Concepts
The mental models behind Ordinary Animator -- understand these and everything else makes sense.
These pages explain how Ordinary Animator works at a model level -- not step-by-step instructions, but the underlying ideas that make the features coherent. They read best in order, in five groups.
The foundations -- the process and the data it runs on:
| Concept | What it explains |
|---|---|
| The Production Pipeline | The ten phases from world-building to release, the episode plan, and how the app maps to them |
| Entities & the Data Model | The project -> episode -> scene -> shot hierarchy, asset entities, properties, and looks |
Making media -- the generation stack, from the three building blocks down to the engine:
| Concept | What it explains |
|---|---|
| Models, Workflows & Recipes | The three building blocks that turn an entity into media, how they nest, and how each gets made |
| Experiments | A question with an answer -- try models on your own artwork without filling up a working gallery |
| The Media Gallery | The pin-board for images, video, and audio, and the Recipe panel where you choose an operation, fill it in and run it |
| From Storyboard to Video | How a shot becomes a clip -- storyboards, media tagged by purpose, and scene-level review |
| ComfyUI Integration | What ComfyUI is, local vs Comfy Cloud, the queue model, and how workflows run |
| OA Workflow Metadata | The note that tells the platform what your workflow is -- every field, and how to add one to a workflow that has none |
| App Inputs and Outputs | What the platform is allowed to fill in when it runs your workflow, what to call each one, and which are filled in for you |
Choosing models -- how to read a model name and decide where it runs:
| Concept | What it explains |
|---|---|
| Choosing the right model | Picking a model for your goal, your budget, and your hardware -- and how the assistant helps |
| Visual styles | What a scene means visually -- the recipes it recommends, in order, each with an art style per model -- so a scene can look different from the rest of an episode |
| Models, builds and LoRAs | What a model's name says, why one model comes in several builds, and where the LoRAs went |
| Model versions and quantization | Why one model comes in several files (fp16, fp8, GGUF) and which fits your graphics card |
| Comfy Cloud or local? | Pay per render with nothing to install, or run on your own hardware for free |
Sound -- the dialogue pipeline:
| Concept | What it explains |
|---|---|
| Audio & Voice Pipeline | How dialogue lines become audio: TTS engines, voice changer, recording, and merged tracks |
| Building Dialogue from Operations | The operations behind dialogue audio -- text to speech, record, voice changer, assemble, trim |
The AI layer and reference:
| Concept | What it explains |
|---|---|
| The AI Assistant | What the Assistant can do, typing and voice typing, and the skills it reaches for |
| Glossary | Our terminology -- our word for each thing, and the industry term it maps to |