███████▏  | 159/221 [00:10<00:04, 15.43it/s]
 73%|███████▎  | 161/221 [00:10<00:03, 15.35it/s]
 74%|███████▍  | 163/221 [00:10<00:03, 15.40it/s]
 75%|███████▍  | 165/221 [00:10<00:03, 15.39it/s]
 76%|███████▌  | 167/221 [00:10<00:03, 15.37it/s]
 76%|███████▋  | 169/221 [00:10<00:03, 15.41it/s]
 77%|███████▋  | 171/221 [00:11<00:03, 15.34it/s]
 78%|███████▊  | 173/221 [00:11<00:03, 15.30it/s]
 79%|███████▉  | 175/221 [00:11<00:03, 15.32it/s]
 80%|████████  | 177/221 [00:11<00:02, 15.31it/s]
 81%|████████  | 179/221 [00:11<00:02, 15.34it/s]
 82%|████████▏ | 181/221 [00:11<00:02, 15.30it/s]
 83%|████████▎ | 183/221 [00:11<00:02, 15.34it/s]
 84%|████████▎ | 185/221 [00:12<00:02, 15.32it/s]
 85%|████████▍ | 187/221 [00:12<00:02, 15.34it/s]
 86%|████████▌ | 189/221 [00:12<00:02, 15.31it/s]
 86%|████████▋ | 191/221 [00:12<00:01, 15.33it/s]
 87%|████████▋ | 193/221 [00:12<00:01, 15.35it/s]
 88%|████████▊ | 195/221 [00:12<00:01, 15.32it/s]
 89%|████████▉ | 197/221 [00:12<00:01, 15.38it/s]
 90%|█████████ | 199/221 [00:12<00:01, 15.30it/s]
 91%|█████████ | 201/221 [00:13<00:01, 15.35it/s]
 92%|█████████▏| 203/221 [00:13<00:01, 15.34it/s]
 93%|█████████▎| 205/221 [00:13<00:01, 15.26it/s]
 94%|█████████▎| 207/221 [00:13<00:00, 15.27it/s]
 95%|█████████▍| 209/221 [00:13<00:00, 15.22it/s]
 95%|█████████▌| 211/221 [00:13<00:00, 15.22it/s]
 96%|█████████▋| 213/221 [00:13<00:00, 15.20it/s]
 97%|█████████▋| 215/221 [00:13<00:00, 15.24it/s]
 98%|█████████▊| 217/221 [00:14<00:00, 15.26it/s]
 99%|█████████▉| 219/221 [00:14<00:00, 15.25it/s]
100%|██████████| 221/221 [00:14<00:00, 15.17it/s]
100%|██████████| 221/221 [00:14<00:00, 15.37it/s]

Examples

View more examples

Run time and cost

This model costs approximately $0.037 to run on Replicate, or 27 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia T4 GPU hardware. Predictions typically complete within 3 minutes. The predict time for this model varies significantly based on the inputs.

Readme

This is the official PyTorch implementation of the ICLR 2022 paper “Latent Image Animator: Learning to Animate Images via Latent Space Navigation”

Citation

If you find this code useful for your research, please consider citing our paper:

@inproceedings{
wang2022latent,
title={Latent Image Animator: Learning to Animate Images via Latent Space Navigation},
author={Yaohui Wang and Di Yang and Francois Bremond and Antitza Dantcheva},
booktitle={International Conference on Learning Representations},
year={2022}
}

Acknowledgement

Part of the code is adapted from FOMM and MRAA. We thank authors for their contribution to the community.