# Intangible Help ## Home - [Welcome to Intangible](https://help.intangible.ai/get-started/readme.md): Describe what you want to make, add what you have, and Intangible builds the scene and renders the shots. - [Get started](https://help.intangible.ai/get-started/get-started.md): The path from a fresh account to a delivered project: set up, describe what you want, direct Intangible agents, take control by hand, deliver. - [Set up your account](https://help.intangible.ai/get-started/sign-up-and-set-up.md): Create an Intangible account, take the Canvas tour, choose a plan, and see what uses credits before you start your first project. - [Your first project](https://help.intangible.ai/get-started/your-first-project.md): Describe a project, confirm the brief, let Intangible agents build the scene, then render keyframes, video and an asset pack. One prompt and two photos to a finished set of shots. - [Start a project](https://help.intangible.ai/get-started/start-a-project.md): Start a project from Home: describe what you want to make, add the files you already have, choose Guide me or Skip, and create the project. - [Start from an empty canvas](https://help.intangible.ai/get-started/start-a-project/create-your-first-project.md): Open a new Intangible project, name it, and understand the scene-and-shot structure before you drop your first object. - [Direct Intangible agents](https://help.intangible.ai/get-started/direct-intangible-agents.md): Confirm the brief once, follow the step list while Intangible agents build, and steer them in the chat panel. Know when to let them run and when to step in. - [Take control](https://help.intangible.ai/get-started/take-control.md): Open Build, Compose or Visualize from a card on the canvas when you want to change something yourself, then go back to the canvas. - [Move the camera](https://help.intangible.ai/get-started/take-control/viewport-navigation.md): Orbit, pan, zoom, frame – operate a 3D scene like a cinematographer. - [Place objects by hand](https://help.intangible.ai/get-started/take-control/place-your-first-objects.md): Drag objects from the asset library, place them on the ground, swap, snap, and lock so they stop drifting on you. - [Deliver](https://help.intangible.ai/get-started/deliver.md): Turn shots into keyframes and video, fix what is not right, and hand off everything as an asset pack or a published project. - [Report a bug or get help](https://help.intangible.ai/get-started/help-and-feedback.md): Found a bug? Report it from inside Studio in a few clicks: Help (?) > Report an Issue, describe it, click Send report and share the Studio tab for a screenshot. - [What's new](https://help.intangible.ai/get-started/whats-new.md): What changed in each Intangible Studio release since 2.0, newest first, with a link to the help page for each change. - [Chat](https://help.intangible.ai/chat-agents-intangible/chat.md): The chat panel is where you direct Intangible agents. Tell them what you want to make in plain words, and they build the scene, place the cameras and render the shots. - [Chat with Intangible](https://help.intangible.ai/chat-agents-intangible/chat-with-intangible.md): Open the chat panel, write a request to Intangible agents, name the card you mean, attach images, and answer the questions they ask with one click. - [Status and steps](https://help.intangible.ai/chat-agents-intangible/status-and-steps.md): Read what Intangible agents are doing: the status line at the top of the panel and the step list as each part of the job lands. - [Pick a model](https://help.intangible.ai/chat-agents-intangible/pick-a-model.md): Choose the AI model Intangible agents think with. This is separate from the model that renders your images and videos. - [What the agents do in Build, Compose and Visualize](https://help.intangible.ai/chat-agents-intangible/in-the-modes.md): What to ask Intangible agents for from the canvas or Build, by mode: environments, populators, roads, objects and poses; camera moves and reels; keyframes, videos and looks. - [Tips for directing agents](https://help.intangible.ai/chat-agents-intangible/limits.md): Habits that get better results from Intangible agents: specific prompts, plain character names, well-named models, undo, checking a video's cost, and asking a stalled agent to continue. - [Work well with Intangible agents](https://help.intangible.ai/chat-agents-intangible/work-well-with-intangible-agents.md): Guides to getting more out of Intangible agents: writing a brief they can build, controlling AI output, and how renders read your scene. - [The canvas](https://help.intangible.ai/canvas/canvas.md): The canvas is a project's home screen: every reference, model, scene, shot and render as a card, laid out in groups, with Intangible agents