Image Official partner

Seedream 5.0 Pro API

Reference-driven composition with native 2K detail.

ByteDance's flagship Seedream 5.0 Pro image and editing model (mid 2026), generating sharp 1K and 2K images from text or up to 10 reference images with advanced reasoning and precision editing.

Get API key Read the docs

2K
Native output: 10
Reference images: ~20s
Avg. generation: 6 credits
From

Seedream 5.0 Pro campaign still of a glass PURE RENEWAL serum bottle on wet mossy slate in morning forest light

Playground

Try Seedream 5.0 Pro right here.

model: seedream-5-pro

Prompt

Aspect ratio Resolution

Media inputs

Reference image

Advanced settings

Output format Guidance Pre-LLM Pre-process the prompt with an LLM. Enhance prompt Seed

Estimated cost 6–11 credits · $0.06–$0.11 Generate in Studio

Output Example

Seedream 5.0 Pro studio photo of a matte white PURE RENEWAL Serum 30ml carton with sage botanical line art — Studio product photo of a matte white carton for a glass serum, label reading "PURE RENEWAL" in serif and "Serum 30ml" underneath, pale sage botanical line art, soft window light, photoreal 2K.

Capabilities

What's new in Seedream 5.0 Pro.

Sharp 1K and 2K output

It renders crisp images at 1K (about 2 MP) and 2K (about 4 MP), with pricing tiered by resolution so you only pay for the detail you need.

Up to 10 reference images

It accepts up to 10 reference images for single- and multi-reference generation, making it strong for product placement, character consistency, and scene compositing.

Advanced prompt reasoning

It uses deep, chain-of-thought understanding to turn data, concepts, and long text into structured layouts like infographics, posters, UI mockups, and charts in a single generation.

Precision editing and layer separation

It supports region-precise edits and can separate an image into editable assets such as text, subject, and background, changing one element without regenerating the whole canvas.

Native multilingual text

It renders accurate text in 14 languages, including right-to-left layouts and accented scripts, a major step up from previous Seedream generations.

Photorealism and material fidelity

It improves physical lighting, material behavior, skin texture, and multi-person compositing for convincing, commercially usable results.

Showcase

See what Seedream 5.0 Pro can create.

Real outputs generated with Seedream 5.0 Pro on Apiframe, each with the prompt behind it.

Try Seedream 5.0 Pro

Seedream 5.0 Pro multi-reference composite of the PURE RENEWAL bottle and carton on a marble bathroom vanity — Place this exact PURE RENEWAL glass serum bottle and its white carton together on a marble bathroom vanity, morning window light, a folded linen towel, photoreal 2K, keep the product identity from the references.

Seedream 5.0 Pro catalog still life of glass PURE RENEWAL serum bottles on pale travertine — Catalog still life, three glass PURE RENEWAL serum bottles at different heights on pale travertine, the nearest bottle labeled "PURE RENEWAL", soft north-window light, photoreal 2K.

Seedream 5.0 Pro dusk street with a PURE RENEWAL serum billboard reflected in wet pavement — Photoreal dusk street with a large outdoor billboard, a giant glass serum bottle, serif headline "PURE RENEWAL", wet pavement reflections, cinematic 2K.

Seedream 5.0 Pro vertical close-up of a serum drop falling onto stone under PURE RENEWAL type — Vertical social ad, extreme close-up of a clear serum pouring from a glass dropper, small serif type "PURE RENEWAL" at the top, pale stone, water droplets, photoreal 2K.

Seedream 5.0 Pro bilingual four-step PURE RENEWAL morning routine infographic with English and Japanese labels — Clean infographic on warm paper: a 4-step morning skincare routine for "PURE RENEWAL". Numbered steps 1-4 with short English labels and Japanese underneath: Cleanse / 洗顔, Serum / セラム, Moisturize / 保湿, SPF / 日焼け止め. Minimal botanical icons, no photos of people, print-ready layout, 2K.

Pricing

Simple per-generation pricing.

6–11 credits per generation ≈ $0.06–$0.11

The rate depends on the resolution and options you pick.

You only pay for successful generations. Failed jobs are refunded automatically.
One credit balance across every model on Apiframe, no per-model plans.
Start with free credits. No subscription required.
Volume discounts on larger plans.

See plans and credit packs Provider prices Compare Seedream 5.0 Pro pricing vs fal.ai and others

Specs

At a glance.

Provider ByteDance

Model ID seedream-5-pro

Aspect ratios 1:1, 3:4, 4:3, 9:16, 16:9

Resolutions 1K, 2K

Image input Supported

Avg. time ~405s

Comparison

Seedream 5.0 Pro vs Nano Banana 2 vs Flux 2 Max

ByteDance's image flagship against the Google and BFL flagships. One key, three options.

Feature	Seedream 5.0 Pro	Nano Banana 2	Flux 2 Max
Max resolution	2K native	4K	4MP
Reference input	Up to 10 images	Multi-image editing	Image prompt + strength dial
Avg. generation	~20s	~12s	~20s
Price per image	6–11 credits (≈$0.06–$0.11)	8–19 credits (≈$0.08–$0.19)	7–20 credits (≈$0.07–$0.20)
Best for	Reference-heavy composition and multilingual text	Everyday generation and editing	Highest-fidelity hero renders

Specs reflect what each model supports on Apiframe today, from the live catalog.

Quickstart

How to call the Seedream 5.0 Pro API.

Send one POST /v2/images/generate request with your API key. The call returns a jobId you can poll, or pass a webhook_url and the result is pushed to you the moment it's ready.

Swap seedream-5-pro for any other model and nothing else changes.

