FAQ
BigBotArt FAQ
BigBotArt is a local-first macOS workbench for AI video and image generation agents, built around an infinite canvas. This page collects the system requirements, the installation steps, and 15 questions on the product, its engines, the workflow, platform, install, and privacy.
AI summary · quotable
BigBotArt in one paragraph
BigBotArt is a local-first macOS workbench for AI video and image generation agents, built around an infinite canvas.
The agents live inside the infinite canvas, a persistent chat on the right edits nodes directly, and storyboards, shot takes, and timeline export close the loop in one project.
h3.c (MiniMax-H3) produces shot-level video with audio, mlxgen (mlx-gen-jzg) downloads image models on demand (Z-Image-Turbo, Qwen-Image family, SeedVR2, and more), Agent chat uses any OpenAI-compatible endpoint, and final export runs through local FFmpeg.
Models and compute stay on your Mac and assets are never uploaded to a cloud; the current release is v0.1.1 for macOS Apple Silicon (arm64).
Full details live in /llms.txt (index) and /llms-full.txt (full text with all 15 answers); updates are published at /feed.xml.
System Requirements
System requirements
BigBotArt currently ships as a macOS Apple Silicon (arm64) desktop app.
An Apple Silicon (arm64) Mac
BigBotArt needs an Apple Silicon (arm64) Mac: the local models and all compute run on that machine.
Generous free disk space
h3.c (MiniMax-H3 alone is about 144GB) and the mlxgen image models are large, so allow tens to well over a hundred GB of free disk before first-run downloads.
macOS version and memory
The exact minimum macOS version and memory requirements are listed on the GitHub Releases page: Releases.
Installation
Installation steps
Four steps to install; the first launch needs a connection to download models.
-
Download the DMG
Download the macOS Apple Silicon build from GitHub Releases: BigBotArt-0.1.1-arm64.dmg.
-
Open the installer and drag the app into Applications
Double-click the DMG to mount the disk image, drag BigBotArt into your Applications folder, and launch it from Applications.
-
Finish the first-launch wizard
On first launch, follow the wizard through environment detection, component installation, and model downloads. This step needs a connection, and the models are large, so allow tens to well over a hundred GB of free disk.
-
Start your first project
Describe the brief on the home screen, pick a Skill, and hit generate — the resident agent lays out the storyboard on the infinite canvas, and you pick takes from the take pool into the timeline.
Questions & Answers
Frequently asked questions
The 15 answers below use exactly the same wording as /llms.txt and /llms-full.txt, so they can be quoted verbatim.
-
What is BigBotArt?
BigBotArt is a local-first macOS workbench for AI video and image generation agents: the agents live inside an infinite canvas, a persistent chat edits nodes directly, and storyboards, shot takes, and timeline export close the loop in one project.
-
Which systems are supported? Do I need to be online?
BigBotArt ships as a macOS Apple Silicon (arm64) app (v0.1.1). Models and compute run on your own Mac and assets never need to be uploaded to a cloud; you only need a connection to download models the first time and to update the app.
-
Which models and engines are used?
The h3.c video engine runs MiniMax-H3 (BF16, ~144GB) for shot-level video with audio — text-to-video, first-last frame, and Ref2VA; optional style packs merge LoRA offline into a copy of the base model. mlxgen (package mlx-gen-jzg) downloads image models on demand: Z-Image-Turbo (default T2I/img2img), Qwen-Image-2.1 and Turbo (with references), Qwen-Image-Edit (instruction edit / inpaint / outpaint), FLUX.2 Klein 9B (multi-reference / outpaint), SeedVR2 3B (upscale), and a Qwen3-VL caption model for Agent vision; an Uncensored T2I variant needs a manual local convert. Agent chat uses any OpenAI-compatible endpoint (for example LM Studio). Final export runs through local FFmpeg; optional post-process Real-ESRGAN / GFPGAN / CodeFormer must be installed separately.
-
What does the end-to-end workflow look like?
Four steps on one screen: ① describe the brief and pick a Skill on the home screen; ② arrange storyboard and shot nodes on the canvas while the resident agent executes; ③ pick takes from the take pool and drop them into the timeline; ④ export the finished cut with local FFmpeg.
-
What are Skills?
A Skill is a preset in two forms — a canvas template plus operating instructions — that you inject into the current project in one click, so the agent lays out storyboards, locks the style, and runs batch generation the way you want.
-
How do I download it? Where is the source code?
Download the macOS Apple Silicon build from GitHub Releases: https://github.com/jiangzhenguo/bigbot.art/releases/download/v0.1.1/BigBotArt-0.1.1-arm64.dmg . Source code and changelog live in the same repository, https://github.com/jiangzhenguo/bigbot.art , and you can also reach us at jyllyj826@gmail.com.
-
What are the system requirements?
You need an Apple Silicon (arm64) Mac. h3.c (MiniMax-H3 alone is about 144GB) and the mlxgen image models are large, so allow tens to well over a hundred GB of free disk before first-run downloads; the exact minimum macOS version and memory requirements are listed on the GitHub Releases page.
-
Are my assets uploaded anywhere?
No. Models and compute stay on your Mac: video, images, and prompts are written only into the local project, and export runs through local FFmpeg, so nothing has to be uploaded to a cloud.
-
What kind of content is it good for?
Common cases are e-commerce product films (turning multi-angle product stills into a product video with sound), short-drama storyboard previz, and shot-level generation such as product rotation or scene extension.
-
What are the main screens?
The three main creation screens are Home (three columns — brief, Skill picker, project stream), Canvas workbench (infinite canvas with resident agent chat and a node palette), and Timeline (take pool, dual audio tracks, export presets, and continuity checks); the app also includes Projects, Assets, Skills, Settings, and the Engine Wizard screens.
-
Does BigBotArt run only on Apple Silicon Macs?
Yes. The current release, v0.1.1, ships only as a macOS Apple Silicon (arm64) build, and the release notes list M1, M2, M3, and M4. You need an Apple Silicon Mac: models and compute run on that machine.
-
How much disk space does the first run need?
h3.c (MiniMax-H3 alone is about 144GB) and the mlxgen image models are large, so allow tens to well over a hundred GB of free disk before first-run downloads. The exact minimum macOS version and memory requirements are listed on the GitHub Releases page.
-
How do I install BigBotArt from the DMG?
Download BigBotArt-0.1.1-arm64.dmg (https://github.com/jiangzhenguo/bigbot.art/releases/download/v0.1.1/BigBotArt-0.1.1-arm64.dmg), double-click it, drag BigBotArt into Applications, and launch it from Applications. On first launch, follow the wizard through environment detection, component installation, and model downloads; that step needs a connection. If 0.1.0 is already installed, quit the old app before replacing it.
-
What do the infinite canvas and the resident agent each do?
The infinite canvas workbench provides 11 node types for arranging storyboards, shots, and assets; storyboards, shot takes, and timeline export close the loop in one project. The resident agent lives in the chat on the right side of the canvas, edits nodes directly, shows tool calls in ToolRunCards, and supports ask.user confirmation cards plus the worker protocol.
-
Do I need an account or a subscription? Are assets uploaded?
No account and no subscription. Models and compute stay on your Mac; projects, the canvas, takes, and assets are written only to the local directory ~/.bigbotart, and video, images, and prompts are not uploaded to a cloud. Final export runs through local FFmpeg. You only need a connection to download models the first time and to update the app.