working alongside. - [Home](https://help.intangible.ai/canvas/home.md): Home is where every project starts: describe what you want to make, add photos, PDFs or 3D files, and create the project. Recent projects, tutorials and templates sit below. - [Groups and cards](https://help.intangible.ai/canvas/groups-and-cards.md): How the canvas is laid out: groups of cards for your uploads, references, scenes, shots and renders, what each card's toolbar does, and how to move around. - [The brief](https://help.intangible.ai/canvas/the-brief.md): The brief is the written plan for your project, made from your prompt and files. Check it, edit any section, and confirm it once to start the build. - [What Intangible agents build](https://help.intangible.ai/canvas/what-intangible-agents-build.md): What lands on the canvas after you confirm the brief: reference sheets, generated references, a scene at true scale with its models and motion, and a shot card for each shot, each one a card you can o - [Batch visualize](https://help.intangible.ai/canvas/batch-visualize.md): Render an image for every shot in a scene in one pass from the scene card on the canvas. Each shot keeps its own prompt, camera and aspect ratio. - [Edit media](https://help.intangible.ai/canvas/edit-media.md): Fix part of an image or video on the canvas by drawing on it and writing a note, with optional reference images, without leaving the canvas. - [Keyframes to video](https://help.intangible.ai/canvas/keyframes-to-video.md): Turn a keyframe on the canvas into a video shot, by asking in the chat or through Edit in Visualize, then skim and play the result. - [Create on the canvas](https://help.intangible.ai/canvas/create-on-the-canvas.md): Upload images, videos and 3D files, and make new images, videos and style presets straight on the canvas, without building a scene first. - [Asset packs](https://help.intangible.ai/canvas/asset-packs.md): Pick the keyframes, videos, references, models and scenes to hand off, and package them into one downloadable ZIP, straight from the canvas. - [Build mode](https://help.intangible.ai/build/build.md): Build mode – the art department where you construct the set, drop in props, and bring your own assets. - [Asset library](https://help.intangible.ai/build/asset-library.md): Over 5,000 greyboxing assets at the bottom of Build mode. Drag in, swap, lock. - [Working with objects](https://help.intangible.ai/build/working-with-objects.md): Click, swap, color, lock, frame, delete – the contextual menu that handles most per-object actions in Build mode. - [Selection and grouping](https://help.intangible.ai/build/selection-and-grouping.md): Marquee selection, parent attachments, and group-level actions – how to act on more than one object at a time. - [Transform](https://help.intangible.ai/build/transform.md): Move, rotate, scale objects with the gizmo. Two coordinate-space modes plus surface, vertex and grid snapping. - [Measurement](https://help.intangible.ai/build/measurement.md): Drop a ruler into the scene and read the distance between two points, with angles if you need them. - [Object details](https://help.intangible.ai/build/object-details.md): Name, description, image reference, and LoRA – the per-object metadata that the visualizer reads when it builds the prompt. - [Environment](https://help.intangible.ai/build/environment.md): Sun position, time of day, background, shadows, terrain and grid – the scene-level environment controls in Build mode. - [Fog](https://help.intangible.ai/build/fog.md): Fog is placed as objects you position and size, not as a single scene setting. - [Import your own models](https://help.intangible.ai/build/import-your-own-models.md): Import 3D models from Blender, Maya, Houdini, or Unreal. GLB, GLTF, DAE, FBX, PLY, OBJ, SOG, SPZ. Smart Import fixes scale and orientation on the way in. - [Import Gaussian splats](https://help.intangible.ai/build/import-gaussian-splats.md): Import a Gaussian splat as a scene object, fix its orientation on the way in, and use it as a surface other objects can snap to. - [Generate a world](https://help.intangible.ai/build/generate-world.md): Describe a place, or show it a photograph, and get a full 3D world back as a Gaussian splat. - [Motion paths](https://help.intangible.ai/build/motion-paths.md): Draw a route in the scene and an object follows it, instead of keyframing every position along the way. - [Game Mode](https://help.intangible.ai/build/game-mode.md): Walk a scene at eye level with a physics-backed character, instead of orbiting it from outside. - [Pose Edit Mode](https://help.intangible.ai/build/pose-edit-mode.md): Pose a character joint by joint, or start from a named pose and adjust from there. - [Image to scene and shot](https://help.intangible.ai/build/image-to-scene-and-shot.md): Turn