AI Art Engine 中文
Menu

Docs · Operations

Manual

Covers the main screens and components of the current release (5.0): project and model configuration, AI chat & MCP setup, one-click workflows, the short-drama agent pipeline model setup, One-Click Workflow, the short-drama Agent pipeline, host assets, the node graph and task queue, comic pages and the ad variant matrix, 3D model generation and the director stage, shots and episodes, the final timeline, and asset packages. Wording follows the in-app UI — switch the app to English under Settings → General → Language. Video walkthroughs are on Bilibili.

First time here? Follow the quickstart and ship your first film in 5 minutes Learn a few concepts What host assets, anchor images and world elements mean Short drama pipeline Episode pipeline: storyboards, grids, review and video Something broken? Diagnose by symptom: balance, wiring, consistency

1. Overview & preparation

AIArtEngine is a professional AI creation tool for short drama, advertising and finished films. Projects and media live in a local directory you choose; text / image / video / audio generation runs through the model providers you configure (OpenRouter, OpenAI, DeepSeek, Zhipu, Kimi, xAI, Google, vLLM, Ollama, LM Studio, Volcengine Ark, Kling, MiniMax, Tongyi Qianwen, ModelScope, ComfyUI, MagicRouter, …), and 3D model generation supports Meshy, Tripo, Rodin (Hyper3D), Luma AI and Lux3D. Use One-Click Workflow to turn a template or a plain-language request into a reusable host asset, then drag it onto the canvas to keep building.

First-time setup

  1. Install the package for your platform from the download page or GitHub Releases.
  2. After launching, open Settings, add a model provider with its key, then fetch and tick the models you want.
  3. (Optional) Under Object storage configure Volcengine TOS / Alibaba Cloud OSS / Tencent Cloud COS (only one can be enabled at a time) so large files such as reference videos can be exposed as URLs.
  4. Back on the home page, create a project and enter the workspace; try “One-Click Workflow” in the top bar, or create a script / shot the traditional way.
There is no traditional menu bar. The top-left logo returns to the home page; “Settings” opens the settings panel. Close the settings by clicking the empty overlay or “Back”.

2. Core concepts

Spend two minutes on the words below and every screen afterwards will make sense. Data in this app is organized as project → shot / episode → node graph → asset: the project is the container, the node graph is the workshop, and assets are what comes out of it.

Project

Everything that belongs to one piece of work, stored in a local directory you pick yourself, with project.json at its root. Media never leaves your machine — copy the whole folder to move to another computer.

See §3 Home & projects

Asset

The umbrella term for every output and piece of media in a project: scripts, beat tables, storyboard images, anchor images, video, audio, 3D models and host assets. Browse and drag them all from the asset library.

See §6 Asset library

Host asset

A reusable component produced by One-Click Workflow. The outside exposes only boundary inputs / outputs, while double-clicking dives into the full inner node graph for fine-tuning. Build once, reuse across projects.

See §7 One-Click Workflow

Node graph

The canvas where nodes and links describe “input → generate → output”. It is the shared foundation of scripts, shots, canvases, the director stage and host assets.

See §8 Node graph

Port

A node's inlet or outlet. Ports strictly distinguish singular from plural: image / images, video / videos, text / texts. Different types never connect, and singular can't go into plural. Round ports are usually a single out; square ports are lists (out-all).

See §8.1 Add and connect

Episode / shot / beat

An episode is made of several shots; a script is first split into a beat breakdown table, then landed onto concrete shots. These use the dedicated port types world / worldEntities / beat, which must not be mixed with plain text.

See §9 Script & shots

Anchor image

A single reference image split out of a 9-grid / 4-grid sheet, cell by cell. It locks a character's face, outfit and setting so every later storyboard stays consistent — this is the key to keeping a short drama from “changing faces”.

See the Short-Video Guide

World element

A reusable setting entry: character, scene, prop. Attached to an episode and shared by every shot, so you don't re-describe the same thing in every setup — another way to keep consistency.

See §11 Canvas & world elements

Director stage

A 3D stage: place models, light the scene and frame the camera, then capture blocking shots or record motion video, which come out of the two square ports out-shots / out-actions.

See §12 Director stage

Final timeline

A multi-track editing panel: drag node outputs or imported media onto tracks, arrange the order, line up audio, then preview and export the finished film.

See §10 Final timeline

Asset package .aipackage

A format that packages assets together with their dependencies for export, so you can migrate to another machine or share with collaborators — importing restores everything as it was.

See §13 Asset packages

2.1 How a short drama actually runs

With the concepts above in place, the full data flow of the short-drama pipeline reads:

  1. Script → broken down by a text model into a beat breakdown table (beat).
  2. Beat → 9-grid storyboard table: one node generates a 3×3 sheet, then 9 anchor images are split out cell by cell and upscaled.
  3. Anchor images → 4-grid motion storyboard table: 2×2 sheets per group, split into 36 motion cells and upscaled.
  4. Motion cells → motion prompt table (36 entries) → 36 motion videos.
  5. Four director review nodes, review1~review4, sit along the way; anything below standard can be sent back for a re-run.
  6. Videos → arranged on the final timeline → export the finished film.
This flow ships as the “short-drama storyboard” template: pick it in One-Click Workflow and all of the above is generated for you — no manual wiring. See the Short-Video Guide and the Quickstart for the full walkthrough.

3. Home & projects

Create a project

  1. Click New Project.
  2. Fill in the project name.
  3. Click Browse to choose the storage directory.
  4. Click Create to enter the workspace.

Open a project

  • Click Open Project and pick project.json inside the project directory.
  • Or click a path in the Recent projects list.

Recent projects

  • The list shows project paths you opened recently.
  • The × on the right means “remove from the recent list” — it does not delete the project files on disk.
This release has no in-app “Delete project” action. To remove a project entirely, delete its folder in your file manager.

4. Settings

Open Settings from the home page or the workspace top bar. Changes are saved automatically.

4.1 General

  • Theme: dark / light.
  • Language: 中文 (Chinese) / English.
  • Auto save: can be enabled, with an interval in seconds.
  • About & updates: view the version and check for updates (see below).

