What is Text to Image?
Text to Image turns a written description into a finished picture. Describe the subject, the setting, the lighting and the style you want, and the AI generates an image to match. It runs in your browser, so there is nothing to install and no GPU needed.
You can choose between two leading image models: OpenAI's GPT Image 2.5, which is strong at fine detail and at rendering readable text, and Nano Banana Pro, Google's Gemini 3 Pro image model. Once you have an image you like, bring it to life with Image to Video or sharpen it with the 8K upscaler.
Key features
Two top image models
Switch between GPT Image 2.5 and Nano Banana Pro with one click and compare how each one interprets the same prompt.
Up to 4 reference images
Upload your own photos or artwork to guide the style, the composition or the look of a character, instead of describing everything in words.
5 aspect ratios
Pick 1:1, 3:4, 4:3, 9:16, 16:9 to fit a profile picture, a phone wallpaper, a social post or a widescreen banner.
Prompt helper
Not sure how to phrase it? Let the AI expand a short idea or a reference image into a detailed prompt for 1 credit.
How to create an AI image
- 1
Describe the image you want. Be specific about the subject, the setting, the lighting and the style — for example "a lighthouse on a rocky coast at sunset, oil painting".
- 2
Optionally add up to 4 reference images as JPG or PNG files up to 20MB each, then choose a model and an aspect ratio.
- 3
Click Generate. Your image appears in a few seconds, is saved to your gallery automatically and can be downloaded right away.
Frequently asked questions
Which AI image model should I use?+
GPT Image 2.5 is the better choice when the image needs fine detail or readable text, such as signs, posters or logos. Nano Banana Pro, built on Google's Gemini 3 Pro, is a strong all-rounder. Both cost only a few credits, so trying the same prompt on each is the quickest way to find out which you prefer.
What are reference images for?+
They show the model what you mean instead of making you describe it. Upload up to 4 images to guide the style, the colours, the composition or the appearance of a person or product, and describe in the prompt how they should be used.
How much does it cost to generate an image?+
Each image costs a small, fixed number of credits that depends on the model you pick, and the exact price is shown on the Generate button before you click it. Credits come in one-time packs starting at $4.99, with no subscription.
Do I need an account?+
You can explore the tool without one. When you click Generate you are asked to create a free account, so your images can be saved to your personal gallery.
Can I use the images I generate?+
Yes. You can download every image, and our Terms of Service assign you our rights in what you generate, subject to the terms of the underlying model providers. DayWaveAI is a safe-for-work platform, so every prompt and uploaded image is screened before anything is generated, and blocked requests are never charged.