a sketch or reference image into a 3D scene and shot. Image-to-3D scene generation that matches the photograph's framing and contents. - [Sets](https://help.intangible.ai/build/sets.md): Save a group of arranged objects as a reusable set – drop a complete coffee-table arrangement or street-corner cluster into another scene with one drag. - [Scene Outliner](https://help.intangible.ai/build/scene-outliner.md): The panel that lists every object in the scene – lock, hide, pin, rename, duplicate. - [Populators](https://help.intangible.ai/build/populators.md): How to create, adjust, and customize populators in Build mode – the procedural environment generators that scatter one asset set across an area. - [Spline populator](https://help.intangible.ai/build/spline-populator.md): A populator shape that distributes objects along a curve. Place fences, roads, hedges, lamp posts, or any repeating element along an authored path. - [Generate 3D Asset](https://help.intangible.ai/build/generate-3d-asset.md): Generate a 3D model from a text prompt or reference image. Drag the result into your scene like any library asset. - [LoRAs](https://help.intangible.ai/build/loras.md): Train a LoRA for character or object consistency in AI renders. Upload references, attach to a Build-mode object, reuse the same look across every shot. - [Compose mode](https://help.intangible.ai/compose/compose.md): Compose mode – the camera department where you place cameras, set lenses, and frame the action. - [Shots](https://help.intangible.ai/compose/shots.md): Add, duplicate, reorder. Each shot saves its own camera, lens, and aspect ratio; animation lives on the shared scene timeline. - [Camera controls](https://help.intangible.ai/compose/camera-controls.md): Free cam, fine-tune, game-controller support. Two camera-control modes per shot. - [Lenses](https://help.intangible.ai/compose/lenses.md): The lens pack in Compose mode and how focal length choice shapes the shot the visualizer renders. - [Aspect ratios and film gates](https://help.intangible.ai/compose/aspect-ratios-and-film-gates.md): Film and social aspect ratios per shot, and what changes downstream when you pick one. - [Shot details](https://help.intangible.ai/compose/shot-details.md): Name and description per shot. The metadata that feeds the visualizer's auto-prompt for that specific shot. - [Aim Camera and Target](https://help.intangible.ai/compose/aim-camera-and-target.md): Lock the camera onto a moving subject so it stays in frame even when the subject travels through the scene. - [Animation](https://help.intangible.ai/compose/animation.md): Keyframe animation for cameras, objects, and characters in Compose mode, authored on the shared scene timeline with smooth interpolation by default. - [Timeline](https://help.intangible.ai/compose/timeline.md): Cut the animatic. The Sequence Timeline lays your shots end to end as an edit – set durations, reorder, scrub the assembled cut. - [Storyboard view](https://help.intangible.ai/compose/storyboard-view.md): Build an AI storyboard inside your project. Every shot in the project laid out as a card, grouped by scene, ready to reorder before you cut. - [Visualize mode](https://help.intangible.ai/visualize/visualize.md): Visualize mode – pick a model, edit the auto-prompt if you want, generate. - [Auto-prompt](https://help.intangible.ai/visualize/auto-prompt.md): How the visualizer assembles the prompt from your 3D scene, camera, and named details. - [Scene context](https://help.intangible.ai/visualize/scene-context.md): How the visualizer's right panel splits the prompt into Scene, Style, and Lighting tabs, and what each one feeds into the model. - [Generate image](https://help.intangible.ai/visualize/generate-image.md): Generate an AI image from your composed shot. Pick a model, set resolution, render. Plus how to read the auto-prompt before committing. - [Generate video](https://help.intangible.ai/visualize/generate-video.md): Generate an AI video from your composed shot. Pick a mode, pick a model, set duration, optionally enable audio, render. Plus how to choose between the Veo, Kling, Luma, Runway, and ByteDance options. - [Edit images](https://help.intangible.ai/visualize/edit-images.md): The Edit image fix-it-in-place workflow. Recolor, remove, or modify specific parts of a generated image without regenerating from scratch. - [First and last frame](https://help.intangible.ai/visualize/first-and-last-frame.md): Two-image video interpolation – supply a start frame and an end frame, the video model fills in the motion between them. - [Video (from scene)](https://help.intangible.ai/visualize/video-from-animation.md): Use the keyframes you set in Compose to drive an AI video model's motion, or render