AI Image Generator:
Choose Models, Tune Settings, Edit Results

Secret Chat includes a built-in AI image generator that turns a written description into a picture — right inside the same private chat workspace you use for everything else. You do not need a separate app or account: pick the Image Generator, describe what you want, and the image appears in your conversation. What makes it flexible is that you are not tied to a single image model, every model brings its own settings, and any picture you create can be reworked with a single button.

For the wider product context — multiple models and local browser storage — see our main private AI chat page.

GPT Image, Grok Imagine, Nano Banana, Qwen and Seedream are trademarks of their respective owners (OpenAI, xAI, Google, Alibaba, and ByteDance). Secret Chat is an independent product and is not affiliated with, endorsed by, or sponsored by any of these model creators. See our Disclaimers for details.

One tool, several image models

Different image models have different styles and strengths, so the Image Generator lets you choose the one that fits the job. You select a model from the Settings, and your choice is remembered for next time. The models available are:

  • Nano Banana 2 — a fast, reliable everyday choice and the default.
  • Nano Banana Pro — a higher-end version for more detailed results.
  • Grok Imagine Pro — xAI's image model, good for bold, creative visuals.
  • GPT Image 2 — OpenAI's image model, strong at following detailed instructions and text in images.
  • Qwen Image 2 Pro — a flexible model with extra style controls.
  • Seedream — another option with fine-grained style controls.

Because each model is a little different, it is worth trying the same idea on more than one to see which look you prefer. Results vary by model and by how you word your description.

Different models, different settings

At a glance, here are the settings each group of models offers:

Nano Banana 2 /
Nano Banana Pro
Grok Imagine Pro /
GPT Image 2
Qwen Image 2 Pro /
Seedream
Aspect RatioAspect RatioAspect Ratio
VariantsVariants
Image Style
Negative Prompt

When you open the Settings, you will see a Model selector at the top and, below it, the options that apply to the model you picked. The settings change to match the model — simpler models show fewer options, while the more advanced ones offer more control. The possible settings are:

  • Model — which image model to use. Changing it updates the rest of the settings to match.
  • Variants — how many different images to create from the same description at once, so you can pick your favourite. Some models allow a handful, others more.
  • Aspect Ratio — the shape of the image, such as square, portrait, or landscape. Choose it to fit where the picture will be used.
  • Image Style — a preset look (offered by some models) that nudges the overall style of the result.
  • Negative Prompt — a short note of what you do not want in the image, for example “clouds, rain, snow.” Available on the models that support it.

For example, the Nano Banana models keep things simple with an aspect ratio choice, while models like Qwen Image 2 Pro and Seedream add variants, a style preset, and a negative prompt for finer control. You do not have to learn all of this up front — sensible defaults are already set, and a Reset option puts everything back if you experiment.

Edit any image with one button

Every image you generate comes with two buttons beneath it: a Download button to save it to your device, and an Edit button (the pencil icon) to change it.

The Edit button is what makes refining a picture easy. Instead of starting over, you click the pencil and the image is placed back into your message box as a starting point. You then simply describe the change you want — “make the sky sunset orange,” “add a small boat,” “remove the text in the corner” — and generate again. The model uses your existing picture as the basis and applies your edit, so you can keep adjusting an image step by step until it looks right.

This image-to-image editing works with the models that support it, and it is the quickest way to fine-tune a result without re-describing the whole scene from scratch.

Tips for better images

  • Be specific. Mention the subject, setting, mood, lighting, and style you have in mind — the more detail, the closer the result.
  • Use variants. Generating a few at once gives you options to choose from in a single step.
  • Set the aspect ratio first so the composition fits where you will use the image.
  • Add a negative prompt (on models that support it) to keep out things you do not want.
  • Refine with Edit. Get close, then use the Edit button to nudge the details rather than starting again.

Private by design

The Image Generator works the same private way as the rest of Secret Chat. Registration is email only — no real name or phone number — and the images you create are kept in your browser's local storage on your own device, rather than in a cloud gallery on our servers. As with any AI tool, your description is sent to the chosen model provider to create the picture, so it is best not to include personal or confidential details in a prompt. For more on how this works, see our private AI models page.

FAQs about the AI Image Generator

Can I choose which image model to use? +

Yes. The Image Generator lets you pick from several models — Nano Banana 2, Nano Banana Pro, Grok Imagine Pro, GPT Image 2, Qwen Image 2 Pro, and Seedream — from the Settings. Your choice is remembered for next time, and each model has its own look and strengths.

Why do the settings change when I switch models? +

Because different models support different options. Simpler models may only offer an aspect ratio, while more advanced ones add variants, a style preset, and a negative prompt. The Settings panel shows only the options that apply to the model you have selected.

How do I edit an image I generated? +

Each generated image has an Edit button (the pencil icon) beneath it. Click it and the image is placed back into your message box; then describe the change you want and generate again. The model uses your existing image as the starting point, so you can refine it step by step.

Can I create more than one image at a time? +

Yes, on models that support it. The Variants setting lets you generate several images from the same description at once, so you can compare them and pick your favourite.

Where are my generated images stored? +

In your browser's local storage on your own device, not in a cloud gallery on our servers. You can download any image you want to keep. Note that your description is still sent to the chosen model provider to create the image, so avoid including personal or confidential details.