ComfyUI Integration

ComfyUI is the AI generation backend that Ordinary Animator uses to produce images and video. You don't need to use ComfyUI directly — Ordinary Animator submits jobs, monitors progress, and routes results to the right gallery automatically.

Two modes: Local and Comfy Cloud

Mode	How it works	Requirements
Local ComfyUI	Runs on your machine at localhost:8188. The browser can't talk to localhost directly, so the Chrome extension proxies requests.	Local ComfyUI install + Chrome extension installed and active
Comfy Cloud	Managed GPU infrastructure. Jobs run in the cloud. No local install needed.	Comfy Cloud subscription + API key configured in Settings

You configure which mode to use — and set the Comfy Cloud API key — on the ComfyUI Settings page.

Workflow JSON

Every ComfyUI job is driven by a workflow JSON file. The workflow describes the node graph: which models to load, what prompts to use, which nodes to connect. Ordinary Animator stores workflow JSON files in your project library or as platform-shared workflows.

Workflows can expose App Inputs — named parameters that Ordinary Animator fills in when submitting a job (prompts, images, dimensions, etc.). These are declared using the ComfyUI App builder and have Title Case names like "Positive Prompt" or "Input Image 1". Recipe steps map their configured Step Inputs to these App Inputs.

Certain infrastructure inputs are filled automatically and never shown as user-editable fields. Seed is one of these: every time you run a workflow, Ordinary Animator injects a fresh random seed, so repeated runs of the same workflow produce varied results. Filename Prefix is another: it routes output files to the correct media gallery slot.

How OA runs and monitors workflows

When a ComfyUI workflow step is run from a recipe, OA injects an OA Workflow Metadata node into the workflow before submission. This node contains YAML metadata that identifies the target media gallery — which project, episode, scene, shot, character, location, or prop the output belongs to — along with the output label.

OA then monitors for completion in one of two ways depending on how the workflow was run:

Queued jobs — the workflow is submitted to the ComfyUI queue (local or cloud). OA watches the queue continuously. When a job completes and its workflow contains an OA Workflow Metadata node, OA parses the YAML, fetches the output files, and saves them to the correct gallery. The generating workflow is stored alongside each file as provenance.

Interactive jobs — the user copies the workflow JSON and pastes it into ComfyUI directly, where they can adjust settings before running. OA polls the ComfyUI queue in the background. When it detects a completed job whose workflow contains an OA Workflow Metadata node, it applies the same routing — the output lands in the right gallery automatically, even though it was run manually.

This automatic routing means outputs always appear in the right place without any manual file management.

Input files

When a recipe step takes an image as input (e.g. a character reference image), OA downloads the file from cloud storage and uploads it to ComfyUI's input directory before submitting the job. This happens automatically.

The ComfyUI Queue page

The ComfyUI Queue page shows all active and recent jobs with their status, workflow name, runtime, and GPU seconds consumed. Click any row for a detail modal.

Legacy note

An older local integration model used a file-watcher service (comfyui-watcher) to detect output files on disk. This has been fully removed. All file operations now use the ComfyUI API and cloud storage.