4.2 Models

  1. Click Add model provider. Options include:
    • OpenRouter: text / image / video (aggregated catalog, single API Key).
    • OpenAI: text (GPT family) / images (gpt-image-1 / gpt-image-2); requires network access to api.openai.com and a non-mainland account. Text-to-image uses /images/generations, reference-image editing uses /images/edits (1 image max).
    • DeepSeek: text only (deepseek-chat / deepseek-reasoner, OpenAI compatible).
    • Zhipu: GLM text (/chat/completions) + CogView text-to-image (glm-image / cogview-4 / cogview-3-flash, /images/generations).
    • Kimi (Moonshot): text (kimi-k2 series / moonshot-v1 series, OpenAI compatible, default Base URL https://api.moonshot.cn/v1).
    • xAI (Grok): text (grok-* chat, OpenAI compatible, default Base URL https://api.x.ai/v1) + Grok Imagine text-to-image (/images/generations, JSON body, supports aspect_ratio) + Grok Imagine Video async video (/videos/generations submitted then polled at GET /videos/{request_id}; 480p / 720p, 5–15s, first-frame image-to-video).
    • Google (Gemini): text (gemini-* chat) + Nano Banana text-to-image / image-to-image (/images/generations, JSON body, supports aspect_ratio / resolution / n / response_format and image reference fields) + Veo 3.1 async video (/videos submitted then polled at GET /videos/{id}; 720p–4K, 4–8s, first-frame image-to-video) — all through the official OpenAI compatibility layer (default Base URL https://generativelanguage.googleapis.com/v1beta/openai).
    • vLLM: local OpenAI-compatible service (default http://localhost:8000/v1), no API Key required; deploying vLLM-Omni diffusion models (e.g. Wan2.2 T2V / I2V) enables video generation (async jobs on /v1/videos, can carry a first-frame image).
    • Ollama: local OpenAI-compatible endpoint (default http://localhost:11434/v1), no API Key required.
    • LM Studio: local OpenAI-compatible endpoint (default http://localhost:1234/v1), no API Key required.
    • Volcengine Ark: text / Seedream images / Seedance video use the Ark API Key; sound design goes through Doubao Speech openspeech (a Speech console API Key, which can differ from the Ark Key) plus a manually entered speaker_id. Video models include Seedance 2.5 (doubao-seedance-2-5-260628: up to 30s per request, 50 omni references, timestamp-level segment editing) plus Seedance 2.0 / 2.0 Fast.
    • Kling: images / video (API Key).
    • MiniMax: text / image / video / voice design (same API Key; default Base URL https://api.minimaxi.com).
    • Tongyi Qianwen: text (compatible mode) / Wanxiang images / Wanxiang video (including HappyHorse, Wan 3.0-Video, …; Bailian API Key). Wan 3.0-Video supports 30s per request with 10 image + 5 video + 5 audio references; it is in public / invite beta, so use the Model ID from the Bailian console.
    • ModelScope: text / text-to-image (ModelScope access token, e.g. ms-…).
    • ComfyUI: images / video / audio via API 2 (POST /api/v2/jobs). The model id is the API-format workflow name in userdata (not a checkpoint), and the model list is pulled from the service dynamically. Video workflows support multimodal references (r2v), video / audio reference injection and first/last frame injection (first_frame / last_frame), with a 15s duration cap. The default local Base URL is http://127.0.0.1:8189 (install comfy-api-proxy first — don't connect to 8188 directly); for the cloud enter https://cloud.comfy.org plus a key. The key can be empty locally. Full steps: ComfyUI guide.
    • MagicRouter: multi-provider aggregation gateway (OpenAI compatible), text / image / video; requires an API Key starting with mr-, default Base URL https://api.magicrouter.ai/v1, model catalog from /models/live, video submitted async then polled.
    • Meshy: text-to-3D / image-to-3D (including multi-image to 3D; API Key; default Base URL https://api.meshy.ai).
    • Tripo: text-to-3D / image-to-3D (API Key; default Base URL https://api.tripo3d.ai).
    • Rodin (Hyper3D): text-to-3D / image-to-3D (API Key; default Base URL https://api.hyper3d.com/api/v2).
    • Luma AI: text-to-3D / image-to-3D (API Key; default Base URL https://api.lumalabs.ai/dream-machine/v1).
    • Lux3D: text-to-3D / image-to-3D / multi-image to 3D (API Key; G1 / G1-Turbo; default Base URL https://api.aholo3d.cn).
  2. After selecting or expanding a provider, the settings page links to its key request page (you can also open these directly):
  3. Enter a display name, Base URL and key (which can be shown or hidden).
  4. After enabling the provider, click Fetch models (Kling / some MiniMax modalities / Bailian image & video / OpenAI and Zhipu images use local static catalogs; local services such as vLLM / Ollama / LM Studio / ComfyUI need no key and are fetched directly).
  5. Use filters plus select-all / clear to tick the models you want; model IDs can also be added manually.
  6. Configure per modality: text / image / video / audio / 3D model (the Ark audio tab also links the speech console and asks for a manual speaker_id; Kling has only image and video tabs; MiniMax supports text / image / video / voice design; OpenAI supports text and image; DeepSeek is text only; Kimi (Moonshot) is text only; xAI (Grok) supports text / image / video with async polling for video; Google (Gemini) supports text / Nano Banana images / Veo 3.1 video with async polling; Zhipu supports GLM text and CogView images; vLLM supports text and video (Wan T2V / I2V); Ollama / LM Studio are text only, though multimodal understanding can pass images into text nodes; ModelScope supports text and image with async text-to-image jobs; ComfyUI supports image / video / audio and has no text tab; MagicRouter supports text / image / video; Meshy / Tripo / Rodin (Hyper3D) / Luma AI / Lux3D only expose a 3D model tab).
  7. Set the default generation model and default voice if needed. Provider cards can be collapsed to save space.
API Keys are stored in a local settings file (Windows example: %APPDATA%\AIArtEngine\aiartengine-settings.json) and are never uploaded to any official server.

4.3 Object storage

Used to upload local files such as reference videos into publicly reachable URLs (signed links are used for private buckets).

  • Add object storage → pick one:
    • Volcengine TOS: AccessKey / SecretKey, Region, Endpoint, Bucket.
    • Alibaba Cloud OSS: AccessKey / SecretKey, Region, Endpoint, Bucket.
    • Tencent Cloud COS: SecretId / SecretKey, Region, Bucket (usually BucketName-APPID).
  • Key request pages (also linked inside settings):
  • A public access domain (CDN / custom domain) is optional; when it's empty, signed URLs are used (valid for about 24 hours).
  • Only one object storage can be enabled at a time — enabling one automatically turns off the others. Cards can be collapsed.

4.4 Extensions

In-app extensions run on Cordis (ctx.editor.*) and can contribute nodes, cards, inspectors, skills and executor overrides; see GRAPH_PLUGINS.md in the repository for development notes. The settings page only lists declarative extensions under the plugins folder in the user data directory. Arbitrary external scripts are never executed — only declared extension information is shown. Official installers don't load the “graph plugin sample” demo.

