> 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/canvas/batch-visualize.md).

# Batch visualize

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.

Batch visualize renders one image for every shot in a scene in a single pass. It is the fastest way to see a whole sequence before you spend time on any one shot: every shot gets a keyframe, and every keyframe comes from the same 3D scene, so the set, the subjects and the light stay consistent from frame to frame.

## What it does

Each shot renders through its own camera, at its own aspect ratio, from a frame inside that shot's range. The prompt for each shot comes from its auto-prompt, the description Intangible writes from what the camera sees. Each image is saved to its shot and shows in the **Visualizations** group with the scene's other renders.

## How to use it

1. **Select the scene card** on the canvas.
2. **Click Batch visualize** in the scene card's toolbar. The button is dimmed while the scene has no shots.
3. **Check the prompts.** The **Scene** tab lists every shot with the prompt it will render with. A shot that has no auto-prompt yet gets one when the panel opens, so give the list a moment to fill in. A prompt can come back empty, and **Generate** stays off until every shot has one, so write the missing ones. Edit any prompt in place; the edit is saved to that shot.
4. **Set a look for the whole scene (optional).** The **Style** and **Lighting** tabs work like the ones in Visualize, except that a preset you pick here applies to every shot in the scene. If the shots currently use different presets, the row reads **Mixed styles** or **Mixed lighting**.
5. **Pick quality and model** in the footer. These apply to this batch only and do not change the model each shot has saved.
6. **Click Generate.**

You can close the panel while the batch runs. Each result lands on its shot when its job finishes.

## Credits

The batch costs what the same renders would cost one by one. If the team does not have enough credits for the whole batch, the usual out-of-credits message appears and nothing is submitted. See [Credits and tokens](https://help.intangible.ai/learn-more/concepts/credits-and-tokens.md).

## Chat with Intangible instead

You can also ask for renders in the chat panel, for example "render keyframes for every shot in scene 01". The agents render each shot the same way the panel does: through its own camera, at a frame inside the shot, with its own prompt.

## Limits

* One model and one quality setting per batch. To give one shot a different model, render it on its own from Visualize.
* The batch covers one scene at a time.

## Related

* [Generate image](https://help.intangible.ai/visualize/generate-image.md) – render one shot with full control in Visualize.
* [Auto-prompt](https://help.intangible.ai/visualize/auto-prompt.md) – where each shot's prompt comes from.
* [Style presets](https://help.intangible.ai/visualize/style-presets.md) and [Lighting presets](https://help.intangible.ai/visualize/lighting-presets.md)
* [Keyframes to video](https://help.intangible.ai/canvas/keyframes-to-video.md) – turn a keyframe into a moving shot.
* [Deliver](https://help.intangible.ai/get-started/deliver.md) – where batch visualize fits in a project.


---

# 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/canvas/batch-visualize.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.
