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

# Selfie

> Selfie is an image-to-image portrait model on Mage, unlimited from Pro, with LoRAs, Textual Inversions, and negative prompts.

Selfie is an image-to-image portrait model. It needs an input image and works from it, takes LoRAs, Textual Inversions, and negative prompts, and runs unlimited from Pro.

## Overview

| Detail         |                                    |
| -------------- | ---------------------------------- |
| Type           | Image                              |
| Origin         | Mage model, available only on Mage |
| Models         | Selfie                             |
| Unlimited from | Pro                                |

## Unlimited generation by plan

Which plan runs each resolution unlimited, at the model's base settings. Gems means that setting always costs Gems on that plan.

| Model  | Setting       | Basic | Pro       | Pro Plus  | Max       |
| ------ | ------------- | ----- | --------- | --------- | --------- |
| Selfie | Base settings | Gems  | Unlimited | Unlimited | Unlimited |

Add-ons such as LoRAs, ControlNet, extra reference images, or reference videos may raise a run's price and move it to a higher plan or to Gems.

## What it supports on Mage

| Feature                   | Support |
| ------------------------- | ------- |
| Characters and References | No      |
| Reference images          | Up to 1 |
| LoRAs                     | Yes     |
| Textual Inversions        | Yes     |
| Negative prompts          | Yes     |
| Edits an input image      | No      |

## Best for

* Portrait variations from a photo you supply
* Stylizing a portrait with a LoRA

## An example prompt to start from

```text theme={null}
portrait, soft window light, film grain, shallow depth of field
```

## Limitations

* It requires an input image and does not generate from text alone.
* No Characters or References.