the scene as video without AI via Direct Render. - [Direct Render](https://help.intangible.ai/visualize/direct-render.md): Render a single shot's 3D scene as video, no AI model, for a small flat fee. The wireframe / greybox view captured as MP4, exactly as authored. - [Style presets](https://help.intangible.ai/visualize/style-presets.md): Preloaded surface treatments applied with one click in the visualizer's Style tab, plus the option to bring your own. - [Lighting presets](https://help.intangible.ai/visualize/lighting-presets.md): Control AI render lighting with the named preset library in the Lighting tab. One click swaps mood without changing composition or style. - [Custom styles](https://help.intangible.ai/visualize/custom-styles.md): Train a custom AI style on your brand's reference images. Save it for reuse across projects, share with the team, keep visual consistency across every render. - [Resolution and cost](https://help.intangible.ai/visualize/resolution-and-cost.md): 1K, 2K and 4K, what each step actually costs on each model, and when the higher resolution is worth it. - [Managing outputs](https://help.intangible.ai/visualize/managing-outputs.md): The gallery to the right of the viewport – favorite, download, delete, and find your renders later. - [Models](https://help.intangible.ai/visualize/ai-models.md): Every image and video model the visualizer exposes, with one-line guidance on when to reach for each. - [Publish](https://help.intangible.ai/publish/publish.md): Export per shot or per project. Present in-app. Hand off to your editor. - [Presentation mode](https://help.intangible.ai/publish/presentation-mode.md): Full-screen play of a sequence for client review meetings. Hides the editor chrome and walks through your shots in order. - [Publish](https://help.intangible.ai/publish/publish-tab.md): Publish a project as a shareable, viewable link. Title it, pick what to include, decide whether to allow comments. - [Poster](https://help.intangible.ai/publish/poster.md): The cover slide of a published project. Uses the first shot's poster image as the background with the title, avatar, and a click-to-play action. - [Export shot video](https://help.intangible.ai/publish/export-shot-video.md): Single-shot video and image export. Two paths: the shot kebab on the storyboard for a direct video MP4, and the per-render download icon for the render's still, its scene reference, or a ZIP of both. - [Export Video](https://help.intangible.ai/publish/export-video.md): Export video at three scopes (shot, scene, sequence) from either Compose or Visualize mode. Filename conventions, ZIP contents, and the editorial-handoff manifest. - [Scene to video](https://help.intangible.ai/publish/scene-to-video.md): Export the greybox animatic from the Scene Timeline as a video. Useful for blocking review and structural sign-off before any renders are produced. - [Export formats](https://help.intangible.ai/publish/export-formats.md): Image and 3D file format options for downloads – PNG, JPEG, GLTF, USD. Cameras carry through; licensed assets may be substituted with stand-ins. - [Concepts](https://help.intangible.ai/learn-more/concepts.md): The Intangible-specific abstractions every other docs page assumes you know. - [How Intangible works](https://help.intangible.ai/learn-more/concepts/how-intangible-works.md): You describe a project and bring your files. Intangible agents plan it, build one 3D scene on the canvas and render from it. You step into Build, Compose or Visualize when you want the controls. - [Projects, scenes and shots](https://help.intangible.ai/learn-more/concepts/projects-and-scenes.md): How projects, scenes, and shots nest. Three nouns, three different jobs. - [References](https://help.intangible.ai/learn-more/concepts/image-reference.md): The single biggest lever for professional fidelity. Bind a reference image to a 3D object and the visualizer locks the rendered look across every shot – the same character, vehicle, or product, consis - [Controlling AI output](https://help.intangible.ai/learn-more/concepts/control-ai-output.md): How Intangible gives you real control over AI output – scene fidelity in Build, framing in Compose, model choice in Visualize. - [How the visualizer thinks](https://help.intangible.ai/learn-more/concepts/how-the-visualizer-thinks.md): Why Intangible's renders stay controlled while pure prompt tools drift. The model gets a 3D scene plus a structured prompt, not just text. - [Animation and shot time](https://help.intangible.ai/learn-more/concepts/animation-and-shot-time.md): How the scene timeline works, why Build-mode moves don't animate, and how shots relate to scene time. - [Credits and tokens](https://help.intangible.ai/learn-more/concepts/credits-and-tokens.md): How