> 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/get-started/readme.md). # Welcome to Intangible Describe what you want to make, add what you have, and Intangible builds the scene and renders the shots.

Welcome to Intangible

Describe what you want to make. Intangible builds the scene and renders the shots. You direct.

## What is Intangible? Intangible is one AI studio for images, video and 3D, in the browser. Describe your idea and watch agents build it out for you. Start on [Home](/canvas/home.md) with a prompt and your photos, PDFs or 3D files. Intangible [agents](/chat-agents-intangible/chat.md) write a brief you confirm, make the references and 3D models, build one 3D scene, place a camera for every shot and render the shots as images and video. Their work lands on the [canvas](/canvas/canvas.md), where every reference, model, scene, shot and render is a card you can trace back to where it came from. Direct the agents in plain words from the chat panel, or step into [Build](/build/build.md), [Compose](/compose/compose.md) or [Visualize](/visualize/visualize.md) to change anything by hand. Every shot comes from the same scene, so the set, product and characters carry across shots. ## How is Intangible different? Prompt-only image and video tools generate each shot from text, so a character drifts between shots and the composition is hard to pin down. Intangible builds a 3D scene first and renders every shot from it. See [How is this different from prompt-only tools?](/learn-more/concepts/how-the-visualizer-thinks.md#how-is-this-different-from-prompt-only-tools-like-midjourney) * **Consistent characters and products across shots:** every shot renders from the same 3D scene, and an [image reference](/learn-more/concepts/image-reference.md) bound to an object keeps its look in every render. * **Camera moves you control:** place and keyframe a real camera in [Compose](/compose/compose.md) for a push-in, orbit, crane or tracking shot, instead of describing the move in a prompt. * **Agents that build the 3D scene for you:** describe the idea in the [chat panel](/chat-agents-intangible/chat.md) and the agents write the brief, build the scene, place the cameras and render the shots. No 3D experience is needed to start, and you can take over by hand at any step. * **Every render traced to its scene:** each render on the [canvas](/canvas/canvas.md) traces back to the scene and shot it came from, so you change the scene and render again rather than re-prompt from scratch. * **Your own 3D models and CAD exports:** import FBX, OBJ or GLB [models](/build/import-your-own-models.md) and [Gaussian splats](/build/import-gaussian-splats.md), or bring scenes from [Blender, Maya, Houdini](/learn-more/how-to/import-from-blender-maya-or-houdini.md) or Unreal, then attach a photo of the real product as its reference. * **Image and video models in one place:** pick the [model](/visualize/ai-models.md) for each shot in Visualize, and switch without rebuilding the scene. {% embed url="" %} ## Watch your idea build itself 1. **Describe it on Home.** Type the idea and add your photos, PDFs or 3D files. See [Home](/canvas/home.md). 2. **Answer a few questions.** With Guide me, the agents ask what they need, then write a brief you confirm. See [The brief](/canvas/the-brief.md). 3. **Get references and models.** The agents make reference sheets and place a 3D model for each subject, usually from the asset library. See [What Intangible agents build](/canvas/what-intangible-agents-build.md). 4. **Create 3D scenes, animate and get shots.** They build the 3D scene, add motion where the brief calls for it, and place a camera for every shot. See [Build](/build/build.md). 5. **Render.** A keyframe for every shot in one pass, then video. See [Batch visualize](/canvas/batch-visualize.md). 6. **Edit and iterate.** Mark up a render to fix one frame, or change the scene and render again. See [Edit media](/canvas/edit-media.md). 7. **Export the asset pack.** Drag the renders, references and models you want onto an asset pack and download one ZIP. See [Asset packs](/canvas/asset-packs.md).

What you bring (a prompt, photos, PDFs, 3D files), the AI builds one 3D scene, then renders stills, video, 3D models and an asset pack

**Describe your idea and watch it build.** Try Intangible free ## Start here


Your first project	Describe it, confirm the brief, and let Intangible build it, from one prompt to video and an asset pack.
The canvas	The whole project on one screen. Every brief, reference, scene and render is a card.
Chat	Direct Intangible agents in plain words. They build the scene and render the shots, from the canvas or Build.

{% hint style="info" %} **Found a bug?** Tell us from inside Studio: click the help icon (?) in the top-right toolbar, pick **Report an Issue**, describe what happened and click **Send report**. It takes a few clicks, and a screenshot of the Studio tab can go with it. See [Report a bug or get help](/get-started/help-and-feedback.md). **What changed lately?** [What's new](/get-started/whats-new.md) lists every release, newest first, with a link to the page for each change. {% endhint %} ## Work by hand


Build mode	Create the scene. Upload CAD, references, characters. The model honors what you imported.
Compose mode	Direct the shot. Place cameras, frame the moment. Spatial input the model can't override.
Visualize mode	Render the draft. The shot you composed, rendered in full and ready for client delivery.

## Build the scene


References	Attach a photo to a 3D object. The render comes back as the actual product, not a generic version. Object fidelity, in one step.
What the agents do in Build, Compose and Visualize	Prompt for a city block, a tropical forest, a living room. The agents collect the objects and arrange them.
Import your own models	FBX, OBJ, GLB, GLTF. Bring your client's actual product with scale and orientation correct.

## Compose the shot


Shots	Add, duplicate, reorder. Each shot saves its own camera, lens, aspect, and timeline.
Camera controls	Free cam to find an angle, fine-tune to nail it. Plus game-controller support.
Animation	Keyframe cameras, characters, and props per shot.

## Render and ship


Models	Every image and video model in the visualizer, with guidance on when to reach for each.
Style presets	Preloaded style looks – photoreal, illustration, storyboard – plus lighting presets for atmosphere and time of day.
Export Video	Bundle every shot in the sequence into one continuous file ready for client delivery.

## How it works


How Intangible works	How the canvas, the agents and Build, Compose and Visualize fit together on a project.
How the visualizer thinks	Why a 3D scene plus a structured prompt beats text alone.
Credits and tokens	What costs credits, where to see your balance, and how to think about cost per shot.

## Run your team


Workspaces	Personal versus team. What changes when you switch and which assets stay where.
Plans and billing	Free, Explorer, Business tiers, plus credit packs and payment options.
Permissions	Member versus owner. Who can edit, who can manage seats, who handles billing.

## Look it up


Keyboard shortcuts	Every shortcut, grouped by mode. The lookup table for fast keyboard work.
Common questions	Credits, plans, AI behavior, workflow. The top-of-inbox set with quick answers.
Known limitations	What Intangible doesn't do today, plus the workaround we recommend for each gap.

--- # 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/get-started/readme.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.