4.5 MCP tool server

The app embeds an MCP tool server for external AI agents such as Claude Code / Codex (and the built-in AI chat panel) — plan & commit workflows, run generation, read/write assets and node graphs. See the MCP setup guide for full steps.

  • Start / restart: the settings page shows run state and port; the default port is 43110, falling back through 43110–43119 when busy. Changing the port or clicking “Restart” brings the server back on the new port.
  • Token: view / copy / edit are supported; it persists across restarts, so configure once. Click “Reset token” if you suspect a leak — the old token is invalidated immediately and clients must re-register with the new one.
  • Connect command: one-click copy of the claude mcp add --transport http … command; run it in a terminal to register the app as a Claude Code MCP server (HTTP direct, no Node.js needed).
The tool server only listens on 127.0.0.1 loopback and every request needs a Bearer token; file access is confined to the project root; every tool call is appended to the audit log <userData>/logs/mcp-audit.jsonl (5 MB rolling).

5. Workspace

Opening a project takes you to the workspace (named “Workspace” in the app navigation). The interface is a dockable multi-panel layout.

5.1 Top bar

  • Unsaved changes show * next to the title; press Ctrl+S to save.
  • ↶ / ↷: undo / redo (also available as shortcuts).
  • One-Click Workflow: generate a reusable host asset from a preset or AI planning (see §7).
  • Episode Pipeline: open the short-drama Agent pipeline window to work through 9-grid, 4-grid, director review and video generation (see §7.5).
  • Task list and Run log: background queue and model call logs.
  • Layout: switch the default layout, save the current layout, export / import a layout .json, delete custom layouts.

Tip: drag a tab to dock it in another area; right-click a tab to float it, detach it into a new window, or close related tabs. Key panels can't be closed while nodes are running.

5.2 The four panels

Panel Purpose
Tools Narrow left column with shortcuts for creating asset drafts.
AI chat Opened via the “◈” button at the bottom of the left column; an in-app AI assistant that can call MCP tools in conversation (see §5.5).
Workspace The central editor; the empty state shows the recommended flow and recent assets, and opened assets become tabs.
Assets Browse and manage the project asset library.
Parameters Inspector panel for the current selection.

5.3 Left toolbar: create assets

Click an icon to create a draft asset, then press Ctrl+S after editing to write it to disk. You can create:

  • Free canvas · host asset · script · world elements · shot · director stage · image · video · audio

Recommended flow in an empty workspace: script → shot → node generation; you can also create a script, shot or director stage directly, or double-click a recent asset to open it.

5.4 Right rail: assets / parameters

The far right of the workspace is a Rider-style vertical rail; the Assets and Parameters panels can be expanded or collapsed independently (a collapsed panel takes no width from the center layout).

  • Click a rail button to toggle the matching side panel.
  • You can drag “Assets” above or below “Parameters”; drop previews only appear in the top / bottom halves (half-screen left / right previews are disabled to avoid leftover grey frames).
  • The layout menu saves the expanded geometry, while collapse preferences are remembered separately — a collapsed state is never written as a zero-width grey hole.

5.5 AI chat panel

The ◈ AI chat button at the bottom of the left column opens the in-app AI assistant. It runs the DeepSeek Harness (dsh) agent runtime and can call the app’s built-in MCP tool server exactly like an external agent — in other words, drive generation and project operations right from the chat window.

  • @-reference assets: type @ to open an asset picker and inline project images / videos / audio / 3D models into your instruction (the composer shows thumbnail previews). dsh parses the @path references directly.
  • Call generation tools: ask “generate a title image from @bg.png into the project” — the assistant calls MCP tools like generate_image, and tool progress is shown as live cards (running / done / failed).
  • Model picker: at the bottom of the panel you can pick any configured text model with a key (not limited to DeepSeek official); the choice is remembered.
  • Multi-session: the toolbar above the composer creates / switches / deletes sessions; message history persists locally.
  • Cancel & status: you can stop a running turn; dsh status lines and tool activity stream back into the panel in real time.
Prerequisites: AI chat bundles both the Node.js runtime and the dsh runtime — ready to use out of the box, no system Node.js required (only exotic environments fall back to on-the-fly downloads). You do need at least one enabled text model with a key; without an open project only pure conversation is available.

5.6 Skills

The chat agent ships with a set of creation skills (derived from the app’s built-in storyboard / director capabilities, injected automatically on each conversation); you can also add your own skills under Settings → Custom skills to give the assistant a tailored way of working.

  • Built-in skills: storyboard / animation (9-grid storyboard table, beat breakdown table, motion prompt table, 4-grid motion storyboard table, …), director review (storyboard / beat / motion prompts), and system creation (script, image-from-prompt, image / video generation, voice, emotion, lighting, multi-angle, upscale, redraw, erase, HD enhance, UI image, UI split, world extraction, beat split, beat unit generation, plan, portrait texture, prompt optimization). These are managed automatically — please don’t edit them.
  • Custom skills: under Settings → Custom skills click “Open folder” and drop in a .md file in dsh SKILL.md format (frontmatter name / description + Markdown body; kebab-case filename such as my-skill.md). It takes effect on the next conversation. “Create sample template” gives you a ready-to-use reference.
  • How skills work: the skill catalog is injected into the conversation context as <available_skills>; when the agent judges a task matches, it loads the skill file on demand as instructions — the skill defines the process and conventions (how to do it), while MCP tools do the actual work (generate images, run workflows).
  • Node-graph nodes use the same skill system to define their behavior; API run logs annotate the skill used by each node.
Skills vs tools: skills are the “job manual”, tools are the “hands”. Say “use the storyboard skill to split this script into a 9-grid storyboard table” — the skill provides the professional workflow (beat → framing → motion → prompt) and tools execute the generation.

6. Asset library

Browse and filter

  • Refresh next to the “Assets” title; search and type filters are supported.
  • The slider at the bottom switches between list view and icon view.
  • A breadcrumb shows the path, e.g. Assets > …
  • Marquee multi-select is supported; you can drag images / videos / audio / models / .aipackage in from your system.

Right-click empty space or a folder

  • Create assets of any type, create a folder.
  • Import asset package / Export asset package.
  • Folders additionally offer: reimport, rename, delete folder (contents move up), delete folder with contents.

Right-click an asset

  • Open editor · reveal in file manager · copy original file.
  • Reimport · export asset package · rename · find references · delete.

Shortcuts with the asset library focused

  • Delete / Backspace: delete the selection.
  • Ctrl+A: select all.
  • Ctrl+C: copy-original-file related action.

