How to Use Kapwing's AI Image Generator (Kai)

Last updated on Nov 11, 2025

Kapwing's AI Image Generator any creator to jump into the studio and transform ideas into images in seconds.

You can use a reference image or start from scratch, then refine every generation with our AI chatbot.

How to Create an Image in the AI Image Generator

1. Access the AI Image Generator:
a) In Workspace by clicking "Generate" and then writing a prompt for an image in Kai
b) In Studio click the easel icon in the top bar to open Kai or type your desired image into the text box in the empty Studio view

2. Generate an Image: In Kai you can simply use the chat flow to request an image.

3. Edit the Image: Kapwing will generate an image. If you are not satisfied, you can review your prompt and try again. After the image is to your liking, you can add it to your canvas to edit further. You can upscale your AI-generated image into a high-resolution version using the ‘Enhance’ button in the canvas, play with the saturation, add text and so much more.

5. Save and Export: Lastly, you can save the image downloading directly within Kai or adding the image to a Kapwing project to edit then export. By exporting the project or saving it to your version history in Kapwing, you’ll be able to return to the image even if you delete it from your media library.

Generate an Image

Reference Images

In Kai, you will see the option to "attach media" within the chat box. When you have an image you want to use to help the AI generate your content, you want to ensure you use a clear and high-quality reference image. If you have multiple images, you can also upload all of them to help the AI gather different angles and perspectives as needed for your final result.

Image Prompting

Kapwing automatically refines your prompt behind the scenes to ensure it’s fully optimized for the LLM.

However, the more detail you provide, the easier it is for the AI to precisely match your vision. For best results, structure your image generation prompt using the included formula:

Style + Character/Object + Verb + Surroundings

Detailed prompts yield better results. For example, instead of "cat," try "a fluffy orange cat sitting on a windowsill with sunlight streaming through."

Here’s an overview of the main elements to consider: Composition, Atmosphere, and Creative Direction.

An infographic that gives an example of an advanced AI prompt with color coding that shows which segment of the prompt is which category — When writing an advanced AI prompt, it's important to keep three key categories in mind: Composition & Perspective, Lighting & Atmosphere, and Style & Aesthetics

Composition

In advanced AI prompts, composition defines what your viewer sees and how they see it. Key elements include:

Subject: The focus of the scene. This might be a product, person, or place.
Frame: How much of your subject is visible. Specifying the frame controls how much of the subject and its surroundings is shown. The frame of your image dictates how much of the subject and atmosphere is visible.
Angle: The position relative to the subject. Specifying the angle changes how the subject appears; low angles make it look bigger and vice versa.
Camera Movement: The way the virtual camera moves. This controls how the subject and scene is revealed, followed, or emphasized. The camera movement affects how the scene is revealed.

Atmosphere

In advanced AI prompts, atmosphere sets the context and mood of the scene. Key elements include:

Lighting: How your video is lit. This might describe the time of day (night, sunset), the light's temperature (warm, cool), or direction (backlit, front-lit).
Specifying lighting sets the mood of your video. For example, warm light sets a drastically different scene than cool fluorescent light.

Three AI-edited images of a girl; one done in low-light, one done at golden hour, and one done in morning light — The lighting greatly influences the temperature, mood, and atmosphere of your output.

Background: The setting that surrounds your subject. It dictates what appears behind the subject, but it also influences the atmosphere of the video.
For example, a neon-lit city street will naturally cast dramatic shadows, while a sunset beach will add warm golden tones.

Three AI-edited images of a girl; one with a background of the mountains, one of a Hong Kong alleyway at night, and one in a professional photo studio — Changing the background also changes the lighting, mood, and visual style of your video.

Creative Direction

In advanced AI prompts, creative direction defines the output's artistic vision. Key elements include:

Visual Style: The overall artistic approach that determines the medium and execution of the output. This could be the format (animation, photorealistic) or the treatment of the subject (romantic, cinematic, surreal)
Cultural/Artistic Influences: The influences that inspire the output.
Unlike visual style, which is more general, influences are based on an artistic tradition or cultural mood. This might include references to media (The Simpsons, anime, Pixar cartoons) or art (impressionism, modern, abstract).
- Referencing influences is one of the easiest ways to upgrade your AI prompts, with some of the most popular prompts being recreations of famous artists, directors, or franchises.
Narrative/Conceptual Notes: Even a short clip benefits from a hint of story — is the subject arriving, transforming, escaping, or celebrating? A narrative anchor makes the video feel intentional.

Learn more about how to write advances AI image prompts here.

Learn more about the other AI features within Kapwing.