> For the complete documentation index, see [llms.txt](https://help.intangible.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.intangible.ai/learn-more/faq/common-questions.md). # Common questions The questions that come up most often on support tickets and onboarding calls. Quick answers with links to the full pages. The questions that come up most on support tickets and onboarding calls, each with a short answer and a link to the full page. ## Canvas and Chat ### Do I need 3D experience? No. Describe what you want on Home and the agents build the 3D scene for you. Choose **Guide me** and the brief plays back what they understood before they build. See [Home](/canvas/home.md). ### Do I need to install anything? No. Intangible runs in the browser, 3D included. See [System requirements](/learn-more/reference/system-requirements.md). ### Can I use Intangible from Claude or ChatGPT? Yes. Connect Claude, ChatGPT, Codex, Grok, Muse, Gemini, Cursor or Perplexity to Intangible's MCP server, then describe the scene in chat and the agent builds it in the Studio tab open in your browser. Any other MCP client connects if it supports remote servers over streamable HTTP with OAuth sign-in. See [Agents & MCP](/intangible-mcp-agents/intangible-mcp-agents.md). ### Can I drive Intangible from code? Yes, through Intangible's MCP server at `https://mcp.intangible.ai/mcp`. Any MCP client that supports remote servers over streamable HTTP with OAuth sign-in connects, with nothing to install and no API key. For many objects or a procedural layout, the agent writes a **scene script**: code, math included, that builds or edits the scene, and the MCP server runs it in a sandbox. See [3D scenes as code](/intangible-mcp-agents/intangible-mcp-agents.md#3d-scenes-as-code). ### Can I bring my own CAD or 3D model? Yes. Import GLB, GLTF, DAE, FBX, PLY or OBJ models from the asset library in Build, and convert a STEP, STL, SketchUp or Revit file to one of those first. Attach a photograph of the real product as the model's reference image to guide its surface in the render. See [Render a CAD file with AI](/learn-more/how-to/render-a-cad-file-with-ai.md). ### Where is Chat? In the bottom-right corner of the canvas and of Build. Click the Chat bar to open the chat panel. Compose and Visualize have no chat panel; ask from the canvas or Build for work in those modes. See [Chat with Intangible](/chat-agents-intangible/chat-with-intangible.md). ### Does the chat remember my earlier messages? Within a project, yes: the conversation survives a page reload, is shared between the canvas and Build, and is there again when you come back to the project. Each person has their own conversation on a project. Chats from before the canvas, which were kept one per scene, are still saved but don't show in the chat panel. In a long conversation, the oldest turns drop out of what the agents read. See [Chat with Intangible](/chat-agents-intangible/chat-with-intangible.md#where-the-conversation-lives). ### Do chat messages cost credits? Yes. Messages to the agents use credits, except with GPT-6 Luna, which is free. The references, renders and videos they make always cost credits. See [Credits and tokens](/learn-more/concepts/credits-and-tokens.md). ### Should I choose Guide me or Skip? Choose **Guide me** when you want to agree the plan first: the agents ask a few questions, then write a brief you confirm. Choose **Skip** when your prompt already says what you want: the agents skip the questions and start building straight away. A brief can still land on the canvas as they build. They may also start a render without asking, which spends credits. See [Home](/canvas/home.md). ### Why do new angles of my product stay consistent? Every shot renders from the same 3D scene. Each object in it carries its geometry, a description and its reference image, so a new camera keeps the object right instead of redrawing it from a flat picture. See [How Intangible works](/learn-more/concepts/how-intangible-works.md#one-3d-scene-under-every-shot). ### If I change the scene, do renders I already made change? No. Renders you make next follow the changed scene; renders you already made stay as they are. See [Troubleshooting Intangible agents](/learn-more/faq/troubleshooting-the-agent.md#fix-it-where-it-starts). ### Can I undo what the agents did? Scene edits, yes: press Cmd+Z (Mac) or Ctrl+Z (Windows) in any mode, and it undoes changes the agents made too. Undo does not cover many canvas card actions, such as placing uploads, and a page reload clears it. See [Known limitations](/learn-more/faq/known-limitations.md#undo-does-not-cover-canvas-card-moves). ### Can I attach a canvas card to a message? No. Name the card in your message instead, the way the canvas names it: "shot 02's keyframe", "scene 01". The chat panel **+** attaches images. See [Chat with Intangible](/chat-agents-intangible/chat-with-intangible.md#point-at-what-you-mean). ### Can two people work on one project? Yes. Invite them from **Share** > **Team** and they get edit access. Edits are not live multiplayer, so agree who edits which assets, and avoid editing the same ones at once. See [Sharing and collaboration](/learn-more/reference/sharing-and-collaboration.md). ### Where are comments? Comments come from viewers of a published project. Read them in Visualize: click **Comments** at the top right, between the notifications bell and the help icon. In a window narrower than 800 pixels it is in the **More** menu (three dots). See [Publish](/publish/publish-tab.md#posting-a-comment). ### Can I export a splat? Yes, as its original file. Select the world card on the canvas and click **Download**. A GLTF export of the scene leaves splats out. See [Import Gaussian splats](/build/import-gaussian-splats.md#limits-and-known-issues). ### Can I stitch videos together? Not in Edit. To join shots into one