7. One-Click Workflow

“One-Click Workflow” uses a preset template or AI planning to produce a reusable host asset (containing a complete node graph plus boundary I/O). Once created, drag it onto any canvas, feed it inputs and take its outputs like a component.

7.1 How to open

  1. Open any project to enter the workspace.
  2. Click One-Click Workflow in the top bar.
You need at least one working text model for AI planning; a pure template preview doesn't depend on AI.

7.2 Presets and description

  • Preset templates (covering the main capability nodes by industry): game user acquisition, game UI, character design, storyboard-to-film, product ads, e-commerce livestream, game 3D assets, comic publishing, knowledge talking-head, 3D blockout previz, short-drama storyboard, custom, and more. Presets with a fixed topology can be previewed directly with “Preview template”. “Game UI” builds a full chain of planning document → UI screen breakdown → UI screen generation, where UI generation can dive into the inner graph to render screen by screen, with a global style reference keeping the look consistent.
  • Industry templates and capability nodes: “E-commerce livestream” chains ad variant matrix → media rework → media QC plus layer separation; “Game 3D assets” chains 3D model generation → director stage → blocking shots → showcase video; “Comic publishing” chains storyboard images ×3 → comic page (panels / balloons / transparent-background export); “Knowledge talking-head” chains script → voice-over + talking-head video → lip sync; “3D blockout previz” chains panorama reference → director stage AI blockout → blocking shots → previz film. Each template's note node documents its step-by-step usage.
  • Workflow description: describe your goal in plain language (e.g. “script → storyboard images → vertical short video”); you can pick a preset first and then edit the description.
  • Models: the text model drives AI planning; the default image / video models are written into the initial parameters of generation nodes.

7.3 Preview → create

  1. Click Preview template (fixed presets) or Generate preview with AI (needs a text model; shortcut Ctrl+Enter / ⌘+Enter).
  2. Inspect the nodes and link topology in the preview area; open the run log to watch the model's planning process.
  3. Confirm with Create workflow, then choose a save directory and name.
  4. The new host asset appears in the asset library; drag it onto a canvas to use it.
What gets created is a host asset: the outer layer exposes boundary inputs / outputs, and the inner graph can be dived into for editing. Multiple same-type outlets (e.g. several character sheets) each keep their own independent boundary output.

7.4 Using it after creation

  • Drag it from the asset library onto the canvas → connect upstream text / images to the host inputs.
  • Double-click or Dive into the inner graph to fine-tune nodes, models and prompts.
  • Select a boundary output or the host node and use “Add to tasks” to run the whole inner chain; it can run in parallel with other chains (see §8.3).

7.5 Episode pipeline: the Agent window

Episode pipeline window: beat breakdown, grid storyboards and director review
Episode pipeline: beat breakdown, 9-grid / 4-grid storyboards and director review.

After creating a host asset from the “Short-drama storyboard (Agent pipeline)” template, click “Episode Pipeline” in the top toolbar to open a dedicated flow window and finish storyboards, tiling, review and video generation in one place. See the Short-Video Guide for the full walkthrough.

  • Three columns: beat breakdown (left), 9-grid storyboard table (center), 4-grid detail (right); drag the dividers to resize each column.
  • 9-grid tiling: click the grid icon to generate the entire 3×3 sheet at once and split out all 9 anchor images; regeneration and director review are supported.
  • 4-grid: click the 2×2 grid icon to generate the current group's sheet; the right side shows the motion prompt and lets you generate / preview the current cell's motion video.
  • Director review: the review button lights up only after that stage's “Regenerate” has written results back. Review defaults to PASS and only FAILs on blocking issues; FAIL reasons are written back and appended to that stage's re-run.
  • Cascading invalidation: after a stage is regenerated, its downstream tiling / extraction / upscale / video are invalidated and show “Not generated”; clicking generate again re-runs the whole chain from the latest text, so new text never pairs with old images.
  • Node inspector: with a “grid select / motion cell select” node selected, edit the cell (1~9) or group × cell (1~9 × 1~4) parameters on the right.

8. Node graph

Node graph: generation chains built from node cards and links
Node graph: generation chains, asset preview and task execution.

The node graph is the core orchestration surface. In scripts, shots, canvases, the director stage, host assets and similar scenes you wire nodes together into “input → generate → output” chains.

8.1 Add and connect

  1. Right-click empty canvas space, or press Space, then choose “Add node”.
  2. Drag a link out from a port; after releasing you can “select a node and connect”.
  3. Rewire: hold and drag an existing link (whichever end you grab is the one that changes), or drag out from an already connected input port onto another compatible port; release over empty space to disconnect. After marquee or multi-selecting links (Shift / Ctrl click), dragging one of them rewires several at once; dragging from an input port carries all of that port's incoming edges.
  4. Drag an asset from the asset library onto the canvas to create a reference quickly.
  5. Select a node or edge and press Delete / Backspace to remove it.

Image / video / audio / script gallery generation nodes have two outputs: out (the currently selected single item, auto-connected by default) and out-all (the whole history, a square port). Each successful run selects the newest item automatically; click a history entry in the Inspector to change the current out.

Director stage edit nodes use two square outputs: out-shots (blocking shots, images) and out-actions (motion captures, videos). Legacy out / out-all links migrate to out-shots on load.

Structured directory ports use the dedicated types world / worldEntities / beat (shown as world elements / world element entities / shot) — don't mix them with plain text.

Port types must match: singular and plural don't interoperate. image can't go into images, and the same applies to video / voice / text. Select image / video / audio / text nodes accept list ports only: feed them from an upstream out-all (or the director stage's out-shots / out-actions); the default round out won't connect. A script node's text also can't go straight into “Select text”.

Generation nodes support locking: when enabled the model call is skipped and the gallery or previous output is reused (toggle it with the lock icon on the node card or in the Inspector).

8.2 Toolbar and canvas interaction

  • Select / pan · fit view · grid and snapping · align / distribute · auto layout.
  • Link style: curve / orthogonal / hidden (the preference is remembered).
  • Minimap: bottom-left overview with a viewport box; it can also be toggled when the layout bar is collapsed.
  • Wheel zoom runs roughly 1%–1000%; clicking the zoom percentage resets related view habits.
  • Execute / stop / add to tasks.
  • Project globals: right-click empty graph space and open “Global parameters” — project name, visual style (up to 4 style reference images, picked from the default style library or uploaded, including a “UI style” category), a global random seed (image / video generation nodes follow it by default and can opt out individually, which makes runs reproducible) and the generation cache root (results are written to Cache/Images, Cache/Videos, etc., and aren't registered in the asset library automatically).
  • Prompt editor reference preview: hovering a referenced node's thumbnail pops a preview — images are shown size-limited and text shows the opening paragraphs (sidecar txt / md content such as scripts is read automatically).

