# Flux Kontext

## What is Flux Kontext?

**Flux Kontext** is a powerful multimodal AI image editing and generation model developed by Black Forest Labs. It combines both **text and visual context**, enabling users to generate new images and edit existing ones with natural language. This model excels at maintaining **character consistency**, performing **precise local modifications**, and offering **fast interactive speeds**, making it ideal for creative projects that require quick iteration and high-quality results.

{% hint style="info" %}
You can upload a picture and ask it to change something, such as clothes, background, or colors, and it will do that while keeping the rest of the image the same.
{% endhint %}

#### Key benefits include:

* **In-Context Image Generation**: Create or modify images using both text prompts and reference images for more nuanced results.
* **Instruction-Based Editing**: Make precise edits to specific parts of an image without disturbing the overall composition.
* **Character Consistency**: Maintain the same character across different edits or scenes—ideal for projects requiring consistent visual identities.
* **Fast & Interactive**: Ideal for real-time creative workflows, offering quick generation and modification speeds.

## How to use?

{% stepper %}
{% step %}
**Select Edit Mode:** Open **ImagineArt** and select **Edit Mode** to start using **Flux Kontext** for image editing or generation.

<figure><img src="/files/zNfYbbM4tMNsKgqtWrEN" alt=""><figcaption></figcaption></figure>

<br>
{% endstep %}

{% step %}
**Select Flux Kontext as Your Model:** Choose **Flux Kontext** as the model for your editing project. This will enable you to leverage its multimodal architecture for precise, context-aware edits.

<figure><img src="/files/jv1zPtvlVEA4hduwNkXE" alt=""><figcaption></figcaption></figure>

{% endstep %}

{% step %}
**Upload Reference Images (Up to 4):** Upload up to **4 reference images** to guide the AI in generating or editing your content. These images

<figure><img src="/files/3AdWnocNSSnGdsOqpXSL" alt=""><figcaption></figcaption></figure>

{% endstep %}

{% step %}
**Use Prompts for Specific Changes:** Input text prompts to specify which elements in your image need modification. Whether it’s changing the background, adjusting the lighting, or modifying the character’s pose, **Flux Kontext** interprets your commands and applies the changes.

<figure><img src="/files/e2ovhWIv6Tct3hY8NSWq" alt=""><figcaption></figcaption></figure>
{% endstep %}

{% step %}
**Choose Aspect Ratio and Number of Images to Generate:** Select the aspect ratio that suits your project and specify the number of images you’d like to generate (e.g., 1-4 images per batch).
{% endstep %}

{% step %}
**Click Create:** Once your reference images are uploaded and your prompts are written, click **Create** to generate the new image. **Flux Kontext** will process your inputs and deliver a refined visual based on the combination of your reference and text description.
{% endstep %}

{% step %}
**Click Create:** After refining your prompt, click **Generate** to see the AI-powered transformation of your image.

<figure><img src="/files/nNB8TB3H3tXeGvAtlL1s" alt=""><figcaption></figcaption></figure>
{% endstep %}
{% endstepper %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://help.imagine.art/creative-suite/edit/flux-kontext.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.