Intangible bills generation work – what costs credits, where you see your balance, and how to think about cost per shot before you click Generate. - [How to](https://help.intangible.ai/learn-more/how-to.md): Task-shaped guides for the control problems that drive pro creatives off pure prompt tools – consistent characters, controlled composition, brand-true renders. - [Keep a character consistent across shots](https://help.intangible.ai/learn-more/how-to/consistent-character-ai.md): How to keep a character, vehicle, or product looking the same across every shot in your sequence. The single highest-leverage technique for pro-quality output. - [Match a client's product exactly](https://help.intangible.ai/learn-more/how-to/brand-true-ai-render.md): How to render a client's exact product, vehicle, or branded asset – not the AI's interpretation of one. The canonical agency workflow for brand-true output. - [Build a storyboard](https://help.intangible.ai/learn-more/how-to/ai-storyboard.md): How to build a complete AI storyboard inside Intangible. From a fresh project to a scene-grouped shot list ready for review. - [Make an animatic](https://help.intangible.ai/learn-more/how-to/ai-animatic.md): How to cut an animatic from your shots in Intangible. From a storyboard to a playable edit you can scrub end to end. - [Control shot composition](https://help.intangible.ai/learn-more/how-to/control-ai-composition.md): How to control composition, lens, aspect ratio, and aim in your AI renders. The Compose-mode decisions the model can't override. - [Control lighting in renders](https://help.intangible.ai/learn-more/how-to/control-lighting-in-renders.md): How to control lighting in AI renders with Visualize lighting presets, and how the Build-mode sun and time of day feed the render when no preset is set. - [Generate a 3D model from an image](https://help.intangible.ai/learn-more/how-to/ai-3d-model-from-image.md): How to generate a 3D model from a reference image (or text prompt) inside Intangible. The fastest path when the asset library doesn't have your specific thing. - [Import from Blender, Maya, or Houdini](https://help.intangible.ai/learn-more/how-to/import-from-blender-maya-or-houdini.md): How to import 3D models from Blender, Maya, Houdini, Cinema 4D, or Unreal into Intangible for AI rendering. Smart Import for FBX, OBJ and GLB. - [Brief AI like a DP](https://help.intangible.ai/learn-more/how-to/brief-ai-like-a-dp.md): How to brief an AI render the way you'd brief a DP – scene, camera, model. The mental model that scales from one shot to a hundred. - [Animate an object](https://help.intangible.ai/learn-more/how-to/animate-an-object.md): Set keyframes on an object in a Compose-mode shot, pick the interpolation, refine the motion, retime or delete keys. - [Render a CAD file with AI](https://help.intangible.ai/learn-more/how-to/render-a-cad-file-with-ai.md): Render a CAD model with AI: export it as GLB, FBX or OBJ, import it into Intangible, attach a photo of the real product, then frame and render. - [Render an architecture model with AI](https://help.intangible.ai/learn-more/how-to/render-an-architecture-model-with-ai.md): Render a SketchUp or Revit model with AI: export it as FBX or OBJ, import it, light it, place cameras, render stills and a walkthrough video. - [Make ad variations from one scene](https://help.intangible.ai/learn-more/how-to/ad-variations-from-one-scene.md): Make AI ad variations of one product from a single scene: duplicate the shot, give each copy its own lighting or style, and render each one. - [Coming from ComfyUI](https://help.intangible.ai/learn-more/how-to/coming-from-comfyui.md): Coming from ComfyUI: where checkpoints, ControlNet, LoRAs, inpainting and first/last-frame video live in Intangible, and what a 3D scene adds to them. - [Coming from FLORA, Krea or fal](https://help.intangible.ai/learn-more/how-to/coming-from-ai-canvas-tools.md): Coming from FLORA, Krea or fal: where models, references, LoRAs, edits and agents live in Intangible, and what a 3D scene with real cameras adds. - [Coming from Runway, Higgsfield, LTX Studio or Flow Studio](https://help.intangible.ai/learn-more/how-to/coming-from-ai-video-tools.md): Coming from Runway, Higgsfield, LTX Studio or Autodesk Flow Studio: where references, start and end frames, storyboards and camera moves live in Intangible. - [Coming from Unity or Unreal](https://help.intangible.ai/learn-more/how-to/coming-from-unity-or-unreal.md): Coming from Unity or Unreal Engine: where Sequencer, Timeline, Cine Cameras, Cinemachine and Movie Render Queue jobs live in Intangible, and how to move a scene across. - [Coming from Maya, Houdini or Blender](https://help.intangible.ai/learn-more/how-to/coming-from-maya-houdini-or-blender.md): Coming from