comfyui-node-datatypes

Map ComfyUI Python data types to io.Data types for node schemas.

265|28|Updated Mar 5, 2026

Search Tags:#models #tensor #data-types #comfyui #conditioning #latents

Ready to run

npx skills add https://github.com/jtydhr88/comfyui-custom-node-skills --skill comfyui-node-datatypes

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: comfyui-node-datatypes
Source: https://github.com/jtydhr88/comfyui-custom-node-skills/tree/main/plugins/comfyui-custom-nodes/skills/comfyui-node-datatypes
Command: npx skills add https://github.com/jtydhr88/comfyui-custom-node-skills --skill comfyui-node-datatypes

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python, torch.

What problem does it solve?

ComfyUI data type definitions and usage guide help developers correctly declare and handle inputs, outputs, and model interactions across tensors, images, latents, conditioning, and other data formats.

Core Features & Use Cases

Reference tables for tensor/data types and model types (IMAGE, LATENT, MASK, CONDITIONING, MODEL, CLIP, VAE, AUDIO, VIDEO, 3D, and more).
Guidance on applying types in node schemas and execution logic, with examples for image pipelines, latent processing, conditioning, and 3D workflows.
Real-world scenarios: building a node that ingests an image and outputs a latent, or a node that converts latents to images.

Quick Start

Define your ComfyUI node schemas using io.Image, io.Latent, io.Model, and related IO types, then implement the execute method to consume and produce these types.

Frequently Asked Questions about comfyui-node-datatypes

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I map ComfyUI data types like IMAGE and LATENT in custom node inputs?▼

To map ComfyUI data types, define node schemas using IO types such as io.Image and io.Latent. This creates required mappings between python types and io.Data types to ensure consistent tensor handling and node behavior.

What ComfyUI tensor formats are supported for video and audio workflows?▼

ComfyUI tensor formats support image, latent, conditioning, mask, audio, video, and 3D workflows. Reference tables document these data type definitions to ensure correct execution logic for both V3 and V1 APIs.

How do I build a ComfyUI node that converts latents to images?▼

To convert latents to images, define your ComfyUI node schema using io.Latent for input and io.Image for output. Implement the execute method to consume and produce these defined tensor types.

Does ComfyUI V3 API support conditioning and model type definitions?▼

Yes, the ComfyUI V3 API supports conditioning and model type definitions. It provides reference tables for MODEL, CLIP, VAE, and CONDITIONING types to handle tensor interactions across both V3 and V1 APIs.

Why does my ComfyUI custom node fail when passing MASK tensors to execute?▼

Passing MASK tensors fails when node schemas lack correct io.Data type mappings. You must properly declare MASK inputs and outputs in the schema to ensure consistent tensor handling during model interactions.