Image previews on node cards and in the Inspector are shown in full with letterboxing, so they're never cropped by a different aspect ratio.

8.3 Execution and the task queue

Method Description
Toolbar “Execute” With a selection it runs the selected nodes and their upstream; with none, it asks for confirmation before “Execute all nodes”.
Hold C Opens the execution ring: run current / re-run / skip upstream / force upstream / add to tasks / stop.
Node right-click Run current · re-run · stop.
Task list Background workflow queue. Selecting an output terminal then “Add to tasks” runs only that sink's upstream; with no output selected it runs the union of every output chain in the graph.
Shared upstream nodes cook only once: when several output chains on the same canvas are queued separately, each task keeps its own progress; tasks queued later wait for earlier ones on overlapping upstream nodes and skip shared nodes already marked done. The sinks themselves still run individually. To force a shared node to re-run, clear its run state or unlock it before queueing.

Group: Ctrl+Shift+G; ungroup: Ctrl+Shift+U.

8.4 Fault-tolerant run mode

Single-node debugging stays strict: a failing node stops the run immediately and reports the error, which is best for isolating problems. But long chains such as whole-graph runs / add-to-tasks / agent pipelines automatically enable fault-tolerant mode: a failing node falls back to cached or gallery outputs, is marked degraded, and downstream keeps executing — a long batch doesn't restart just because one node hiccupped.

  • Degraded nodes are flagged in the run log, pipeline overview and node state (degraded + failure reason).
  • Best for “partial failure is acceptable” batch scenarios; when debugging, use single-node execution to keep the strict fail-fast behavior.

8.5 Node types at a glance

Generation / assets

  • Image generation · video generation · audio generation · script generation · shot generation · world element extraction · planning doc generation · director stage edit · canvas edit · 3D model generation · 2D frame animation · model (reference) · host asset
  • 3D model generation: text / upstream reference images → a 3D model asset (Meshy, Tripo, Rodin (Hyper3D), Luma AI, Lux3D; text-to-3D / image-to-3D, with multi-image to 3D on some); submit async → poll → download, and the result can feed the director stage or downstream nodes, with write-back binding persistence and cancellation.
  • Host asset: bring an existing asset (image / video / audio / script / shot / director stage, …) into the current canvas as a node — the output port type is that asset's port type; double-click a host asset node to dive into its internal workflow (see 8.6 Host assets and Dive).

Output

  • Image / video / audio / script output · director stage output · shot output · world element output · final timeline

Utility

  • Note · text · select image / video / audio / text · grid select · motion cell select · prompt optimizer · image-to-prompt · UI screen breakdown / UI screen generation · frame animation sheet · comic page · ad variant matrix · media QC · media rework · bundle
  • Bundle: gather several upstream outputs (image / video / audio, …) into one group so they can be fed to an output or downstream node as a whole; also handy as a temporary organizing tool.

Motion (under the motion group)

  • Frame animation sheet: double-click to open the prompt panel (character / FX / martial-arts presets, default prompt and system prompt); row / column parameters are appended to the prompt and an image model produces the sheet; the output preview supports deleting and selecting output images.
  • 2D frame animation: takes a sprite sheet, set row / column parameters in the Inspector, and the node card plays a frame-by-frame preview automatically; cooking clears the previous output instead of accumulating.

Comics & ads

  • Comic page: grid panels plus a speech balloon editor. Drag images from the asset library into a panel / import locally / fill from upstream in one click; each panel's image path can be cleared; panel size is adjusted by span with the right / bottom / bottom-right handles (continuous live preview, snapping to the grid on release); balloons can be dragged to move and scaled proportionally with corner handles (0.5~4×); clicking empty space sets page-level and panel background colors. PNG export defaults to a transparent background; cooking fills upstream images in reading order and composites a PNG into the gallery.
  • Ad variant matrix: set the product description and aspect ratio, then double-click to enter variant dimension configuration and comparison preview, producing multiple ad variants on the same theme in one run.

QC & rework (Agent pipeline)

  • Media QC: connect an upstream image (or a video, reviewed by its first frame) and let a vision model give a director PASS / FAIL verdict; you can add review points, or leave it empty to use the built-in QC bundle.
  • Media rework: generate → QC → on failure automatically inject the FAIL reason and regenerate until it PASSes or the attempt limit is reached; the top bar's “Agent pipeline overview” shows QC / rework run status centrally.

Image editing (under the image group)

Multi-angle editor: fast camera and framing switches
Multi-angle edit: fast camera and framing switches.
Lighting editor: fine control of light and atmosphere
Lighting: fine control of light and atmosphere.
Mood editor: control the emotion and color grade of a shot
Mood: control the emotion and color grade of a shot.
Image editor: local repaint and image revision
Image edit: local repaint and image revision.
  • Multi-angle edit · lighting effects · portrait texture adjust · mood adjust · HD upscale · outpainting · repaint · erase · cutout · crop · grid split · layer separation
  • Layer separation (Seedream 5.0 Pro layer_decomposition): split an image into a base image plus up to 16 transparent PNGs, reorder layers in the dive editor and recompose locally; supports wheel zoom and Space-drag panning, and exports PSD (preserving layer order, position, size, alpha channel, names and nested groups) or PNGs grouped into subfolders.
  • Retouching / image editing happens in Dive; options and prompts are written back to the node params in real time and stay visible in the Inspector. Preview opens as a dialog rather than taking a Dive tool slot.

Video editing (under the video group)

  • Lip sync · frame pulling · segment reshoot; frame pulling and segment reshoot open sub-windows on double-click (pull station / reshoot station), sharing the “double-click to open a sub-window” interaction with image editing.
  • Frame pulling: connect an upstream video and double-click to open the pull station, browse frame by frame and grab / annotate key frames for storyboards or prompts.
  • Segment reshoot: connect the source video and double-click to open the reshoot station, mark the start / end time to change and describe the change; running it reshoots only that range (Seedance 2.5 timestamp-level editing) and leaves the rest untouched. The prompt box supports @ references to port media, and the video model can be picked on the right.

Shot / world

  • Shot breakdown / shot table / shot generation / shot reference · select shot · world element extraction / world element review / world element generation / world element entity output
  • Select shot: pick one shot (or match by condition) from several upstream shots as the current output — commonly used to decide which shot continues in a multi-branch shot flow.