Maya, Houdini or Blender: where shots, cameras, playblasts and scatter tools live in Intangible, and how to hand a scene across and back. - [Coming from Lumion, D5 Render or Twinmotion](https://help.intangible.ai/learn-more/how-to/coming-from-lumion-d5-or-twinmotion.md): Coming from Lumion, D5 Render or Twinmotion: bring the same architecture model in, get an AI render, and know where sky, entourage, scatter and camera paths live. - [Reference](https://help.intangible.ai/learn-more/reference.md): Lookups, not workflows. The pages here are for when you already know what you want. - [Account and settings](https://help.intangible.ai/learn-more/reference/account.md): How signing in works, where your account fields live, and the three Settings tabs that control language, graphics, and extensions. - [Notifications](https://help.intangible.ai/learn-more/reference/notifications.md): What sends you a notification, where the bell is, and how to accept invites, download asset packs and mark notifications read or unread. - [Sharing and collaboration](https://help.intangible.ai/learn-more/reference/sharing-and-collaboration.md): Two ways to get someone into a project – email-invite for editors, Publish for viewers and clients. - [Keyboard shortcuts](https://help.intangible.ai/learn-more/reference/keyboard-shortcuts.md): Every keyboard shortcut exposed in the editor. Mac and Windows variants listed where they differ. - [Supported file formats](https://help.intangible.ai/learn-more/reference/supported-file-formats.md): Which file formats Intangible accepts for import and exports for download. Plus what's not supported and what to do about it. - [System requirements](https://help.intangible.ai/learn-more/reference/system-requirements.md): Browser, GPU, network, and asset-size requirements for running Intangible smoothly. - [Glossary](https://help.intangible.ai/learn-more/reference/glossary.md): Every Intangible-specific term, defined. From Intangible agents and the canvas to Workspace, with cross-links to the relevant docs. - [FAQ](https://help.intangible.ai/learn-more/faq.md): Common questions, troubleshooting, and the honest list of what Intangible doesn't do today. - [Common questions](https://help.intangible.ai/learn-more/faq/common-questions.md): The questions that come up most often on support tickets and onboarding calls. Quick answers with links to the full pages. - [Troubleshooting Intangible agents](https://help.intangible.ai/learn-more/faq/troubleshooting-the-agent.md): What to do when Intangible agents say they are done before the work is on the canvas, change the wrong scene, skip your questions, stall on a step or spend more credits than you expected. - [Troubleshooting rendering](https://help.intangible.ai/learn-more/faq/troubleshooting-rendering.md): Why renders go wrong, and where to fix each kind of wrong. Stubborn extra objects, drifting characters, dark output, ignored references. - [Troubleshooting import](https://help.intangible.ai/learn-more/faq/troubleshooting-import.md): Common Smart Import problems and how to fix each one. Models in the ground, models the size of a building, wrong orientation. - [Known limitations](https://help.intangible.ai/learn-more/faq/known-limitations.md): What Intangible doesn't do. Useful for setting expectations on a brief, scoping a pitch, or knowing when to use external tools. - [Agents & MCP](https://help.intangible.ai/intangible-mcp-agents/intangible-mcp-agents.md): Connect Claude, ChatGPT, Codex, Grok, Muse, Gemini, Cursor, Perplexity or an open model to Intangible over MCP. Setup steps, then your first scene. - [Choosing a model](https://help.intangible.ai/intangible-mcp-agents/choosing-a-model.md): Which AI models work with Intangible over MCP, and how to pick one for a large build. - [Anthropic Claude](https://help.intangible.ai/intangible-mcp-agents/anthropic-claude.md): Intangible works with Anthropic's Claude. Claude builds 3D scenes in Intangible over MCP from claude.ai, Claude Desktop, Claude mobile and Claude Code. Apps, models and setup steps. - [Connect Claude](https://help.intangible.ai/intangible-mcp-agents/anthropic-claude/connect-claude-desktop.md): Connect Claude (claude.ai, Claude Desktop and Claude mobile) to Intangible's Model Context Protocol (MCP) server as a custom connector, then build 3D scenes from a chat. - [Connect Claude Code](https://help.intangible.ai/intangible-mcp-agents/anthropic-claude/connect-claude-code.md): Connect Claude Code to Intangible's Model Context Protocol (MCP) server with one command, then build 3D scenes from the terminal. - [OpenAI](https://help.intangible.ai/intangible-mcp-agents/openai.md): Intangible works with OpenAI's ChatGPT and Codex. GPT-6 models build 3D scenes in Intangible over MCP, including on a personal