cjwbw/tokenflow:d456a26c – Run with an API on Replicate

Version

You're looking at a specific version of this model. Jump to the model overview.

cjwbw /tokenflow:d456a26c

Playground API

Input

video

*file

Input video.

inversion_prompt

string

Shift + Return to add a new line

Describe your input video or leave it empty.

Default: ""

diffusion_prompt

*string

Shift + Return to add a new line

Describe your output video.

negative_diffusion_prompt

string

Shift + Return to add a new line

ugly, blurry, low res, unrealistic, unaestheticugly, blurry, low res, unrealistic, unaesthetic

Specify things to not see in the output

Default: "ugly, blurry, low res, unrealistic, unaesthetic"

n_frames

integer

Number of frames in the video to process.

Default: 40

width

integer

Width of the output video. For non-square videos, we recommend using 672 x 384 or 384 x 672, aspect ratio 1.75.

Default: 512

height

integer

Height of the output video. For non-square videos, we recommend using 672 x 384 or 384 x 672, aspect ratio 1.75.

Default: 512

fps

integer

Frames per second in the output video

Default: 10

num_inversion_steps

integer

Number of inversion step.

Default: 50

num_diffusion_steps

integer

Number of sampling step.

Default: 50

guidance_scale

number

(minimum: 1, maximum: 20)

Scale for classifier-free guidance

Default: 7.5

seed

integer

Random seed. Leave blank to randomize the seed.

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

npx create-replicate --model=cjwbw/tokenflow

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

const output = await replicate.run(
  "cjwbw/tokenflow:d456a26c0c1764ac4d9b933a564fe70e660c46423ba0afb5d3200f1a46060728",
  {
    input: {
      fps: 10,
      width: 512,
      height: 512,
      n_frames: 40,
      guidance_scale: 7.5,
      inversion_prompt: "",
      num_diffusion_steps: 50,
      num_inversion_steps: 50,
      negative_diffusion_prompt: "ugly, blurry, low res, unrealistic, unaesthetic"
    }
  }
);
console.log(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 cjwbw/tokenflow using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "cjwbw/tokenflow:d456a26c0c1764ac4d9b933a564fe70e660c46423ba0afb5d3200f1a46060728",
    input={
        "fps": 10,
        "width": 512,
        "height": 512,
        "n_frames": 40,
        "guidance_scale": 7.5,
        "inversion_prompt": "",
        "num_diffusion_steps": 50,
        "num_inversion_steps": 50,
        "negative_diffusion_prompt": "ugly, blurry, low res, unrealistic, unaesthetic"
    }
)
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 cjwbw/tokenflow 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": "d456a26c0c1764ac4d9b933a564fe70e660c46423ba0afb5d3200f1a46060728",
    "input": {
      "fps": 10,
      "width": 512,
      "height": 512,
      "n_frames": 40,
      "guidance_scale": 7.5,
      "inversion_prompt": "",
      "num_diffusion_steps": 50,
      "num_inversion_steps": 50,
      "negative_diffusion_prompt": "ugly, blurry, low res, unrealistic, unaesthetic"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/chenxwh/tokenflow@sha256:d456a26c0c1764ac4d9b933a564fe70e660c46423ba0afb5d3200f1a46060728 \
  -i 'fps=10' \
  -i 'width=512' \
  -i 'height=512' \
  -i 'n_frames=40' \
  -i 'guidance_scale=7.5' \
  -i 'inversion_prompt=""' \
  -i 'num_diffusion_steps=50' \
  -i 'num_inversion_steps=50' \
  -i 'negative_diffusion_prompt="ugly, blurry, low res, unrealistic, unaesthetic"'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/chenxwh/tokenflow@sha256:d456a26c0c1764ac4d9b933a564fe70e660c46423ba0afb5d3200f1a46060728
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "fps": 10,
      "width": 512,
      "height": 512,
      "n_frames": 40,
      "guidance_scale": 7.5,
      "inversion_prompt": "",
      "num_diffusion_steps": 50,
      "num_inversion_steps": 50,
      "negative_diffusion_prompt": "ugly, blurry, low res, unrealistic, unaesthetic"
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

No output yet! Press "Submit" to start a prediction.