Others

  • Graph plugin sample (loaded only for local debugging; absent from official installers)

8.6 Typical node workflows

  1. Script: create a script → pick a text model on the right → fill in “generation prompt” → run the generation node → connect it to “script output”.
  2. Shot: script → “shot breakdown” → “shot table” (run to import JSON) → “shot generation” / video generation → “shot output”; for batch storytelling use the One-Click Workflow “short-drama storyboard (Agent pipeline)” template.
  3. Image / video: connect upstream references into the generation port → reference them with @ in the prompt → execute → export the result with an output node. To build video and reference video from scratch on a free canvas, see the dedicated guide.
  4. Final cut: shot / video node outputs → open the script asset's final timeline → drag clips onto tracks, assemble and export.
  5. One-Click Workflow: create a host from the top bar → drag it onto the canvas and wire it up → Dive to fine-tune → add to tasks.

8.6 Host assets and Dive

A host asset (including One-Click Workflow output and selection wrappers) exposes only boundary inputs / boundary outputs on the outside; double-click or Dive into it to edit the full inner topology.

  • Boundary outputs map one-to-one onto sinks: several same-type results (e.g. multiple character sheets) each get their own outlet instead of being merged into one.
  • Note-style text nodes aren't exposed as host outlets by default.
  • The whole inner chain can be queued in the task list; a host node also participates as a black box in larger flows on the canvas.
  • Retouch / image editing tools operate inside Dive and write options back to node parameters; large previews open as dialogs.

9. Script & shots

9.1 Script assets

Generate and edit script content through the node graph. Connect the result to “script output” and pick a suitable text model and prompt in the parameter panel. Script assets can be dragged into other graphs as upstream.

9.2 Shot assets

  • A shot (beat) replaces the old storyboard: narrative is organized per shot, then broken down and generated into camera-ready shots.
  • Shot breakdown (storyboard artist · beat breakdown table): splits time / space / characters / action / conflict / atmosphere columns out of the script.
  • Shot table: view and edit breakdown results in bulk; rows can be added and deleted, and double-clicking the node opens the table window.
  • Shot generation / shot reference: generate content per shot in bulk, or reference a specific shot to keep working; combined with the Episode Pipeline's 9-grid / 4-grid storyboard tables and motion video generation, this completes the whole short-drama chain.

9.3 Storyboard thinking and prompt presets

The old standalone “storyboard asset / camera blocking” has been removed — storyboarding now lives in shots and the Episode Pipeline: the beat breakdown table splits shots, the 9-grid / 4-grid storyboard tables turn shots into camera setups you can generate, and images and video come from generation nodes.

  • Camera language: hero / mysterious entrance, two-shot medium, over-the-shoulder reverse, high angle, from behind, Dutch angle, and more.
  • Body orientation: full front, 45° front, pure profile, 45° back and strict back.
  • Acting: anger, dissociation, mania, relief, anxiety, sadness, confidence and surprise broken down into facial, breathing, shoulder / neck, finger and weight-shift movement.
  • Lighting: top light, frontal side light, Rembrandt, volumetric, backlight and motivated light sources inside the frame.
  • Ad camera moves and transitions: impact hard cut, flash to white, motion match, short dissolve, match cut, foreground occlusion, rack-focus reveal, jump cut and product hero reveal.

The prompt presets of video and image generation nodes (storyboard artist · beat breakdown table / 9-grid storyboard table / 4-grid motion storyboard table, …) write this camera language straight into the prompt; the frame pulling node can grab key frames from a reference video first, then use segment reshoot for local changes — see the Node graph chapter.

10. Final timeline

The final timeline assembles shot / video node outputs and imported media into a timeline you can preview and export; it's usually opened on a script asset.

10.1 Opening and layout

  • Open the final timeline editor from a script-related flow (left: media library · center: preview · bottom: multi-track timeline).
  • Track types: video · picture-in-picture · voice-over · subtitles · music.
  • The media library header can refresh inputs and auto-place on tracks (laying media onto tracks in order), and the media display size is adjustable.

10.2 Left-side media

  • Node inputs: video / audio collected from upstream nodes. They can't be deleted from the list (deleting a track clip doesn't affect the list).
  • Imported media: appears here after being dragged into the timeline from the asset library or your file system. It can be deleted, which also removes the matching clips from tracks.
  • In the import area right-click to create a group; groups can be renamed and deleted (deleting one returns its media to “Ungrouped”). Drag imported items into a group or back to “Ungrouped”. Groups are saved with the timeline document.
  • Video media icons use the first-frame thumbnail; audio media shows a generic audio icon.

10.3 Placing and arranging

  • Drag from the list onto a track to place it; audio dropped on a video track lands on the voice-over track automatically. “Auto-place on tracks” also spreads everything out in one click.
  • Clips on tracks can be dragged left / right to change timing, or moved to another track; double-click a clip to preview / locate it.
  • Clip actions: split at the playhead, copy / paste (pasted at the playhead), remove clip. The properties panel fine-tunes start time / clip duration / volume, and audio clips support fade in / fade out.
  • Track management: hide / show, lock / unlock, collapse / expand; drag a track edge to change its height; “Total duration” sets the timeline length (it can't be shorter than the content). The timeline has its own undo / redo.
  • Subtitle track: you can add subtitles and edit their text.

10.4 Playback

  • Center preview playback: plays only the currently selected video or audio clip (the button is disabled when no media clip is selected).
  • Bottom timeline toolbar playback: plays the whole timeline (video sequence + audio tracks) with return to start, pause, loop and speed settings.

10.5 Picture-in-picture and transitions

  • Picture-in-picture overlay: drag a video onto the preview overlay to layer it as PiP; the properties panel adjusts horizontal / vertical position, width / height, opacity and volume (resettable in one click). The preview frame can follow the original video or the export aspect ratio, and PiP is composited on export.
  • Transitions: a blue handle appears where two clips overlap on a video track — drag it to adjust the overlap / transition length. In / out transition effects include dissolve, fade in / out, A fade out / B fade in, flash white, slide left / right / up / down, wipe left / right / up / down and circle open / circle close, all composited on export.

10.6 Subtitles

  • Select a subtitle clip and edit the text, font size, height (vertical position), color and style in the properties panel; scrolling the wheel while a clip is selected also changes the font size.
  • Subtitles are exported with the film, and can also be exported separately as an SRT file.

10.7 Export

The timeline toolbar offers Export film: set the resolution (preset or custom width / height), frame rate and bitrate. It prefers the local ffmpeg to mux an MP4 and falls back to WebM recording when ffmpeg isn't installed. Export progress and the result path are reported in the UI. Use “Fit width” to zoom the timeline.