ChatGPT Plus plan. Apps, models and setup steps. - [Connect ChatGPT](https://help.intangible.ai/intangible-mcp-agents/openai/connect-chatgpt.md): Connect ChatGPT to Intangible's Model Context Protocol (MCP) server as a custom MCP plugin, then build 3D scenes from a chat. - [Connect Codex](https://help.intangible.ai/intangible-mcp-agents/openai/connect-codex.md): Connect OpenAI Codex to Intangible's Model Context Protocol (MCP) server with one command, then build 3D scenes from the terminal. - [xAI Grok](https://help.intangible.ai/intangible-mcp-agents/connect-grok.md): Intangible works with xAI's Grok. grok.com, Grok Bot and Grok Build build 3D scenes in Intangible over MCP, including on Grok's free plan. Apps, models and setup steps. - [Meta Muse](https://help.intangible.ai/intangible-mcp-agents/connect-muse.md): Intangible works with Meta's Muse. The Muse app (Muse Spark) and Muse Code (Muse Wonder) build 3D scenes in Intangible over MCP. Apps, models and setup steps. - [Google Gemini](https://help.intangible.ai/intangible-mcp-agents/google-gemini.md): Intangible works with Google Gemini: the Gemini app on personal Google accounts, and Gemini CLI. Apps, models and setup steps. - [NVIDIA Nemotron](https://help.intangible.ai/intangible-mcp-agents/nvidia-nemotron.md): Intangible works with NVIDIA Nemotron. Nemotron 3.5 Super VL builds 3D scenes in Intangible over MCP when run through Grok Build with NVIDIA's API. Models and setup steps. - [Cursor](https://help.intangible.ai/intangible-mcp-agents/connect-cursor.md): Intangible works with Cursor. Connect Cursor to Intangible's Model Context Protocol (MCP) server in mcp.json, then build 3D scenes from Cursor's Agent mode. - [Perplexity](https://help.intangible.ai/intangible-mcp-agents/connect-perplexity.md): Intangible works with Perplexity. Add Intangible's Model Context Protocol (MCP) server as a custom connector, then build 3D scenes from a Perplexity Computer task. - [Other MCP clients](https://help.intangible.ai/intangible-mcp-agents/connect-other-agents.md): Connect any other Model Context Protocol (MCP) client to Intangible: what the client needs and the values to enter. - [What your agent can do](https://help.intangible.ai/intangible-mcp-agents/what-your-agent-can-do.md): What an agent connected to Intangible's Model Context Protocol (MCP) server does in Build, Compose and Visualize, how it paces a long job, and where you finish by hand. - [Agent recipes](https://help.intangible.ai/intangible-mcp-agents/what-your-agent-can-do/agent-recipes.md): Three briefs to paste into Claude, ChatGPT or another MCP agent to build a 3D scene in Intangible, frame shots and render, with what to check after each. - [Blender MCP and Intangible MCP](https://help.intangible.ai/intangible-mcp-agents/what-your-agent-can-do/blender-mcp-and-intangible-mcp.md): Blender MCP and Intangible MCP side by side: what each server does, how to move a .blend model into Intangible as GLB, and which Intangible tool covers each Blender MCP job. - [Troubleshooting and FAQ](https://help.intangible.ai/intangible-mcp-agents/troubleshooting-and-faq.md): Fixes for connecting an AI agent to Intangible's Model Context Protocol (MCP) server: the server URL, supported clients, sign-in problems, approvals, and empty-scene issues. - [Teams & billing](https://help.intangible.ai/teams-and-billing/teams-and-billing.md): Workspaces, plans, invites, project ownership. Everything tied to who's on your team and what tier you're on. - [Workspaces](https://help.intangible.ai/teams-and-billing/workspaces.md): Personal workspace versus team workspace. What changes when you switch, and why team workspaces are the right home for shared client work. - [Create and invite](https://help.intangible.ai/teams-and-billing/create-and-invite.md): Make a team, add seats, send invites. The full setup flow for a multi-user workspace from scratch. - [Plans and billing](https://help.intangible.ai/teams-and-billing/plans-and-billing.md): Free, Explorer, Business plans. Payment methods, multiple owners, credit packs, annual discounts. - [Permissions](https://help.intangible.ai/teams-and-billing/permissions.md): Member versus Owner permissions on a team workspace. Who can edit projects, who can manage seats, who can change billing. - [Project ownership](https://help.intangible.ai/teams-and-billing/project-ownership.md): Transfer a project to another team member. The right tool when the original creator is leaving the team or handing off the lead. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation This site has an agentic ask interface you may use to query the documentation dynamically by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://help.intangible.ai/index.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.