edenartlab / comfyui-workflows

  • Public
  • 61.7K runs

Run edenartlab/comfyui-workflows with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

Input schema

The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.

Field Type Default value Description
mode
string
txt2vid
txt2vid, img2vid, vid2vid, upscale, txt2img, inpaint, makeitrad
text_input
string
prompt
interpolation_texts
string
| separated list of prompts for txt2vid)
input_images
string
Input image(s) for various endpoints. Load-able from file, url, or base64 string, (urls separated by pipe symbol)
style_images
string
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
Input mask image(s) for various endpoints. Load-able from file, url, or base64 string, (urls separated by pipe symbol)
input_video_path
string
For vid2vid. Load source video from file, url, or base64 string
steps
integer
25

Min: 10

Max: 40

Steps
width
integer
1280

Min: 512

Max: 3840

Width
height
integer
1280

Min: 512

Max: 3840

Height
n_frames
integer
40

Min: 16

Max: 264

Total number of frames (txt2vid, vid2vid, img2vid)
ip_adapter_weight
number
0.65

Max: 2

Strenght of the IP_adapter style
motion_scale
number
1.1

Max: 2

Motion scale (AnimateDiff)
n_samples
integer
1

Min: 1

Max: 4

batch size
control_method
string (enum)
coarse

Options:

coarse, fine

Shape Control method (coarse usually gives nicer results, fine is more precise to the input video)
controlnet_strength
number
0.85

Max: 1.5

Strength of controlnet guidance
denoise_strength
number
1

Max: 1

How much denoising to apply (1.0 = start from full noise, 0.0 = return input image)
blend_value
number
0.5

Max: 1

Blend factor (weight of the first image vs the second)
loop
boolean
False
Try to make a loopable video
guidance_scale
number
7.5

Min: 1

Max: 20

Strength of text conditioning guidance
negative_prompt
string
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
Negative Prompt
seed
integer
Sampling seed, leave Empty for Random

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema
{
  "type": "array",
  "items": {
    "type": "object",
    "title": "CogOutput",
    "required": [
      "files"
    ],
    "properties": {
      "name": {
        "type": "string",
        "title": "Name"
      },
      "files": {
        "type": "array",
        "items": {
          "type": "string",
          "format": "uri"
        },
        "title": "Files"
      },
      "isFinal": {
        "type": "boolean",
        "title": "Isfinal",
        "default": false
      },
      "progress": {
        "type": "number",
        "title": "Progress"
      },
      "attributes": {
        "type": "object",
        "title": "Attributes"
      },
      "thumbnails": {
        "type": "array",
        "items": {
          "type": "string",
          "format": "uri"
        },
        "title": "Thumbnails"
      }
    }
  },
  "title": "Output",
  "x-cog-array-type": "iterator"
}