Text to image AI: generate an image from a prompt, in the browser or by API

Makernice text to image creates one image from a written prompt, in the browser console or through one API key. All 4 image models in the Makernice AI image generator support it, at 1K or 2K depending on the model, with up to 8 aspect ratios. Each image is quoted first and billed per image.

Makernice Team · Updated November 2, 2026

How do you generate an image from text 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 Text to image, pick a model and an aspect ratio, then write the prompt.
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":"qwen3-image","mode":"t2i","prompt":"A flat-lay photo of a ceramic coffee set on a linen tablecloth, soft window light","resolution":"2k","aspect_ratio":"3:2"}'

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":"qwen3-image","mode":"t2i","prompt":"A flat-lay photo of a ceramic coffee set on a linen tablecloth, soft window light","resolution":"2k","aspect_ratio":"3:2"}}'

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

Which resolutions and aspect ratios does each Makernice text-to-image model support?

Seedream 5.0 Pro, Qwen3 Image and Qwen3 Pro Image let you choose 1K or 2K; Seedream 5.0 renders at a fixed 2K and rejects a resolution field. 21:9 works on Seedream 5.0, Qwen3 Image and Qwen3 Pro Image but not on Seedream 5.0 Pro. Each request returns one image.

Catalog facts from GET /v1/models. Every image model takes prompts of up to 4,000 characters.
Model	Resolutions	Aspect ratios
Seedream 5.0 Pro	1K, 2K	1:1 · 4:3 · 3:4 · 16:9 · 9:16 · 2:3 · 3:2
Seedream 5.0	2K (fixed)	1:1 · 4:3 · 3:4 · 16:9 · 9:16 · 2:3 · 3:2 · 21:9
Qwen3 Image	1K, 2K	1:1 · 3:2 · 2:3 · 4:3 · 3:4 · 16:9 · 9:16 · 21:9
Qwen3 Pro Image	1K, 2K	1:1 · 3:2 · 2:3 · 4:3 · 3:4 · 16:9 · 9:16 · 21:9

Catalog facts from GET /v1/models. Every image model takes prompts of up to 4,000 characters.

How much does one image cost with Makernice text to image?

Text to image costs from $0.0236 per image on Qwen3 Image (1K) to $0.0702 on Seedream 5.0 Pro (2K), price list v12, November 3, 2026. On Qwen3 Image, 2K costs the same as 1K. The aspect ratio and the prompt do 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	Per image
Seedream 5.0 Pro	1K	$0.0351/image
Seedream 5.0 Pro	2K	$0.0702/image
Seedream 5.0	2K	$0.0336/image
Qwen3 Image	1K	$0.0236/image
Qwen3 Image	2K	$0.0236/image
Qwen3 Pro Image	1K	$0.0328/image
Qwen3 Pro Image	2K	$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 a Makernice text-to-image request include?

mode: "t2i", model and a prompt of up to 4,000 characters. No reference_images: to start from your own pictures, use image to image.
resolution only where the model offers a choice; leave it out on Seedream 5.0.
aspect_ratio from the model's list in the table above.
One request returns one image. For four variations, quote and create four generations.

Frequently asked questions

Does a 2K image cost more than a 1K image on Makernice?

It depends on the model. On Seedream 5.0 Pro and Qwen3 Pro Image, 2K costs more per image than 1K. On Qwen3 Image, both tiers cost the same. Seedream 5.0 has a single fixed 2K tier.

Which Makernice text-to-image models support a 21:9 aspect ratio?

Seedream 5.0, Qwen3 Image and Qwen3 Pro Image. Seedream 5.0 Pro accepts 7 ratios without 21:9: 1:1, 4:3, 3:4, 16:9, 9:16, 2:3, 3:2.

How long can a Makernice text-to-image prompt be?

Up to 4,000 characters after trimming, on all 4 image models. A longer prompt is rejected with a 400 error when you ask for the quote.

Does Makernice charge for a failed text-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 · Image to image · Seedream 5.0 vs Qwen3 Image · How image generation is priced · Pricing