Node packVerifiedExternal

comfyui-art-venture

Sourcegithub.com/sipherxyz/comfyui-art-venture

Maintainer@sipherxyzCgrade

Package profile

Status: Verified
Publisher: @sipherxyz
Source: GitHub
Stars: 366

README

ArtVenture Custom Nodes

A comprehensive set of custom nodes for ComfyUI, focusing on utilities for image processing, JSON manipulation, model operations and working with object via URLs

Image Nodes

LoadImageFromUrl

Loads images from URLs.

Inputs:

image: List of URLs or base64 image data, separated by new lines
keep_alpha_channel: Preserve alpha channel
output_mode: List or batch output. Use List if you have different resolutions.

load image from url

JSON Nodes

LoadJsonFromUrl

Loads JSON data from URLs.

Inputs:

url: JSON URL
print_to_console: Print JSON to console

LoadJsonFromText

Loads JSON data from text.

Inputs:

data: JSON text
print_to_console: Print JSON to console

Get<*>FromJson

Includes GetObjectFromJson, GetTextFromJson, GetFloatFromJson, GetIntFromJson, GetBoolFromJson.

Use key format key.[index].subkey.[sub_index] to access nested objects.

get data from json

Utility Nodes

StringToNumber

Converts strings to numbers.

Inputs:

string: Input string
rounding: Rounding method

TextRandomMultiline

Randomizes the order of lines in a multiline string.

Inputs:

text: Input text
amount: Number of lines to randomize
seed: Random seed

text random multiline

TextSwitchCase

Switch between multiple cases based on a condition.

Inputs:

switch_cases: Switch cases, separated by new lines
condition: Condition to switch on
default_value: Default value when no condition matches
delimiter: Delimiter between case and value, default is :

The switch_cases format is case<delimiter>value, where case is the condition to match and value is the value to return when the condition matches. You can have new lines in the value to return multiple lines.

text switch case

Inpainting Nodes

PrepareImageAndMaskForInpaint

Prepares images and masks for inpainting operations. It's to mimic the behavior of the inpainting in A1111.

Inputs:

image: Input image tensor
mask: Input mask tensor
mask_blur: Blur amount for mask (0-64)
inpaint_masked: Whether to inpaint only the masked regions, otherwise it will inpaint the whole image.
mask_padding: Padding around mask (0-256)
width: Manually set inpaint area width. Leave 0 default to the masked area plus padding. (0-2048)
height: Manually set inpaint area height. (0-2048)

Outputs:

inpaint_image: Processed image for inpainting
inpaint_mask: Processed mask
overlay_image: Preview overlay
crop_region: Crop coordinates (input of OverlayInpaintedImage)

inpaiting prepare

OverlayInpaintedImage

Overlays inpainted images with original images.

Inputs:

inpainted: Inpainted image
overlay_image: Original image
crop_region: Crop region coordinates

Outputs:

IMAGE: Final composited image

LaMaInpaint

Remove objects from images using LaMa model.

lama remove object

LLM Nodes

LLM API Config: Generic model settings (model, tokens, temperature).
NanoBanana API Config: Preset for Gemini 2.5 Flash Image (modalities/aspect ratio).
OpenAI API: Connect to OpenAI chat/completions.
OpenRouter API: Route to many providers via OpenRouter; supports text and images where available.
Gemini API: Google Gemini (text and image generation).
Claude API: Anthropic Claude messages.
AWS Bedrock Claude API: Claude via AWS