video, export the scene or the sequence: the export cuts the shots together in timeline order. See [Export Video](/publish/export-video.md). For titles, transitions, sound or a finer cut, download the clips and edit them in the video editor you already use, such as Premiere Pro, DaVinci Resolve, Final Cut Pro or CapCut. ### Can I edit an image I uploaded? Yes. Select it and click **Edit image**, or ask the agents in the chat panel: name the file and say what to change. Either way the edited copy lands as a new card and the original stays as it was. Uploaded videos can't be edited. See [Edit media](/canvas/edit-media.md#edit-an-image-you-uploaded). ## Credits ### What does a render cost? Costs vary by model and resolution. The credits button at the top right shows your remaining balance. For a breakdown by action type, open **Usage** from the profile menu. A 1K image is among the cheapest actions; a 2K video is the most expensive. See [Credits and tokens](/learn-more/concepts/credits-and-tokens.md). ### What happens when I run out of credits? A paywall appears when you click Generate or attempt a paywalled feature. On a paid plan, buy a credit pack, upgrade, or wait for the cycle to roll over. On Free, subscribe to a plan to get monthly credits and the option to buy packs. See [Plans and billing](/teams-and-billing/plans-and-billing.md). ### Do credit packs expire? Yes, one year after purchase. Until then they carry over from cycle to cycle and get used after the cycle's allotment runs out. See [Plans and billing](/teams-and-billing/plans-and-billing.md). ## Plans ### Can I try before I subscribe? Yes. The Free tier gives you enough credits to walk through [Your first project](/get-started/your-first-project.md) and try most features. See [Sign up and set up](/get-started/sign-up-and-set-up.md). ### Do I need Business for everything? No. Free covers most of the product, but Generate 3D Asset isn't available on it – that unlocks on Explorer and up. Explorer has everything except multi-seat teams; Business and Enterprise add teams. Solo creators usually do well on Explorer. See [intangible.ai/pricing](https://www.intangible.ai/pricing) for the current matrix. ### Can I downgrade later? Yes. Downgrades take effect at the next billing cycle; the current cycle keeps the higher tier's features. Your existing credit balance is preserved into the new tier – monthly credits don't accumulate across cycles, but whatever you have at downgrade carries over. ## Teams ### How do I work with another person on the same project? Two paths. For ongoing collaboration on multiple projects, set up a team workspace with [Create and invite](/teams-and-billing/create-and-invite.md). For one-off review of a specific project, invite them by email from **Share** > **Team**. See [Sharing and collaboration](/learn-more/reference/sharing-and-collaboration.md). ### Can a contractor join a team without a Business account of their own? Yes. Send them an invite from your Business team; they accept and join your team. Their own account stays free until they want their own Business plan. ### Can I move a project from personal to a team? Not directly. Recreate it in the team workspace. ## AI behavior ### Why is my hero asset rendering as something generic? The model isn't being given the specific reference. Attach an image of the actual asset to the object via Object Details → Image reference in Build mode. See [Image reference](/learn-more/concepts/image-reference.md). ### The same character looks different in every shot. How do I fix that? Two practices that compound: give the character a plain object name and attach image references to it. A descriptive name like "pirate captain" pulls the model toward a generic stereotype, while a plain name like "Mark" lets the attached reference image define the look. See the tip on character consistency in [Image reference](/learn-more/concepts/image-reference.md). ### A render keeps including something I don't want. If the unwanted element is in the 3D scene, hide or delete it in Build mode and regenerate. If it's something the model is hallucinating, edit the rendered image directly with **Edit image** ([Edit images](/visualize/edit-images.md)) or download, fix in Photoshop, re-upload as a start frame ([First and last frame](/visualize/first-and-last-frame.md)). ### Why don't the agents find my imported model? The agents find imported models by their names and descriptions. A model named "object-12" won't answer to "the green Bronco". Rename and describe it in [Object details](/build/object-details.md), or place it by hand. See [Custom assets](/chat-agents-intangible/in-the-modes.md#custom-assets). ## Workflow ### The animation I authored isn't showing up in the render. You probably authored it in Build mode. Animation only commits to a shot, and that requires Compose mode with a shot active. See [Animation and shot time](/learn-more/concepts/animation-and-shot-time.md). ### Can I bring a camera move in from Blender? Bring the scene in as GLB or FBX, then rebuild the move in Compose. With a shot active, set the camera one way at one moment, change it at a later moment, and Intangible interpolates between. Position, rotation, lens and aim target all keyframe, and smooth interpolation is on by default. Import brings geometry, and skeletons for rigged models; the camera move is built on the scene timeline. See [Animation](/compose/animation.md) and [Import from Blender, Maya or Houdini](/learn-more/how-to/import-from-blender-maya-or-houdini.md). ### Can I type exact camera position and rotation values? Yes. Select the camera in Build or Compose and click **Transform** on the toolbar that appears beside it. Type **Position** X, Y and Z and **Rotation** X, Y and Z in degrees; press Enter and the camera moves. A camera bound to an aim target takes its rotation from the target, so move the