voodoohop/flux-dance – Run with an API on Replicate

voodoohop / flux-dance

Cold

Public
273 runs
L40S

Run with an API

Playground API Examples README Versions

Input

style_suffix

string

Shift + Return to add a new line

angular, academic art, cubism, an abstract drawing by Svetoslav Roerich, abstract illusionism, concept art, angular, broken-stained-glass, concrete poetry, anton semono. black and white, granular, abstract, hand drawings, grainy, dmysticism, sacred symbology, blueprintangular, academic art, cubism, an abstract drawing by Svetoslav Roerich, abstract illusionism, concept art, angular, broken-stained-glass, concrete poetry, anton semono. black and white, granular, abstract, hand drawings, grainy, dmysticism, sacred symbology, blueprint

Style suffix to append to each prompt

Default: "angular, academic art, cubism, an abstract drawing by Svetoslav Roerich, abstract illusionism, concept art, angular, broken-stained-glass, concrete poetry, anton semono. black and white, granular, abstract, hand drawings, grainy, dmysticism, sacred symbology, blueprint"

narrative

string

Shift + Return to add a new line

Silhouettes of valleys 
Silhouettes of hillsSilhouettes of valleys 
Silhouettes of hills

Narrative prompts, one per line. Each line defines a prompt for a certain time in the sequence.

Default: "Silhouettes of valleys \nSilhouettes of hills"

audio_file

file

Audio file to drive interpolation (optional)

width

integer

Width of the generated image

Default: 512

height

integer

Height of the generated image

Default: 512

seed

integer

Random seed

Default: 42

interpolation_steps

integer

Number of interpolation steps between seeds (ignored if audio_file is provided)

Default: 4

variation_strength

number

Controls how much the audio amplitude affects the image variation (0-1)

Default: 0.3

audio_smoothing

number

Smoothing factor for audio (0-1, higher = more smoothing)

Default: 0.8

audio_loudness_type

string

Type of audio loudness measurement to use

Default: "peak"

fps

integer

Frames per second for the video

Default: 10

output_format

string

Format of the output image

Default: "png"

interpolate_prompts

boolean

Interpolate between prompts instead of switching between them

Default: true

loop_interpolation

boolean

Loop the interpolation back to the first prompt

Default: false

model_name

string

Which model to use for generation

Default: "flux"

guidance_scale

number

(minimum: 1, maximum: 20)

Guidance scale for Stable Diffusion model (higher = more adherence to prompt, ignored for FLUX)

Default: 7.5

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

npx create-replicate --model=voodoohop/flux-dance

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 voodoohop/flux-dance using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "voodoohop/flux-dance:73078397bad4806ee9d2fa7e281e984c579a6a8fdd2d352c91261f7a93e7e0c0",
  {
    input: {
      fps: 10,
      seed: 42,
      width: 512,
      height: 512,
      narrative: "Silhouettes of valleys \nSilhouettes of hills",
      model_name: "flux",
      style_suffix: "angular, academic art, cubism, an abstract drawing by Svetoslav Roerich, abstract illusionism, concept art, angular, broken-stained-glass, concrete poetry, anton semono. black and white, granular, abstract, hand drawings, grainy, dmysticism, sacred symbology, blueprint",
      output_format: "png",
      guidance_scale: 7.5,
      audio_smoothing: 0.8,
      loop_interpolation: false,
      variation_strength: 0.3,
      audio_loudness_type: "peak",
      interpolate_prompts: true,
      interpolation_steps: 4
    }
  }
);

// 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 voodoohop/flux-dance using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "voodoohop/flux-dance:73078397bad4806ee9d2fa7e281e984c579a6a8fdd2d352c91261f7a93e7e0c0",
    input={
        "fps": 10,
        "seed": 42,
        "width": 512,
        "height": 512,
        "narrative": "Silhouettes of valleys \nSilhouettes of hills",
        "model_name": "flux",
        "style_suffix": "angular, academic art, cubism, an abstract drawing by Svetoslav Roerich, abstract illusionism, concept art, angular, broken-stained-glass, concrete poetry, anton semono. black and white, granular, abstract, hand drawings, grainy, dmysticism, sacred symbology, blueprint",
        "output_format": "png",
        "guidance_scale": 7.5,
        "audio_smoothing": 0.8,
        "loop_interpolation": False,
        "variation_strength": 0.3,
        "audio_loudness_type": "peak",
        "interpolate_prompts": True,
        "interpolation_steps": 4
    }
)
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 voodoohop/flux-dance 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": "voodoohop/flux-dance:73078397bad4806ee9d2fa7e281e984c579a6a8fdd2d352c91261f7a93e7e0c0",
    "input": {
      "fps": 10,
      "seed": 42,
      "width": 512,
      "height": 512,
      "narrative": "Silhouettes of valleys \\nSilhouettes of hills",
      "model_name": "flux",
      "style_suffix": "angular, academic art, cubism, an abstract drawing by Svetoslav Roerich, abstract illusionism, concept art, angular, broken-stained-glass, concrete poetry, anton semono. black and white, granular, abstract, hand drawings, grainy, dmysticism, sacred symbology, blueprint",
      "output_format": "png",
      "guidance_scale": 7.5,
      "audio_smoothing": 0.8,
      "loop_interpolation": false,
      "variation_strength": 0.3,
      "audio_loudness_type": "peak",
      "interpolate_prompts": true,
      "interpolation_steps": 4
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

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

Run time and cost

This model costs approximately $0.32 to run on Replicate, or 3 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 L40S GPU hardware. Predictions typically complete within 6 minutes. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.