> ## Documentation Index
> Fetch the complete documentation index at: https://support.myapps.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Generate

> The main studio for images, video, audio, and 3D

**Generate** is the core of Pixio. You pick a model, fill in its inputs, and run it. Results land in your history, your assets, and your prompt history automatically.

## Layout

<CardGroup cols={3}>
  <Card icon="sliders" title="Left — controls">
    Model list and the generation form. The form changes to match whichever model you select.
  </Card>

  <Card icon="image" title="Center — preview">
    Full-size view of the current result. Images, video, audio, and 3D all preview in place.
  </Card>

  <Card icon="clock-rotate-left" title="Right — history">
    Every generation, newest first, with chained actions on each one. Scrolls to load more.
  </Card>
</CardGroup>

## The top bar

Alongside **Home**, **Create**, **Analytics**, **My Assets** and **Prompt History**, three controls sit to the right of the navigation:

| Control | What it does |
| - | - |
| **Pixio Legacy** | Brings your work across from Pixio v1 — **Sync Prompts** and **Sync Trained LoRAs**. Run it once if you're coming from the old app. |
| **Prompt Optimizer** | Rewrites a prompt for better results. Available on **paid plans**; on Free you're prompted to upgrade. |
| **Your plan** | Shows your current subscription (e.g. *Maker Monthly*) |

Your credit balance and profile menu sit at the far right.

<Info>
  **Pixio Legacy** is the migration path from v1. Prompts and trained LoRAs don't move across on their own — sync them and they appear in [Prompt History](/library/prompt-history) and in the LoRA picker.
</Info>

## Choosing a model

Models are grouped by the family that makes them, and each entry shows:

* **What it does** — text-to-image, image-to-video, video-to-video, lipsync, text-to-3D, and so on
* **Credit cost** — per run, or per second for models billed by duration
* **Access** — whether your plan can run it

Over 500 models are available. See [Models](/models) for how to narrow that down.

The picker has **Search models…**, a type filter (**All types**), a sort (**Default**), and a **Maker** toggle to show only Maker-eligible models. Below that, **Favorites** first, then **All Models** grouped by family with a count per family.

Credits show as an exact number for fixed-price models and with a `~` for models whose cost varies with duration or resolution.

### Favorites

Tap the star on any model to favorite it. Favorites are saved to your account and pinned in their own section at the top of the picker, so the handful of models you actually use stay one click away.

### Plan access

Your plan controls which models you can run. Models outside your plan are marked in the list. Some models are free on specific plans, so they don't draw down your balance at all. Details in [Credits & Plans](/credits).

## The form

Each model exposes its own inputs — prompt, image size, quality, output format, duration, resolution, seed, style, guidance. **Every input has a Field information tooltip** explaining what it does and what range it accepts, so you don't have to guess.

At the bottom of the form, above the Generate button, you'll see:

| | |
| - | - |
| **Estimated cost** | What this run will cost, updating as you change settings |
| **Maker full-discount runs (24h)** | On Maker, how many full-discount runs you have left in the rolling 24-hour window for this model |

<Info>
  The Maker discount counter is per rolling 24 hours, not per calendar day, and applies to models in a capped group. When it's used up the model still runs — it just draws on credits. See [Maker Mode](/advanced/maker-mode).
</Info>

### Using your own images and video

Models that take a reference image, source video, or audio track let you either:

* **Upload a file** directly from the form, or
* **Pick from your assets** — anything you've generated or uploaded before

Uploads are stored against your account and show up in the **Uploads** tab of [My Assets](/assets), ready to reuse.

### LoRAs

If you've trained a custom LoRA, models that support it expose a LoRA picker in the form. Trigger your LoRA by including its trigger word in the prompt. LoRA training requires Premium or above.

## Running a generation

<Steps>
  <Step title="Submit">
    The run is created immediately and appears in the right column as **processing**. **Estimated cost** shows what it will cost before you commit.
  </Step>

  <Step title="Wait">
    You can navigate away, start another generation, or close the tab — the job keeps running. Images are usually seconds; video can take several minutes.
  </Step>

  <Step title="Result">
    On success the output appears in the preview and history. On failure you are **not charged**.
  </Step>
</Steps>

### Not enough credits

If your balance won't cover the run, Pixio tells you before starting it and points you at [Billing](/credits) to top up or upgrade. Nothing is queued and nothing is charged.

## Chained actions

This is the part worth learning. Hover any finished item in the right column and you can push it straight into the next model — no downloading, no re-uploading.

**From an image**

| Action | What it does |
| - | - |
| **Regenerate** | Run again with the same prompt and inputs |
| **Create Video** | Animate the still into a video |
| **Next Frame** | Continue the sequence from this frame |
| **Create 3D Model** | Turn the image into a 3D mesh |
| **Upscale** / **Image Upscale** | Increase resolution |
| **Remove BG** | Cut out the background |
| **Photo Restoration** | Repair and clean up a photo |
| **Edit Image** | Make a targeted edit from an instruction |
| **Add Lipsync** | Drive a face from audio |
| **Generate Voice** | Produce a voice track |

**From a video**

| Action | What it does |
| - | - |
| **Upscale Video** | Increase resolution |
| **Caption Video** | Burn in captions |
| **Lipsync Video** | Sync mouth movement to audio |
| **Edit Video** | Make a targeted edit from an instruction |
| **Remove BG** | Cut the background out of the clip |
| **No Watermark** | Produce a clean version |

**From a 3D model**

**Refine 3D model** improves mesh quality on models that support refinement.

<Tip>
  The cheapest way to get good video: generate several inexpensive images, pick the best one, then chain **Create Video** from it. Iterating at image prices instead of video prices saves an enormous number of credits.
</Tip>

## Your results

Every finished generation is available in three places automatically:

* **History** — the right column, newest first
* **[My Assets](/assets)** — your full library, with uploads on a second tab
* **Prompt History** — every prompt you've used, searchable and reusable

From the preview or history you can **download** a result, **publish** it to the public gallery, **unpublish** it later, or **delete** it.

<Info>
  Generations belong to the account that made them. On a team account, everyone on the team shares the same assets and the same credit pool.
</Info>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.