Image to image AI: edit a picture or combine several with a prompt

Makernice image to image edits a picture or combines several into one from a prompt, in the browser console or through one API key. All 4 image models in the Makernice AI image generator support it, with up to 14 input images on Seedream 5.0. Each image is quoted first and billed per image.

Makernice Team · Updated November 2, 2026

How do you edit or combine images on Makernice?

Use the web console for a few images without code, or the API for apps and batches. Both use the same models, the same prices and the same prepaid balance.

In the browser (no code)

Sign in and top up your prepaid balance (from $15; it never expires).
Open Create → Image, choose Image to image, pick a model and upload your pictures (JPEG, PNG or WebP, up to 10 MB each), then say what to change.
The price appears before you press Generate. Download the image when it's ready; delivered images are kept for 30 days.

Open the image console

With the API

Quote: POST /v1/generations/quote returns the exact amount, holds nothing and locks the price for 12 minutes.
Create: POST /v1/generations with the quote_id, the same input and an Idempotency-Key header. The quoted amount is held from your balance.
Poll GET /v1/generations/{id} until status is succeeded, or add a top-level callback_url to get a webhook. Then download outputs[0].url.

Quickstart · Webhooks · No charge for failed generations

curl https://api.makernice.com/v1/generations/quote \
  -H "Authorization: Bearer $MAKERNICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"seedream-5.0-pro","mode":"i2i","prompt":"Replace the background with a plain light grey studio wall and keep the product unchanged","reference_images":["https://example.com/product.png"],"resolution":"2k"}'

curl https://api.makernice.com/v1/generations \
  -H "Authorization: Bearer $MAKERNICE_API_KEY" \
  -H "Idempotency-Key: 7c1e9a2b-order-1842" \
  -H "Content-Type: application/json" \
  -d '{"quote_id":"qt_…","input":{"model":"seedream-5.0-pro","mode":"i2i","prompt":"Replace the background with a plain light grey studio wall and keep the product unchanged","reference_images":["https://example.com/product.png"],"resolution":"2k"}}'

curl https://api.makernice.com/v1/generations/gen_… \
  -H "Authorization: Bearer $MAKERNICE_API_KEY"

How many reference images can each Makernice image-to-image model take?

Image to image (mode i2i) takes your pictures in reference_images: up to 14 on Seedream 5.0, 10 on Seedream 5.0 Pro and 3 on Qwen3 Image and Qwen3 Pro Image. Each model accepts the same aspect ratios as in text to image, and in the console this mode is called Image to image.

Catalog facts from GET /v1/models. Side-by-side model notes: Seedream 5.0 vs Qwen3 Image.
Model	Max input images	Resolutions
Seedream 5.0 Pro	10	1K, 2K
Seedream 5.0	14	2K (fixed)
Qwen3 Image	3	1K, 2K
Qwen3 Pro Image	3	1K, 2K

Catalog facts from GET /v1/models. Side-by-side model notes: Seedream 5.0 vs Qwen3 Image.

Is image to image more expensive than text to image on Makernice?

Yes, on every model and resolution below. Image to image costs from $0.0411 per image on Qwen3 Image (1K) to $0.114 on Seedream 5.0 Pro (2K), price list v12, November 3, 2026. The number of input images does not change the price.

Per image, from GET /v1/pricing. Your quote shows the exact amount before you run anything. Live rates: Pricing.
Model	Resolution	Image to image	Text to image
Seedream 5.0 Pro	1K	$0.0702/image	$0.0351/image
Seedream 5.0 Pro	2K	$0.114/image	$0.0702/image
Seedream 5.0	2K	$0.042/image	$0.0336/image
Qwen3 Image	1K	$0.0411/image	$0.0236/image
Qwen3 Image	2K	$0.0411/image	$0.0236/image
Qwen3 Pro Image	1K	$0.0531/image	$0.0328/image
Qwen3 Pro Image	2K	$0.096/image	$0.0657/image

Per image, from GET /v1/pricing. Your quote shows the exact amount before you run anything. Live rates: Pricing.

Prices as of November 3, 2026 (price list v12).

What should you check before sending a Makernice image-to-image request?

Through the API, each image in reference_images must be a public https URL of up to 2,048 characters, because the API has no upload endpoint. In the console you upload files instead.
More than 3 images works only on Seedream 5.0 Pro and Seedream 5.0; more than 10 only on Seedream 5.0.
Leave out resolution on Seedream 5.0; it always renders at 2K.
Only upload images you own or have permission to use, and don't upload photos of other people without their consent.

Frequently asked questions

What is the difference between image to image and reference images on Makernice?

They are the same mode. Image to image (mode i2i) takes your pictures in the reference_images field, whether you edit one picture or combine several. The console calls this mode Image to image.

Do more input images cost more in Makernice image to image?

No. Image to image is priced by the model and the resolution. Sending one picture or the model's maximum gives the same quote.

Which Makernice image models can combine more than 3 images?

Seedream 5.0 Pro and Seedream 5.0: up to 10 on Seedream 5.0 Pro and 14 on Seedream 5.0. Qwen3 Image and Qwen3 Pro Image take up to 3.

Does Makernice charge for a failed image-to-image generation?

No. Creating a run holds the quoted amount. If the generation fails, times out or is canceled while queued, the hold is released in full. Quality is not a failure condition: a delivered image is charged, whatever you think of it. Note: if a finished output is blocked by output moderation for a policy violation, the run is still charged. You can contact support for a manual review.

AI image generator · Text to image · How image generation is priced · Seedream 5.0 vs Qwen3 Image · Pricing