Image to image · text to image · 4 models

Image to Image AI: edit any picture with a prompt

Upload a photo, say what should change — the background, the style, the outfit, the light — and get a new image in 10 to 60 seconds. Nano Banana 2, Nano Banana Pro, GPT Image 2 and Seedream in one place, up to 4K.

0/4000
  • Image to image · text to image
  • 4 models in one place
  • Up to 14 reference images
  • Up to 4K
  • Free images to start

Before and after, with the exact prompt

Real results from this site and the prompt that made each one. Use one as a starting point.

  • Nano Banana 2: Place this sneaker on a polished concrete plinth in a bright studio with soft window light and a long shadow. Keep the shoe's shape, colors and logo exactly the same.BeforeAfter

    “Place this sneaker on a polished concrete plinth in a bright studio with soft window light and a long shadow. Keep the shoe's shape, colors and logo exactly the same.”

    Image to image · Nano Banana 2 · 2K

    Use this prompt
  • Nano Banana Pro: Turn this photo into a loose watercolor illustration on textured paper. Keep her face, hair and pose recognizable.BeforeAfter

    “Turn this photo into a loose watercolor illustration on textured paper. Keep her face, hair and pose recognizable.”

    Image to image · Nano Banana Pro · 2K

    Use this prompt
  • Nano Banana 2: Make it a snowy winter night: snow on the roofs and street, warm light in the windows, falling snow. Keep the buildings and the camera angle.BeforeAfter

    “Make it a snowy winter night: snow on the roofs and street, warm light in the windows, falling snow. Keep the buildings and the camera angle.”

    Image to image · Nano Banana 2 · 2K

    Use this prompt
  • GPT Image 2: Restyle this living room in a warm Japandi style: light oak, linen sofa, paper lamp, a few plants. Keep the windows, walls and layout.BeforeAfter

    “Restyle this living room in a warm Japandi style: light oak, linen sofa, paper lamp, a few plants. Keep the windows, walls and layout.”

    Image to image · GPT Image 2 · 2K

    Use this prompt
  • Nano Banana 2: Put the dog from Image 1 in the astronaut suit from Image 2, floating inside a space station, Earth in the window. Keep the dog's face and fur color.BeforeAfter

    “Put the dog from Image 1 in the astronaut suit from Image 2, floating inside a space station, Earth in the window. Keep the dog's face and fur color.”

    Image to image · Nano Banana 2 · 2K

    Use this prompt
  • GPT Image 2: A minimalist poster for a coffee shop called "MORNING RITUAL": a ceramic cup with steam on a cream background, bold serif headline at the top, small text "Open 7am – 3pm" at the bottom.

    “A minimalist poster for a coffee shop called "MORNING RITUAL": a ceramic cup with steam on a cream background, bold serif headline at the top, small text "Open 7am – 3pm" at the bottom.”

    Text to image · GPT Image 2 · 2K

    Use this prompt

What is image to image AI?

Image to image AI takes a picture you already have plus a written instruction and returns a new picture: the same subject with a different background, style, outfit, light or detail. Unlike text to image, it starts from your pixels, so faces, products and layouts can stay recognizable.

This site runs four image models in the browser: Google's Nano Banana 2 and Nano Banana Pro, OpenAI's GPT Image 2 and ByteDance's Seedream 5.0 Flash. Upload up to 14 pictures, refer to them as Image 1, Image 2 in the prompt, pick a model and resolution, and download the result. You can also start from text alone.

Image To Image AI is an independent service and is not affiliated with or endorsed by Google, OpenAI or ByteDance. Nano Banana is a nickname for Google's Gemini image models; trademarks belong to their owners.

The models at a glance

Checked against the sources linked on each line.

Nano Banana 2
Google's Gemini 3.1 Flash Image, announced February 26, 2026: Pro-level quality at Flash speed, up to 5 characters and 14 objects kept consistent, output from 512 px to 4K. Google
Nano Banana Pro
Google's Gemini 3 Pro Image, announced November 20, 2025: legible text in images, 2K and 4K output, blends up to 14 images and keeps up to 5 people consistent. Google
GPT Image 2
OpenAI's model behind ChatGPT Images 2.0, announced April 21, 2026, with improved text rendering, multilingual text and visual reasoning. OpenAI
Seedream 5.0 Flash
ByteDance's faster, lower-cost Seedream 5.0 model: text to image and image to image with up to 10 reference images, output up to 2K. BytePlus (ByteDance)
Reference images
Nano Banana 2 takes up to 10 object and 4 character images; Nano Banana Pro up to 6 objects, 5 characters and 3 style images — 14 in total for each. Google AI for Developers
Output
1K, 2K or 4K (Nano Banana 2 also 512 px), in aspect ratios from 1:8 to 8:1. Every Gemini image carries Google's invisible SynthID watermark. Google AI for Developers

What you can do with it

Four models, one prompt box, and the price on the button before you generate.

