camenduru/champ | Run with an API on Replicate

camenduru / champ

Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance

Cold

Public
14K runs
A100 (80GB)
GitHub
Paper
License

Iterate in playground

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=camenduru/champ

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";
import fs from "node:fs";

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

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

const output = await replicate.run(
  "camenduru/champ:4b57a21012518a1a15cf70699df24f5bc75ed7a149fe06ebc04459e029315e1e",
  {
    input: {
      guidance_data: "example_data/motions/motion-06",
      ref_image_path: "https://replicate.delivery/pbxt/KdEPlRvrT0Bw4dppxVyLhVxLL9doJGpjKIxMdtOSVIKIUJj1/932c5fad-b1ec-4e13-964f-20936db20954.png"
    }
  }
);

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

output = replicate.run(
    "camenduru/champ:4b57a21012518a1a15cf70699df24f5bc75ed7a149fe06ebc04459e029315e1e",
    input={
        "guidance_data": "example_data/motions/motion-06",
        "ref_image_path": "https://replicate.delivery/pbxt/KdEPlRvrT0Bw4dppxVyLhVxLL9doJGpjKIxMdtOSVIKIUJj1/932c5fad-b1ec-4e13-964f-20936db20954.png"
    }
)
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 camenduru/champ 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": "camenduru/champ:4b57a21012518a1a15cf70699df24f5bc75ed7a149fe06ebc04459e029315e1e",
    "input": {
      "guidance_data": "example_data/motions/motion-06",
      "ref_image_path": "https://replicate.delivery/pbxt/KdEPlRvrT0Bw4dppxVyLhVxLL9doJGpjKIxMdtOSVIKIUJj1/932c5fad-b1ec-4e13-964f-20936db20954.png"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-03-25T14:52:59.807226Z",
  "created_at": "2024-03-25T14:51:20.317794Z",
  "data_removed": false,
  "error": null,
  "id": "zmdovmzbljmxg37lq47g554vcq",
  "input": {
    "guidance_data": "example_data/motions/motion-06",
    "ref_image_path": "https://replicate.delivery/pbxt/KdEPlRvrT0Bw4dppxVyLhVxLL9doJGpjKIxMdtOSVIKIUJj1/932c5fad-b1ec-4e13-964f-20936db20954.png"
  },
  "logs": "0%|          | 0/20 [00:00<?, ?it/s]\n  5%|▌         | 1/20 [00:04<01:26,  4.57s/it]\n 10%|█         | 2/20 [00:08<01:16,  4.27s/it]\n 15%|█▌        | 3/20 [00:12<01:11,  4.18s/it]\n 20%|██        | 4/20 [00:16<01:06,  4.15s/it]\n 25%|██▌       | 5/20 [00:20<01:01,  4.12s/it]\n 30%|███       | 6/20 [00:24<00:57,  4.11s/it]\n 35%|███▌      | 7/20 [00:29<00:53,  4.10s/it]\n 40%|████      | 8/20 [00:33<00:49,  4.11s/it]\n 45%|████▌     | 9/20 [00:37<00:45,  4.12s/it]\n 50%|█████     | 10/20 [00:41<00:41,  4.14s/it]\n 55%|█████▌    | 11/20 [00:45<00:37,  4.14s/it]\n 60%|██████    | 12/20 [00:49<00:33,  4.13s/it]\n 65%|██████▌   | 13/20 [00:53<00:28,  4.12s/it]\n 70%|███████   | 14/20 [00:57<00:24,  4.12s/it]\n 75%|███████▌  | 15/20 [01:02<00:20,  4.13s/it]\n 80%|████████  | 16/20 [01:06<00:16,  4.12s/it]\n 85%|████████▌ | 17/20 [01:10<00:12,  4.12s/it]\n 90%|█████████ | 18/20 [01:14<00:08,  4.13s/it]\n 95%|█████████▌| 19/20 [01:18<00:04,  4.13s/it]\n100%|██████████| 20/20 [01:22<00:00,  4.15s/it]\n100%|██████████| 20/20 [01:22<00:00,  4.14s/it]\n  0%|          | 0/116 [00:00<?, ?it/s]\n  4%|▍         | 5/116 [00:00<00:02, 47.07it/s]\n  9%|▊         | 10/116 [00:00<00:03, 32.14it/s]\n 12%|█▏        | 14/116 [00:00<00:03, 29.52it/s]\n 16%|█▌        | 18/116 [00:00<00:03, 28.26it/s]\n 18%|█▊        | 21/116 [00:00<00:03, 27.68it/s]\n 21%|██        | 24/116 [00:00<00:03, 27.26it/s]\n 23%|██▎       | 27/116 [00:00<00:03, 26.99it/s]\n 26%|██▌       | 30/116 [00:01<00:03, 26.79it/s]\n 28%|██▊       | 33/116 [00:01<00:03, 26.65it/s]\n 31%|███       | 36/116 [00:01<00:03, 26.55it/s]\n 34%|███▎      | 39/116 [00:01<00:02, 26.48it/s]\n 36%|███▌      | 42/116 [00:01<00:02, 26.43it/s]\n 39%|███▉      | 45/116 [00:01<00:02, 26.40it/s]\n 41%|████▏     | 48/116 [00:01<00:02, 26.38it/s]\n 44%|████▍     | 51/116 [00:01<00:02, 26.36it/s]\n 47%|████▋     | 54/116 [00:01<00:02, 26.35it/s]\n 49%|████▉     | 57/116 [00:02<00:02, 26.32it/s]\n 52%|█████▏    | 60/116 [00:02<00:02, 26.32it/s]\n 54%|█████▍    | 63/116 [00:02<00:02, 26.34it/s]\n 57%|█████▋    | 66/116 [00:02<00:01, 26.34it/s]\n 59%|█████▉    | 69/116 [00:02<00:01, 26.33it/s]\n 62%|██████▏   | 72/116 [00:02<00:01, 26.33it/s]\n 65%|██████▍   | 75/116 [00:02<00:01, 26.33it/s]\n 67%|██████▋   | 78/116 [00:02<00:01, 26.33it/s]\n 70%|██████▉   | 81/116 [00:02<00:01, 26.32it/s]\n 72%|███████▏  | 84/116 [00:03<00:01, 26.33it/s]\n 75%|███████▌  | 87/116 [00:03<00:01, 26.32it/s]\n 78%|███████▊  | 90/116 [00:03<00:00, 26.34it/s]\n 80%|████████  | 93/116 [00:03<00:00, 26.33it/s]\n 83%|████████▎ | 96/116 [00:03<00:00, 26.32it/s]\n 85%|████████▌ | 99/116 [00:03<00:00, 26.34it/s]\n 88%|████████▊ | 102/116 [00:03<00:00, 26.34it/s]\n 91%|█████████ | 105/116 [00:03<00:00, 26.33it/s]\n 93%|█████████▎| 108/116 [00:04<00:00, 26.34it/s]\n 96%|█████████▌| 111/116 [00:04<00:00, 26.34it/s]\n 98%|█████████▊| 114/116 [00:04<00:00, 26.33it/s]\n100%|██████████| 116/116 [00:04<00:00, 26.83it/s]\nIMAGEIO FFMPEG_WRITER WARNING: input image is not divisible by macro_block_size=16, resizing from (330, 406) to (336, 416) to ensure video compatibility with most codecs and players. To prevent resizing, make your input image divisible by the macro_block_size or set the macro_block_size to 1 (risking incompatibility).\n[swscaler @ 0x6afb340] Warning: data is not aligned! This can lead to a speed loss",
  "metrics": {
    "predict_time": 99.474665,
    "total_time": 99.489432
  },
  "output": "https://replicate.delivery/pbxt/uHlaOVt9Xi7VA1n8qGEIFhWUeWMrKcDwpqXxp1dIJLslD6RJA/animation.mp4",
  "started_at": "2024-03-25T14:51:20.332561Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/zmdovmzbljmxg37lq47g554vcq",
    "cancel": "https://api.replicate.com/v1/predictions/zmdovmzbljmxg37lq47g554vcq/cancel"
  },
  "version": "6100385d214e61f027f7567e4be8aa1fe35bbdb274e86ba58cbb8b924a7c804f"
}