target to turn it. An agent connected over MCP sets the same values by coordinates in a scene script. See [Aim Camera and Target](/compose/aim-camera-and-target.md) and [3D scenes as code](/intangible-mcp-agents/intangible-mcp-agents.md#3d-scenes-as-code). ### Does Intangible save my project automatically? Yes. Every change saves as you work, with no save button. If the connection drops, the changes wait in your browser and send when it comes back, and leaving the page while anything is unsaved asks you first. ### Can I restore an earlier version of a project? Yes. Intangible backs up projects as periodic snapshots, and support can restore one for you. Use **Report an Issue** in the help menu to ask, naming the project and roughly when it was last right. Snapshots are taken at intervals, not on every change, so there is no change-by-change version history; for a step back within a session, use undo. ### I can't find an object I placed. Open the [Scene Outliner](/build/scene-outliner.md), find it by name, press `F` to frame the camera on it. Common cause: the object spawned outside the camera frustum and you didn't notice. ### I scaled an object to zero and now I can't select it. Open the [Scene Outliner](/build/scene-outliner.md), find the object by name. From there you can rescale it via the gizmo's white center cube or by dragging a fresh copy of the asset from the Asset Library to replace it. ## Outputs ### Where do my renders live? On the canvas, renders from your shots land in **Visualizations**, newest first. In Visualize, each shot's renders sit in the gallery to the right of the viewport; switching shots shows a different gallery. See [Groups and cards](/canvas/groups-and-cards.md) and [Managing outputs](/visualize/managing-outputs.md). ### Do renders keep going if I close the tab? Yes. Image and video generations run on Intangible's servers, so closing the tab or letting the laptop sleep doesn't stop one. A canvas generation saves to your team's library on the server. A render from a shot lands in that shot's gallery when you next open the project. For a shot render, the browser sends a capture of the shot through its camera, the prompt, the reference images on its objects and their details. ### What can I export? Renders as PNG or JPEG, video as MP4, and the 3D scene as GLB, GLTF or USD for Unreal Engine, Maya or Houdini. Scene exports keep the hierarchy, transforms and cameras. See [Export formats](/publish/export-formats.md). ### Can I download multiple renders at once? Yes, as an asset pack. Click **Add an asset pack** in the canvas's bottom toolbar, drag the renders, videos and anything else you want onto it, then click **Generate** and **Download**. You get one ZIP of what you put in. The Visualize gallery downloads one render at a time. See [Asset packs](/canvas/asset-packs.md). ### Why is my exported video lower resolution than I expected? [Export Video](/publish/export-video.md) downloads each clip at the resolution it was rendered at. In a scene or sequence export, the joined video takes the resolution of the first video in the export, and the other shots are scaled to fit it. If you want a higher-resolution version of any clip, re-render that clip at a higher resolution before exporting. ## Rights and privacy ### Can I use Intangible renders commercially? Yes, on a paid plan. You own the images, videos and 3D scenes you make in Intangible, and Intangible doesn't claim ownership of them. Commercial use is included on Explorer, Business and Enterprise. Library 3D models in a render may carry their own license terms, and each AI model provider's own terms also apply. See the [Terms of Service](https://www.intangible.ai/terms-of-service). ### Is my uploaded client work used to train AI models? On Free, Explorer and Business, Intangible may use what you upload and make to improve the service, which includes training its models. On Enterprise, it doesn't train on your team's inputs or outputs unless your agreement allows it. On every plan you own your content, and Intangible won't publish it as a standalone work or name you as its source without your permission. For the terms by plan, see section 5.6 of the [Terms of Service](https://www.intangible.ai/terms-of-service); for security details, see [trust.intangible.ai](https://trust.intangible.ai). ## Browser and performance ### Why is the viewport stuttering? Most likely browser memory pressure or a complex scene. Close other tabs, lower the **Studio Graphics** tab settings (Ambient Occlusion off, Viewport maximum object count reduced), restart the browser. See [Account and settings](/learn-more/reference/account.md) and [System requirements](/learn-more/reference/system-requirements.md). ### Should I use Chrome or Safari? Either. Chrome and Safari are the two officially supported browsers. Other browsers run standard compatibility checks but aren't actively QA'd. {% hint style="info" %} **Still stuck, or think it's a bug?** Report it from inside Studio: click the help icon (?) in the top-right toolbar and pick **Report an Issue**. Describe it, click **Send report** and share the Studio tab for a screenshot. See [Report a bug or get help](/get-started/help-and-feedback.md). {% endhint %} ## Related * [Troubleshooting rendering](/learn-more/faq/troubleshooting-rendering.md) * [Troubleshooting import](/learn-more/faq/troubleshooting-import.md) * [Known limitations](/learn-more/faq/known-limitations.md) * [Report a bug or get help](/get-started/help-and-feedback.md) --- # 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 If you need additional information that is not directly available in this page, you can query the documentation 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/learn-more/faq/common-questions.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. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.