
AI image to image generator
Upload a picture, say what to change and get the new version in up to 4K. Choose from 9 models, all on one account.
You bring
One or more images
The picture to change. Every model takes more than one.
A prompt
What changes and what stays.

Pick a model
9 models run image to image here. The table below compares their limits and prices.

Add your picture
Upload one or more images and say what should change: the style, the scene or one detail.

Get your picture
You see the price before you run it, and a generation that fails costs nothing.
AI models for image to image
Ardscale runs image to image on 9 models, made by OpenAI, Google, Alibaba, and ByteDance.

GPT Image 2.5· Image
Images up to 4K, in 13 aspect ratios

GPT Image 2.6· Image
Images up to 4K, in 13 aspect ratios

Nano Banana 2.1· Image
Images up to 4K, in 14 aspect ratios

Nano Banana 2· Image
Images up to 4K, in 14 aspect ratios
| Model | Maker | Top resolution | Aspect ratios | Price |
|---|---|---|---|---|
| GPT Image 2.5 | OpenAI | 4K | 1:1, 3:2, 2:3, 4:3, 3:4, 5:4, 4:5, 16:9, 9:16, 21:9, 2:1, 1:2, 9:21 | From 3 credits per image |
| GPT Image 2.6 | OpenAI | 4K | 1:1, 3:2, 2:3, 4:3, 3:4, 5:4, 4:5, 16:9, 9:16, 21:9, 2:1, 1:2, 9:21 | From 3 credits per image |
| Nano Banana 2.1 | 4K | 1:1, 3:2, 2:3, 4:3, 3:4, 5:4, 4:5, 16:9, 9:16, 21:9, 1:4, 4:1, 1:8, 8:1 | From 3 credits per image | |
| Nano Banana 2 | 4K | 1:1, 3:2, 2:3, 4:3, 3:4, 5:4, 4:5, 16:9, 9:16, 21:9, 1:4, 4:1, 1:8, 8:1 | From 4 credits per image | |
| Nano Banana Pro | 4K | 1:1, 3:2, 2:3, 4:3, 3:4, 5:4, 4:5, 16:9, 9:16, 21:9 | From 8 credits per image | |
| Qwen-Image 3.0 Pro | Alibaba | 2K | 1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3, 2:1, 1:2, 21:9, 9:21, 4:5, 5:4, 4:1, 1:4, 8:1, 1:8 | From 6 credits per image |
| Qwen-Image 3.0 | Alibaba | 2K | 1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3, 2:1, 1:2, 21:9, 9:21, 4:5, 5:4, 4:1, 1:4, 8:1, 1:8 | From 5 credits per image |
| Seedream 5.5 | ByteDance | 2K | 1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3, 21:9, 2:1, 1:2 | From 3 credits per image |
| Seedream 5.0 Pro | ByteDance | 2K | 1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3, 2:1, 1:2, 21:9 | From 6 credits per image |
Length, resolution and aspect ratios show each model’s full range. One mode can narrow it, and a clip that starts from your image usually takes the image’s shape.
Which AI models run image to image on Ardscale?
Ardscale runs image to image on 9 models: GPT Image 2.5, GPT Image 2.6, Nano Banana 2.1, Nano Banana 2, Nano Banana Pro, Qwen-Image 3.0 Pro, Qwen-Image 3.0, Seedream 5.5, and Seedream 5.0 Pro.
What resolution are the images?
Images come out at up to 4K, on GPT Image 2.5, GPT Image 2.6, Nano Banana 2.1, Nano Banana 2, and Nano Banana Pro. You choose the aspect ratio on every model.
How much does image to image cost?
On Ardscale, image to image starts at 3 credits per image, on GPT Image 2.5, GPT Image 2.6, Nano Banana 2.1, and Seedream 5.5. Every model has its own price and you see it before you generate. A generation that fails costs nothing.
What is the difference between image to image and text to image?
Image to image changes pictures you already have, guided by a prompt. Text to image has no starting picture, so the prompt is all the model gets.