  • Four models, one place

    Nano Banana 2, Nano Banana Pro, GPT Image 2 and Seedream 5.0 Flash. Switch models and your prompt and pictures stay.

  • Up to 14 reference images

    Combine a person, a product, an outfit and a style in one edit. Each upload gets a name — Image 1, Image 2 — and typing @ inserts it in the prompt.

  • Keeps what matters

    Say what to keep — the face, the logo, the layout — and what to change. Image to image starts from your pixels, so the subject stays recognizable.

  • Up to 4K

    1K for drafts, 2K for posts and 4K for print on Nano Banana 2, Nano Banana Pro and GPT Image 2; Seedream goes up to 2K. Auto keeps your picture's shape.

  • Seconds, not minutes

    Most images are ready in 10 to 60 seconds: about 15 s on Nano Banana 2 and Seedream, 20 s on GPT Image 2 and 50 s on Nano Banana Pro.

  • Private by default

    Your uploads and results are visible only to you. Uploads are deleted after 30 days; results stay in your library until you delete them.

How it works

Three steps, usually under a minute.

  1. 01

    Upload a picture

    Add one or more JPG, PNG or WebP pictures, up to 10 MB each. Or skip this step and start from text.

  2. 02

    Say what to change

    Describe the edit in plain words and what to keep, for example "make it golden hour, keep her face and the dress". With several pictures, refer to them as Image 1, Image 2.

  3. 03

    Generate and download

    Pick the model, resolution and shape, see the price on the button, and download the image when it's ready.

Which model should I use?

Start with Nano Banana 2. Switch when you need sharper text, closer instruction following or a lower price.

Nano Banana 2Nano Banana ProGPT Image 2Seedream 5.0 Flash
Best forEveryday edits that keep faces and productsCareful edits and text in imagesDetailed instructions, posters and typographyQuick, low-cost drafts
Resolution1K / 2K / 4K1K / 2K / 4K1K / 2K / 4K1K / 2K
Reference imagesUp to 14Up to 14Up to 14Up to 10
Typical waitAbout 15 sAbout 50 sAbout 20 sAbout 15 s
PriceFrom 2 creditsFrom 4 creditsFrom 2 creditsFrom 2 credits

Pay per image

300 credits for $9.99. Nano Banana 2 at 1K is 2 credits an image, so the smallest pack makes about 150 images — roughly $0.07 each.

Starter

$9.99

300 credits · one-time

  • ≈ 150 Nano Banana 2 images at 1K
  • ≈ 50 Nano Banana Pro images at 4K
  • $0.07 per Nano Banana 2 1K image

Creator

Most popular

$29.99

1000 credits · one-time

  • ≈ 500 Nano Banana 2 images at 1K
  • ≈ 166 Nano Banana Pro images at 4K
  • $0.06 per Nano Banana 2 1K image

Studio

Save 16%

$69.99

2500 credits · one-time

  • ≈ 1250 Nano Banana 2 images at 1K
  • ≈ 416 Nano Banana Pro images at 4K
  • $0.06 per Nano Banana 2 1K image

Nano Banana 2

Google

Google's fast image model (Gemini 3.1 Flash Image) and the default here. Good at keeping faces, products and layouts while it edits; about 15 seconds.

ResolutionPer image≈ Price
1K2 credits$0.07
2K3 credits$0.10
4K4 credits$0.13

Up to 14 reference images per edit, included in the price.

Nano Banana Pro

Google

Google's Gemini 3 Pro Image. The most careful edits and the most legible text in images; slower, about 50 seconds.

ResolutionPer image≈ Price
1K4 credits$0.13
2K4 credits$0.13
4K6 credits$0.20

Up to 14 reference images per edit, included in the price.

GPT Image 2

OpenAI

OpenAI's image model. Follows long, detailed instructions closely and sets clean typography for posters and mockups; about 20 seconds.

ResolutionPer image≈ Price
1K2 credits$0.07
2K3 credits$0.10
4K4 credits$0.13

Up to 14 reference images per edit, included in the price.

Seedream 5.0 Flash

ByteDance

ByteDance's fast, low-cost Seedream 5.0 model. Good for quick drafts and variations; up to 2K, about 15 seconds.

ResolutionPer image≈ Price
1K2 credits$0.07
2K2 credits$0.07

Up to 10 reference images per edit, included in the price.

One-time packs · purchased credits never expire · back automatically if an image fails

Full pricing

Image to image AI questions

·

Edit your first image

Upload a picture, write one sentence, and see it change.

Start editing