Seedream 5.0 — 14 references, one image

Name: Seedream 5.0
Brand: ByteDance
SKU: seedream-5.0

Seedream 5.0 supports text-to-image and image-to-image, and takes up to 14 reference images, the most on the platform's image models. It is priced as a single 2k tier and the request has no resolution parameter. Eight aspect ratios are available, including 21:9.

Highlights

Single tier · Text to image · Image to image

Best for

Image workflows that blend many reference images, such as character sheets, collages and style fusion.

Input

Text, up to 14 reference images

Output

Image

Input

Prompt

Aspect ratio

ResultPreview

Estimated price$0.0336$0.0336/img

Checking your session…

Try one of these prompts

Pricing

Prepaid in US dollars. We hold the quoted amount while it runs and charge it only on delivery — failed runs are free.

Cost of your first test

$0.0336

One image at the lowest-cost settings.

What your top-up buys

Top up

$10

≈ 297 test runs

$50

≈ 1488 test runs

$100

≈ 2976 test runs

Model	Mode	Resolution	Our price	Official	You save
Seedream 5.0 ByteDance	Text to image	2K	$0.0336/img	$0.035/img	-4%
Seedream 5.0 ByteDance	Image to image	2K	$0.042/img

This model has one fixed resolution, so every request is priced the same tier.

What is the Seedream 5.0 API?

The Seedream 5.0 API generates and edits images with ByteDance's Seedream 5.0. It does not take a resolution parameter, and it accepts up to 14 reference images where Seedream 5.0 Pro accepts 10 and offers 1k or 2k. Choose this one when the number of references matters most.

2 ways to generate, one endpoint

Set mode, send the inputs it needs — that's it.

Text to image

mode: "t2i" · prompt

Describe the image you want in the prompt.

Image to image

mode: "i2i" · reference_images (≤ 14)

Add up to 14 reference images, then describe the edit or the new image.

What you can build with this model

Workflows this model is a good fit for.

Multi-reference compositing

Combine several subject, style and background images into one new composition.

Try it in the playground

Wide and ultrawide visuals

Create banners and key art in 21:9 as well as portrait and square ratios.

Try it in the playground

Character sheets

Use many reference views of a character to keep a consistent look across outputs.

Try it in the playground

Why run Seedream 5.0 on MakerNice

Quote before you pay

Every run gets an exact quote first, locked for 12 minutes. You're charged that amount — never more.

Failed runs are free

We hold the amount while the model runs and charge only on delivery. Failures and queued cancellations cost nothing.

Switch models with one field

Same request, key, balance and console for all 16 models. Not happy with the result? Change model and run it again.

Which should you pick: Seedream 5.0, Seedream 5.0 Pro?

Compare modes, length, resolution and references, then run the same prompt on each.

	Seedream 5.0	Seedream 5.0 Pro
Modes	Text to image · Image to image	Text to image · Image to image
Resolution	Single tier	1K / 2K
Reference images	Up to 14	Up to 10
Starting price	$0.0336/img	$0.0351/img

Integrate Seedream 5.0 in three steps

Step 1

Create an API key

Open

Step 2

Quote and create

POST the input to /v1/generations/quote with the model field set to seedream-5.0, then create the generation with the quote id.

Open

Step 3

Poll the result

GET /v1/generations/{id} until the status is succeeded, then download the output.

Open

Docs/API/SEEDREAM-5-0

API reference

Copy-paste requests for this model. The full parameter reference is in the docs.

curl https://api.makernice.com/v1/generations/quote \
  -H "Authorization: Bearer $MAKERNICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedream-5.0",
    "mode": "t2i",
    "prompt": "A sprawling fantasy city on a cliff above the sea at golden hour, banners and waterfalls, ultrawide matte painting."
  }'

Invalid request

400 invalid_request names each failing field. Fields the mode doesn't use are rejected too. Nothing is held.

Key or balance

401 means a missing or invalid key; 402 means the balance or the key's spend limit isn't enough.

Quote problems

A changed price-affecting field returns 422 quote_mismatch; an expired quote 410; a used one 409. Get a new quote.

Failed generation

A failed generation is never charged — the hold is released in full. Keep the generation id and retry when you're ready.

Frequently asked questions

Common questions about this model.

What is Seedream 5.0?

Seedream 5.0 is an AI image generation model from ByteDance, available through the MakerNice API with one key and one prepaid balance. Blend up to 14 reference images into one: Seedream 5.0 is built for character sheets, collages and style fusion, priced as a single 2K tier.

How many reference images does Seedream 5.0 support?

Up to 14 reference images, sent in reference_images in image to image mode.

How much does Seedream 5.0 cost per image?

Seedream 5.0 is billed per image, and the rate depends on the settings you choose; every combination is listed in the price table on this page. Call POST /v1/generations/quote to get the exact amount before you run it. Failed runs are never charged.

Seedream 5.0 vs Seedream 5.0 Pro: which should I use?

Seedream 5.0 is the one for blending many references: up to 14 at a single 2k tier. Seedream 5.0 Pro lets you choose 1k or 2k and takes up to 10 reference images.

Can I pick 1k or 2k?

No. This model is priced as a single 2k tier and does not take a resolution parameter. Seedream 5.0 Pro offers 1k and 2k.

How do I fetch the finished image?

Image jobs use the same flow as video: create the job, poll GET /v1/generations/{id} until it succeeds, then request /v1/generations/{id}/outputs/0 with your key.