11. Canvas & world elements

11.1 Canvas assets

  • Free canvas: a blank node canvas — right-click to add nodes, or drag assets in from the asset library. Creating another yields “Free Canvas 2” and so on. To build video generation and reference video on a canvas, see Free canvas: video generation & reference video.

11.2 World elements / shots

  • Table view: world elements are character / scene / prop / weapon; the shot table has time / space / characters / action / conflict / atmosphere columns. Rows can be added and deleted.
  • Double-clicking the matching node opens the extraction / breakdown prompt, the table or the editing window.

12. Director stage

3D director stage: characters, cameras and blocking shots
3D director stage: blocking shots, motion recording and camera views.

The director stage handles 3D posing, cameras, animation preview and recording. The node chain is usually “director stage edit → (optional) select / downstream generation”. The edit node offers two square outputs (blocking shots and motion captures) and two kinds of input: a 3D model input port — connect a 3D model generation result and diving into the stage instantiates it into the scene automatically; and a panorama input port — connect a panorama image and it becomes the stage background when you dive in.

12.1 Open from a node

  1. Double-click a “director stage edit” node in the node graph to open the stage window.
  2. After closing the stage or syncing, results are written to the node: out-shots (blocking shots, images) and out-actions (motion captures, videos).
  3. The node Inspector previews blocking thumbnails and motion videos (double-click for the media preview).

12.2 Viewport controls

  • Left button selects · middle button pans · hold the right button for fly-through: W/A/S/D to move, Q/E to descend / ascend, Shift to accelerate, mouse to look.
  • Q / R / S: move / rotate / scale tools.
  • Bottom viewport toolbar: panorama / animation mode switch, aspect ratio (Auto follows the viewport size, or fixed 21:9 / 16:9 / 4:3 / 1:1 / 3:4 / 9:16 — it affects preview and capture framing), a selection bounds toggle, screenshot and reset view.

12.3 Sidebar and objects

  • Left scene list: hierarchy, search, create camera / empty object / primitives (cube, sphere, cylinder, pointed arch, torus, plane, … 20+); drag the right edge to resize the list (remembered locally).
  • AI blockout: provide perspective / 360 panorama references (up to 3) plus a prompt, and a text model builds a scene blockout from primitives — a quick way to lock down perspective and spatial layout.
  • Objects: delete, hide, show name, lock; drag to reparent. The hierarchy supports multi-select batch delete and multi-select drag to reparent (moving the whole group while preserving world transforms); camera groups can be deleted as a group, preset cameras included, and it's undoable.
  • Properties · pose (FK / IK, AI pose — generate bone rotations from natural language, common pose presets) · material texture override: replace an object's base / normal map, with options to remove or hide a texture slot, or restore the model's own textures in one click.

12.4 Blocking and motion

The “Blocking & motion” button in the title bar opens a panel with two categories:

  • Blocking: viewport screenshot history. Capture with the toolbar camera button; double-click a thumbnail to preview it.
  • Motion: videos recorded in animation mode. After a successful recording it's written to the project's Cache/Videos/ automatically (no directory picker) and the Motion category opens.

12.5 Views and panorama

  • Director view / camera switching; six-way views; reset.
  • Shading mode: the shading menu at the right of the title bar offers shaded / wireframe / shaded wireframe (solid with a wireframe overlay) for checking topology, intersections and occlusion. The choice is remembered locally; the default is shaded.
  • Gizmos display: the Gizmos menu at the right of the title bar adjusts gizmo size and toggles scene text, camera gizmos, the grid and selection bounds. “Include scene text / camera names in captures and video” decides whether blocking shots and motion recordings overlay those labels.
  • Move to view: Ctrl+Alt+F; align with view: Ctrl+Shift+F.
  • Panorama: drag in a background image and adjust zoom / pan / rotation, plus ground and sky colors.
  • You can also connect a panorama to the director stage node's panorama input port (single image); diving into the stage then sets it as the background automatically, with no manual drag needed.

12.6 Animation mode and recording

  • Switch between panorama mode and animation mode.
  • Tracks and keyframes: K adds a keyframe, Delete removes one, and Space plays / pauses.
  • The red dot button in the animation panel is record motion: it records the current animation to WebM, saves it to the cache directory automatically and adds it to the Motion list.

13. Asset packages .aipackage

The format identifier is com.aiartengine.asset-package; packages move media and their dependencies between projects.

Export

  1. Select assets, or enter the target folder.
  2. Right-click and choose “Export asset package”.
  3. Tick the folders / assets in the dialog; optionally enable “Include dependencies” → “Export”.

Import

  1. Right-click empty space or the root of the asset library and choose “Import asset package”, or drag a .aipackage file straight in.
  2. Tick the entries to import (one package at a time) → “Import”.
  3. Entries support reuse and remapping; script assets can carry shot / generation result data.

14. Shortcuts

Scope Shortcut Action
Global editing Ctrl+S Save (a draft prompts “Save asset” first)
Global Ctrl+Z / Ctrl+Shift+Z (or Ctrl+Y) Undo / redo
Node graph Hold C Execution ring
Node graph Space Open the menu / hold to pan (context dependent)
Node graph Delete / Backspace Delete a node or link
Node graph Ctrl+Shift+G / U Group / ungroup
Asset library Delete · Ctrl+A · Ctrl+C Delete · select all · copy-related
Node graph Ctrl+C / V / A Copy / paste / select all nodes
Director stage Q / R / S Move / rotate / scale
Director stage Ctrl+Z / Ctrl+Shift+Z (or Ctrl+Y) · Ctrl+C / V Stage undo / redo · copy / paste selected objects
Director stage Ctrl+Alt+F · Ctrl+Shift+F Move to view · align with view
Director stage fly W/A/S/D · Q/E · Shift While holding the right button: move · descend / ascend · accelerate
Final timeline Space · Delete · Ctrl+A / Z / Y / C / V Play / pause · delete clips · select all / undo / redo / copy / paste
Director stage animation K · Delete · Space Keyframe · delete keyframe · play / pause
Dialogs Esc Close common popups
On macOS read Ctrl as ⌘ Command (except where system conventions differ). The settings panel special-cases Delete / Backspace so you don't close settings or delete model list items by accident.

15. Troubleshooting

Find your symptom below — entries are ordered by how often they happen, and the vast majority of issues are solved within the first three. If you're still stuck, reach out in QQ group 647306826, by email at 284139554@qq.com, or on GitHub Issues (attaching the run log gets you an answer much faster).

“Insufficient balance”, or everything fails as soon as it runs

Generation calls the model provider you configured yourself, and the provider bills you for it. This app never collects payment on its behalf, so errors like this almost always come from the provider account.