Generated in

1 minute 39 seconds

Tweak it Report View full prediction

0%|          | 0/20 [00:00<?, ?it/s]
  5%|▌         | 1/20 [00:04<01:26,  4.57s/it]
 10%|█         | 2/20 [00:08<01:16,  4.27s/it]
 15%|█▌        | 3/20 [00:12<01:11,  4.18s/it]
 20%|██        | 4/20 [00:16<01:06,  4.15s/it]
 25%|██▌       | 5/20 [00:20<01:01,  4.12s/it]
 30%|███       | 6/20 [00:24<00:57,  4.11s/it]
 35%|███▌      | 7/20 [00:29<00:53,  4.10s/it]
 40%|████      | 8/20 [00:33<00:49,  4.11s/it]
 45%|████▌     | 9/20 [00:37<00:45,  4.12s/it]
 50%|█████     | 10/20 [00:41<00:41,  4.14s/it]
 55%|█████▌    | 11/20 [00:45<00:37,  4.14s/it]
 60%|██████    | 12/20 [00:49<00:33,  4.13s/it]
 65%|██████▌   | 13/20 [00:53<00:28,  4.12s/it]
 70%|███████   | 14/20 [00:57<00:24,  4.12s/it]
 75%|███████▌  | 15/20 [01:02<00:20,  4.13s/it]
 80%|████████  | 16/20 [01:06<00:16,  4.12s/it]
 85%|████████▌ | 17/20 [01:10<00:12,  4.12s/it]
 90%|█████████ | 18/20 [01:14<00:08,  4.13s/it]
 95%|█████████▌| 19/20 [01:18<00:04,  4.13s/it]
100%|██████████| 20/20 [01:22<00:00,  4.15s/it]
100%|██████████| 20/20 [01:22<00:00,  4.14s/it]
  0%|          | 0/116 [00:00<?, ?it/s]
  4%|▍         | 5/116 [00:00<00:02, 47.07it/s]
  9%|▊         | 10/116 [00:00<00:03, 32.14it/s]
 12%|█▏        | 14/116 [00:00<00:03, 29.52it/s]
 16%|█▌        | 18/116 [00:00<00:03, 28.26it/s]
 18%|█▊        | 21/116 [00:00<00:03, 27.68it/s]
 21%|██        | 24/116 [00:00<00:03, 27.26it/s]
 23%|██▎       | 27/116 [00:00<00:03, 26.99it/s]
 26%|██▌       | 30/116 [00:01<00:03, 26.79it/s]
 28%|██▊       | 33/116 [00:01<00:03, 26.65it/s]
 31%|███       | 36/116 [00:01<00:03, 26.55it/s]
 34%|███▎      | 39/116 [00:01<00:02, 26.48it/s]
 36%|███▌      | 42/116 [00:01<00:02, 26.43it/s]
 39%|███▉      | 45/116 [00:01<00:02, 26.40it/s]
 41%|████▏     | 48/116 [00:01<00:02, 26.38it/s]
 44%|████▍     | 51/116 [00:01<00:02, 26.36it/s]
 47%|████▋     | 54/116 [00:01<00:02, 26.35it/s]
 49%|████▉     | 57/116 [00:02<00:02, 26.32it/s]
 52%|█████▏    | 60/116 [00:02<00:02, 26.32it/s]
 54%|█████▍    | 63/116 [00:02<00:02, 26.34it/s]
 57%|█████▋    | 66/116 [00:02<00:01, 26.34it/s]
 59%|█████▉    | 69/116 [00:02<00:01, 26.33it/s]
 62%|██████▏   | 72/116 [00:02<00:01, 26.33it/s]
 65%|██████▍   | 75/116 [00:02<00:01, 26.33it/s]
 67%|██████▋   | 78/116 [00:02<00:01, 26.33it/s]
 70%|██████▉   | 81/116 [00:02<00:01, 26.32it/s]
 72%|███████▏  | 84/116 [00:03<00:01, 26.33it/s]
 75%|███████▌  | 87/116 [00:03<00:01, 26.32it/s]
 78%|███████▊  | 90/116 [00:03<00:00, 26.34it/s]
 80%|████████  | 93/116 [00:03<00:00, 26.33it/s]
 83%|████████▎ | 96/116 [00:03<00:00, 26.32it/s]
 85%|████████▌ | 99/116 [00:03<00:00, 26.34it/s]
 88%|████████▊ | 102/116 [00:03<00:00, 26.34it/s]
 91%|█████████ | 105/116 [00:03<00:00, 26.33it/s]
 93%|█████████▎| 108/116 [00:04<00:00, 26.34it/s]
 96%|█████████▌| 111/116 [00:04<00:00, 26.34it/s]
 98%|█████████▊| 114/116 [00:04<00:00, 26.33it/s]
100%|██████████| 116/116 [00:04<00:00, 26.83it/s]
IMAGEIO FFMPEG_WRITER WARNING: input image is not divisible by macro_block_size=16, resizing from (330, 406) to (336, 416) to ensure video compatibility with most codecs and players. To prevent resizing, make your input image divisible by the macro_block_size or set the macro_block_size to 1 (risking incompatibility).
[swscaler @ 0x6afb340] Warning: data is not aligned! This can lead to a speed loss

This output was created using a different version of the model, camenduru/champ:6100385d.

Examples

View more examples

Run time and cost

This model costs approximately $0.55 to run on Replicate, or 1 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 A100 (80GB) GPU hardware. Predictions typically complete within 7 minutes. The predict time for this model varies significantly based on the inputs.

Readme

🐣 Please follow me for new updates https://twitter.com/camenduru
🔥 Please join our discord server https://discord.gg/k5BwmmvJJU
🥳 Please join my patreon community https://patreon.com/camenduru

Input

Output

Examples

Run time and cost

Readme

🕸 Replicate

🧬 Code

📄 Paper

🌐 Page

🏢 Sponsor