Edit an image you add
Give it an image and a prompt that says what to change. The edited images come back.
Create a picture from a description
Preview version of Gemini 3 Pro image generation model.
Opens the image studio with Gemini 3 Pro Image Preview ready to use. You can look around as a guest. Running it takes the Studio plan or higher.


What it makes
Create a picture from a description
Turns a written description into a picture.
What you need
Optional: a picture to start from.
What you get
A new picture
Gemini 3 Pro Image Preview makes a new image from a written prompt, and it edits an image you add. This version costs 1500-2000 credits. When you edit, you give it a prompt and an image. You get back the edited images plus a text description of them.
Making a new image needs only a prompt and has no options. When you edit, you get five options. Aspect Ratio has ten choices, including auto, 16:9, 4:3 and 1:1, and starts at auto. Resolution can be 1K, 2K or 4K and starts at 1K. System Prompt is an optional instruction that steers the model's persona and style across the request. Limit Generations is experimental and starts on. It makes 1 image per run and ignores any image count in your prompt. Enable Web Search lets the model use the latest information from the web. It starts switched off.
Another version of Gemini 3 Pro Image Preview makes images from a prompt only. It has Aspect Ratio, System Prompt, Resolution, Limit Generations and Enable Web Search for new images and costs 1500 credits. Here, a new image has no options.
Same job: create a picture from a description. Compare before you choose.
A speed-tuned variant of Stable Diffusion XL that generates high-quality images in a handful of steps, trading a little fine detail for near-instant results - ideal for rapid concept exploration and draft iteration.
Alibaba's fast-inference Qwen Image variant, tuned for near-instant text-to-image generation without sacrificing prompt accuracy - built for rapid drafts and high-volume workflows.
Alibaba's Qwen Image model generates accurate, detailed visuals from text prompts with strong prompt comprehension, including legible in-image text and complex compositions.
A FLUX variant tuned by Krea for stylized, painterly image generation - strong for concept art and creative visuals that want more artistic flair than strict photorealism.
Give it an image and a prompt that says what to change. The edited images come back.
Write a prompt without adding an image to create a new picture.
When you edit, you also receive a text description of the images.
To make a new picture, write a prompt. To change a picture, write a prompt and add your image.
Say what the new image should show, or what to change in the image you added.
When you edit, pick Aspect Ratio, Resolution and any other option you want. Then run for 1500-2000 credits.
Add your image and describe the change in a prompt.
Write a prompt without adding an image and describe what you want to see.
Quick answers to help you get the most out of Gemini 3 Pro Image Preview in FunAI Studio.