edenartlab/comfyui-workflows – Run with an API on Replicate

edenartlab / comfyui-workflows

Cold

Public
63.5K runs
A100 (80GB)

Run with an API

Playground API Examples README Versions

Input

mode

string

Shift + Return to add a new line

txt2vid, img2vid, vid2vid, upscale, txt2img, inpaint, makeitrad

Default: "txt2vid"

text_input

string

Shift + Return to add a new line

prompt

interpolation_texts

string

Shift + Return to add a new line

| separated list of prompts for txt2vid)

input_images

string

Shift + Return to add a new line

Input image(s) for various endpoints. Load-able from file, url, or base64 string, (urls separated by pipe symbol)

style_images

string

Shift + Return to add a new line

Input style image(s) (for IP_adapter) for various endpoints. Load-able from file, url, or base64 string, (urls separated by pipe symbol)

mask_images

string

Shift + Return to add a new line

Input mask image(s) for various endpoints. Load-able from file, url, or base64 string, (urls separated by pipe symbol)

input_video_path

string

Shift + Return to add a new line

For vid2vid. Load source video from file, url, or base64 string

steps

integer

(minimum: 10, maximum: 40)

Steps

Default: 25

width

integer

(minimum: 512, maximum: 3840)

Width

Default: 1280

height

integer

(minimum: 512, maximum: 3840)

Height

Default: 1280

n_frames

integer

(minimum: 16, maximum: 264)

Total number of frames (txt2vid, vid2vid, img2vid)

Default: 40

ip_adapter_weight

number

(minimum: 0, maximum: 2)

Strenght of the IP_adapter style

Default: 0.65

motion_scale

number

(minimum: 0, maximum: 2)

Motion scale (AnimateDiff)

Default: 1.1

n_samples

integer

(minimum: 1, maximum: 4)

batch size

Default: 1

control_method

string

Shape Control method (coarse usually gives nicer results, fine is more precise to the input video)

Default: "coarse"

controlnet_strength

number

(minimum: 0, maximum: 1.5)

Strength of controlnet guidance

Default: 0.85

denoise_strength

number

(minimum: 0, maximum: 1)

How much denoising to apply (1.0 = start from full noise, 0.0 = return input image)

Default: 1

blend_value

number

(minimum: 0, maximum: 1)

Blend factor (weight of the first image vs the second)

Default: 0.5

loop

boolean

Try to make a loopable video

Default: false

guidance_scale

number

(minimum: 1, maximum: 20)

Strength of text conditioning guidance

Default: 7.5

negative_prompt

string

Shift + Return to add a new line

nude, naked, text, watermark, low-quality, signature, padding, margins, white borders, padded border, moiré pattern, downsampling, aliasing, distorted, blurry, blur, jpeg artifacts, compression artifacts, poorly drawn, low-resolution, bad, grainy, error, bad-contrastnude, naked, text, watermark, low-quality, signature, padding, margins, white borders, padded border, moiré pattern, downsampling, aliasing, distorted, blurry, blur, jpeg artifacts, compression artifacts, poorly drawn, low-resolution, bad, grainy, error, bad-contrast

Negative Prompt

Default: "nude, naked, text, watermark, low-quality, signature, padding, margins, white borders, padded border, moiré pattern, downsampling, aliasing, distorted, blurry, blur, jpeg artifacts, compression artifacts, poorly drawn, low-resolution, bad, grainy, error, bad-contrast"

seed

integer

Sampling seed, leave Empty for Random

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

npx create-replicate --model=edenartlab/comfyui-workflows

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 edenartlab/comfyui-workflows using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "edenartlab/comfyui-workflows:1569f61c7d3700c604028c6f08f97aa109753191f9c3df8a4b007e561cab735d",
  {
    input: {
      loop: false,
      mode: "txt2vid",
      steps: 25,
      width: 1280,
      height: 1280,
      n_frames: 40,
      n_samples: 1,
      blend_value: 0.5,
      motion_scale: 1.1,
      control_method: "coarse",
      guidance_scale: 7.5,
      negative_prompt: "nude, naked, text, watermark, low-quality, signature, padding, margins, white borders, padded border, moiré pattern, downsampling, aliasing, distorted, blurry, blur, jpeg artifacts, compression artifacts, poorly drawn, low-resolution, bad, grainy, error, bad-contrast",
      denoise_strength: 1,
      ip_adapter_weight: 0.65,
      controlnet_strength: 0.85
    }
  }
);
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 edenartlab/comfyui-workflows using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "edenartlab/comfyui-workflows:1569f61c7d3700c604028c6f08f97aa109753191f9c3df8a4b007e561cab735d",
    input={
        "loop": False,
        "mode": "txt2vid",
        "steps": 25,
        "width": 1280,
        "height": 1280,
        "n_frames": 40,
        "n_samples": 1,
        "blend_value": 0.5,
        "motion_scale": 1.1,
        "control_method": "coarse",
        "guidance_scale": 7.5,
        "negative_prompt": "nude, naked, text, watermark, low-quality, signature, padding, margins, white borders, padded border, moiré pattern, downsampling, aliasing, distorted, blurry, blur, jpeg artifacts, compression artifacts, poorly drawn, low-resolution, bad, grainy, error, bad-contrast",
        "denoise_strength": 1,
        "ip_adapter_weight": 0.65,
        "controlnet_strength": 0.85
    }
)

# The edenartlab/comfyui-workflows model can stream output as it's running.
# The predict method returns an iterator, and you can iterate over that output.
for item in output:
    # https://replicate.com/edenartlab/comfyui-workflows/api#output-schema
    print(item)

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 edenartlab/comfyui-workflows 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": "1569f61c7d3700c604028c6f08f97aa109753191f9c3df8a4b007e561cab735d",
    "input": {
      "loop": false,
      "mode": "txt2vid",
      "steps": 25,
      "width": 1280,
      "height": 1280,
      "n_frames": 40,
      "n_samples": 1,
      "blend_value": 0.5,
      "motion_scale": 1.1,
      "control_method": "coarse",
      "guidance_scale": 7.5,
      "negative_prompt": "nude, naked, text, watermark, low-quality, signature, padding, margins, white borders, padded border, moiré pattern, downsampling, aliasing, distorted, blurry, blur, jpeg artifacts, compression artifacts, poorly drawn, low-resolution, bad, grainy, error, bad-contrast",
      "denoise_strength": 1,
      "ip_adapter_weight": 0.65,
      "controlnet_strength": 0.85
    }
  }' \
  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 runs on Nvidia A100 (80GB) GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

This model doesn't have a readme.