> 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/deliver.md).

# Deliver

Turn shots into keyframes and video, fix what is not right, and hand off everything as an asset pack or a published project.

The scene is built and the cameras are placed. Delivering means turning that into pictures and footage someone else can use, in four steps.

## 1. Keyframes for every shot

Select the scene card and click **Batch visualize**. The panel has one prompt per shot, filled in from what is in each shot. A prompt can come back empty; **Generate** stays off until every shot has one, so write the missing ones. Then every shot gets a keyframe in one pass, rendered through its own camera, so the set and subjects stay consistent across the sequence. The renders land in a **Visualizations** group. See [Batch visualize](https://help.intangible.ai/canvas/batch-visualize.md).

## 2. Video from the keyframes

In the chat panel, name the shots you want moving: "Turn the render of shot 03 into a short video." Before starting, the agents show a choice card listing each option's model, length and cost; your pick starts the video, and it lands in the shot's Visualize media list and in **Visualizations**. A video animated from a render invents its motion, so if the clip must move the way the scene does, pick the option that follows the scene's motion. See [Keyframes to video](https://help.intangible.ai/canvas/keyframes-to-video.md).

## 3. Fix what is not right

For a frame that is nearly right, open **Edit image** or **Edit video** on its card, draw over the part to change and say what to change. See [Edit media](https://help.intangible.ai/canvas/edit-media.md).

## 4. Pack it up

Click **Add an asset pack** in the bottom toolbar, then drag the renders, videos and anything else you want onto the pack. Click **Generate**, then **Download**. You get one ZIP with what you put in, in folders by type, with a manifest. See [Asset packs](https://help.intangible.ai/canvas/asset-packs.md).

## Present instead of hand off

To show the work rather than send files, publish the project and share the link. See [Publish](https://help.intangible.ai/publish/publish.md).

## Related

* [The canvas](https://help.intangible.ai/canvas/canvas.md)
* [Credits and tokens](https://help.intangible.ai/learn-more/concepts/credits-and-tokens.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/get-started/deliver.md?ask=<question>&goal=<user_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.
