Skip to main content
Image (3) 1

What is Image Prompt?

Think of an Image Prompt as the “visual shorthand” for your creative ideas. Instead of relying solely on words, you provide a starting image; a photo, a sketch, or even a previous generation to act as a structural anchor. You simply upload or drag your image into the Image Prompt field, and the AI uses it as a foundational layer of inspiration. It’s like a conversation where your image sets the scene, and your text prompt provides the direction.

How to use Image Prompt

1

Open the settings panel and enable Image Prompt

Image (4) 1
2

Upload your reference image

You can upload any image from your device by clicking the ”+” button to open the file browser, or simply drag and drop an image directly into the field. Supported formats include JPEG, PNG, and WEBP. For best results, use a clear, well-lit image that reflects the composition or style you want the AI to draw inspiration from.
Image (5) 1
3

Write your text prompt

Once uploaded, the AI will analyse your image and use it as a visual foundation alongside your text prompt. The more relevant your image is to your desired outcome, the more accurately the AI can capture the mood, structure, and style you’re going for. You’ll see a thumbnail preview of your uploaded image in the field confirming it’s been applied.
Image (6) 1
Example combinations:
  • Reference image of a misty forest + prompt: "A lone cabin with warm glowing windows, winter evening, oil painting style"
  • Reference image of a sports car + prompt: "Same car on a coastal highway at sunset, cinematic photography, motion blur"
  • Reference image of a character sketch + prompt: "Full color illustration, fantasy armor, dramatic lighting"
4

Select your model and settings

Not happy with the first result? That’s completely normal — and part of the fun! You can adjust your text prompt, swap out your reference image, or tweak your settings and generate again. Each iteration builds on your feedback, helping you get closer to your ideal image with every attempt.
Image (7) 1
5

Click Create

When you’re happy with your image prompt and text, hit the Create button to generate your image. The AI will combine your visual reference and text instructions to produce a unique result. Depending on the selected model and settings, generation typically takes just a few seconds.Supported models
Image (8)

Support

Support

Image prompt is supported by all available image generation models.
ModelDescription
Flux devA pioneering experimental engine engineered for rapid, high-detail image synthesis with a bold artistic diversity.
RealisticA high-fidelity generator that produces true-to-life visuals with precise textures, authentic lighting, and natural depth for portraits and scenes.
ChatGPT ImageDelivers prompt-accurate visuals, excels at incorporating readable, precise text into images.
Imagen 3Specializes in producing photorealistic, detailed images with accurate lighting, textures, and object relationships.
Flux Ultra 1.1Excels at high-resolution photorealistic rendering with fine-grained texture fidelity, making it ideal for product visualizations and architectural mock-ups.
Ideogram v3Noted for its advanced typography control—it can generate images that incorporate crisp, correctly spelled text in complex layouts.
Minimax ImageGreat for realistic portraits, product images, and structures.
Seedream v3Specializes in dream-like cinematic scenes; it synthesizes rich lighting, atmospheric depth, and vibrant color palettes reminiscent of concept-art mood boards.
Ideogram CharacterBest in class one-shot character consistency model.
Dreamina Image 3.1Great for mood, design, worldbuilding, and storytelling. Not ideal for prompt-as-spec use cases like typography-heavy layouts.
The model you choose affects how strongly the reference image influences the output. Experiment with different models to find the balance between reference fidelity and creative freedom that works best for your project.