What to check, in order:

  1. Sign in to the provider console and confirm the balance or remaining quota is sufficient (an exhausted free tier fails just the same).
  2. Settings → Models: confirm the key is correct, not expired and not revoked.
  3. Confirm the models you need are ticked and enabled, and that default text / image / video models are each set.
  4. Run the same node with a different model — that separates “an account problem” from “a single-model problem”.
Invalid key, 401 / 403, or the model list won't load
  1. Check for stray spaces or line breaks around the key; copying and pasting it again usually fixes it.
  2. Confirm the key has permission for the model in question on the provider side — some models require a separate application.
  3. If you use a proxy or relay service, make sure the relay address is complete (including the /v1 path and similar).
  4. On a restricted network, configure a proxy in settings and retry; HTTPS interception on corporate networks also breaks fetching.
Links won't connect: “port type mismatch”

Ports strictly distinguish singular from plural: mismatched types never connect, and singular can't go into plural — image won't go into images, and the same goes for video / voice / text.

Common fixes:

  1. When a node needs a list input (e.g. “Select image / video / audio / text”), connect from the upstream square port (out-all, or out-shots / out-actions on the director stage); the default round out won't connect.
  2. Structured directory ports use world / worldEntities / beat (world elements / world element entities / shot) and must not be mixed with plain text.
  3. A script node's text also can't go straight into “Select text” — use the matching list port.

See §8 Node graph.

A node finished but produced nothing, or tasks stay queued
  1. Open the node's run log and read the actual error (most of the time the model returned an error or a parameter was invalid).
  2. Confirm upstream nodes ran successfully: if upstream never finished, downstream has no input.
  3. Check whether the task queue is saturated by another long job; pause or cancel queued tasks.
  4. Gallery generation nodes have two outputs, out (currently selected) and out-all (whole history). If you wired out, check in the Inspector that the item you expect is selected.
Characters “change faces”, or storyboards don't match

This is the classic trap of pure text-to-image. Solve it with references rather than repeating descriptions:

  1. Use anchor images: split reference images out of a 9-grid / 4-grid sheet cell by cell, then feed them in as references for later generations to lock face, outfit and setting.
  2. Register characters, scenes and props as world elements so every shot shares one description instead of re-describing them each time.
  3. Check whether a node in the middle switched models or heavily rewrote the prompt — style drift usually comes from there.
  4. In the short-drama flow, make good use of the review1~review4 review nodes to send sub-par results back in time.

See §2 Core concepts and the Short-Video Guide.

Images look soft, or the resolution is too low
  1. Append an HD upscale node at the end of the generation chain; the short-drama template already includes that step.
  2. Check the resolution setting on the generation node — some models need an explicit size.
  3. Avoid over-compression: watch the scale factor and export format when exporting.
Video doesn't move, the length is wrong, or a reference video is ignored
  1. Confirm the motion prompt is filled in properly; a static description produces an almost static shot.
  2. Confirm the chosen video model supports the target duration and resolution.
  3. Reference videos need a publicly reachable URL: configure object storage (TOS / OSS / COS, only one enabled at a time). You can skip it for purely local previews, but reference-video features will be limited.
  4. See the Video Guide.
Object storage won't configure, or video URLs won't open
  1. Only one object storage can be enabled at a time (Volcengine TOS / Alibaba Cloud OSS / Tencent Cloud COS) — disable the old one before enabling a new one.
  2. Check that the bucket permission is public read; links generated for a private bucket can't be opened from outside.
  3. Verify the AccessKey has read / write permission on that bucket and that the region is correct.
  4. Make sure a reachable public domain is filled in (CDN domains need to be ICP-filed).
ComfyUI won't connect, or reports a workflow format error
  1. Confirm comfy-api-proxy is running locally and that the port matches the one configured in the app.
  2. Confirm ComfyUI itself is running and reachable.
  3. You must use an API-format workflow (enable Dev Mode in ComfyUI and export with “Save (API Format)”); the UI format (which contains nodes / links arrays) won't work.
  4. See the ComfyUI guide.
Fails to start, blank screen, or update fails
  1. Confirm the installer matches your system architecture (on macOS, Intel vs Apple silicon).
  2. If the first launch is blocked by system security policy, allow the app to run in System Settings.
  3. If an update fails, re-check under Settings → General → About & updates, or download the release manually and install over it.
  4. If it still misbehaves, back up your project directory, reset the configuration and retry — and remember to attach logs and your OS version when reporting.
How do I let Claude Code and other AI assistants operate the app? (Install MCP)

The app ships with an MCP tool service. Once connected, Claude Code and other AI agents can plan workflows, edit node graphs, run generations and query tasks from a chat. The app must be running first. Pick either of the two methods:

  1. stdio bridge (recommended, needs Node.js 18+): run claude mcp add aiartengine -- node <install-dir>/resources/mcp-bridge.mjs.
  2. HTTP direct (no Node.js needed): open Settings → MCP and copy the “Claude Code connection command”, or run it manually as claude mcp add --transport http aiartengine <endpoint> --header "Authorization: Bearer <token>" (endpoint and token live in the app-side mcp.json and persist across restarts).

After registering, restart the agent session for the tools to appear. The app-side mcp.json (%APPDATA%/aiartengine/mcp.json) is maintained by the app — do not edit it by hand. If the register command errors (e.g. Script not found), your Claude Code install is usually broken — reinstall and retry. Full steps and the tool list: MCP guide.

AI chat panel errors / model unavailable / spinner never ends
  1. Model unavailable (HTTP_404 etc.): the chat panel uses the text model selected in the model dropdown — the model ID must match a name that actually exists at the chosen provider; switch to a model enabled on your provider account or to another provider whose key you've configured.
  2. No model selected / none available: first enable at least one text model with its key under Settings → Models.
  3. Spinner never ends: make sure Node.js ≥ 22.19 on this machine (installers bundle the runtime); watch the panel status line and logs.
  4. Tool execution failed: check the error on the tool card — usually the project isn't open or the API key ran out of quota.
When diagnosing, run the same node with a different model — it's the fastest way to tell “an app problem” from “a model / account problem”.

16. About & updates

Path: Settings → General → About & updates.

  • Current version: shown as v{version} (pre-releases such as 4.1.0-beta.1 are flagged as prerelease).
  • Check for updates: queries GitHub Releases; in dev mode it reports that updates aren't checked.
  • States include: checking, new version found and downloading, already up to date, download progress, failure.
  • When the download finishes you can click Restart and install.
  • Changelog: the full version history lives in CHANGELOG.