Get API key Read the docs

generate.js

const response = await fetch("https://api.apiframe.ai/v2/images/generate", {
  method: "POST",
  headers: {
    "X-API-Key": "afk_your_api_key_here",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "prompt": "a sleek silver sports car on a coastal highway at sunset, hyper-realistic",
    "model": "seedream-5-pro",
    "seedreamParams": {
      "image_input": "https://example.com/input.jpg",
      "output_format": "jpg",
      "guidance_scale": 3,
      "use_pre_llm": false
    }
  }),
});
const { jobId } = await response.json();
console.log(jobId);

import requests

response = requests.post(
    "https://api.apiframe.ai/v2/images/generate",
    headers={
        "X-API-Key": "afk_your_api_key_here",
        "Content-Type": "application/json",
    },
    json={
        "prompt": "a sleek silver sports car on a coastal highway at sunset, hyper-realistic",
        "model": "seedream-5-pro",
        "seedreamParams": {
            "image_input": "https://example.com/input.jpg",
            "output_format": "jpg",
            "guidance_scale": 3,
            "use_pre_llm": False
        }
    },
)
print(response.json())  # { "jobId": "...", "status": "QUEUED" }

curl -X POST https://api.apiframe.ai/v2/images/generate \
  -H "X-API-Key: afk_your_api_key_here" \
  -H "Content-Type: application/json" \
  -d '{
        "prompt": "a sleek silver sports car on a coastal highway at sunset, hyper-realistic",
        "model": "seedream-5-pro",
        "seedreamParams": {
            "image_input": "https://example.com/input.jpg",
            "output_format": "jpg",
            "guidance_scale": 3,
            "use_pre_llm": false
        }
    }'

let job;
do {
  await new Promise((r) => setTimeout(r, 2000));
  job = await fetch("https://api.apiframe.ai/v2/jobs/JOB_ID", {
    headers: { "X-API-Key": "afk_your_api_key_here" },
  }).then((r) => r.json());
} while (job.status !== "COMPLETED" && job.status !== "FAILED");
console.log(job.result);

import requests, time

while True:
    job = requests.get(
        "https://api.apiframe.ai/v2/jobs/JOB_ID",
        headers={"X-API-Key": "afk_your_api_key_here"},
    ).json()
    if job["status"] in ("COMPLETED", "FAILED"):
        break
    time.sleep(2)
print(job["result"])

curl https://api.apiframe.ai/v2/jobs/JOB_ID \
  -H "X-API-Key: afk_your_api_key_here"

Input schema

Every field Seedream 5.0 Pro accepts, with types and defaults. The full reference lives in the docs.

Field	Type	Description
prompt required	string	Text description of what to generate.
model required	string	The model identifier for this endpoint. Default:"seedream-5-pro" · "seedream-5-pro"
seedreamParams.image_input	string (URL)	Reference image (URL)
seedreamParams.output_format	string	Output format Default:"jpg" · "jpg", "png"
seedreamParams.guidance_scale	number	Guidance Default:3 · min 1, max 10, step 0.5
seedreamParams.use_pre_llm	boolean	Pre-process the prompt with an LLM. Default:false
seedreamParams.enhance_prompt	boolean	Enhance prompt Default:false
seedreamParams.seed	number	Reuse a number to reproduce the same result. step 1

Seedream versions

Every Seedream image model on Apiframe. Switch with one parameter.

Use cases

What teams build with Seedream 5.0 Pro.

Multi-reference composition

Up to 10 reference images in one request, pin a face, a product, a palette, and a layout, and the model composes them into one scene.

Multilingual text in-frame

Native multilingual text rendering puts accurate on-image copy into localized creative without a per-language design pass.

Precision editing

Layer-aware editing separates subject from background, so targeted changes land without collateral damage to the rest of the frame.

E-commerce at scale

Photorealism and material fidelity at 6–11 credits per image keep catalog-scale generation affordable.

Reviews

9,800+ developers. One API.

Real Apiframe reviews from Trustpilot and G2.

Speeds up our ad creative iteration

The API integrates directly into my existing pipeline, so I can generate and iterate on image variations for Meta ads without jumping between tools. We can go from concept to a testable ad in the same day instead of spreading it across a week.

Ethan M. July 2026 G2

Fast, reliable, easy to integrate

Image generation requests are processed quickly, and the results are consistently high quality. Customer support has also been responsive whenever I had questions. It has saved me a lot of development time.

Nana Arianto July 2026 Trustpilot

Seamless integrations, effortless setup

Generating ad creatives for Facebook and Google ads is more streamlined now since we use APIFRAME to manage the workflow, which used to require a lot of time with official APIs. The initial setup was very easy, just a matter of using curl.

Bean A. July 2026 G2

Seedream 5.0 Pro questions

What teams ask before shipping with Seedream 5.0 Pro. Everything else lives in the docs.

What is Seedream 5.0 Pro?

ByteDance's flagship Seedream 5.0 Pro, a unified text-to-image and image-editing model that generates sharp 1K and 2K images from text or up to 10 reference images.

What resolutions does it support?

It generates at 1K (around 2 MP) and 2K (around 4 MP), with 2K as the default. Pricing is tiered by the resolution you request.

How is it different from Seedream 5 Lite?

Pro is the flagship generation-and-editing tier tuned for sharp 1K/2K output, multi-reference workflows, precision editing, and stronger multilingual text rendering, where Lite trades some of that for speed and lower cost.

How many reference images can it use?

Up to 10 reference images in a single generation for single- and multi-reference composition and editing.

Where can you access it?

Through Apiframe with a single API, async jobs, and webhooks. Apiframe routes to BytePlus ModelArk with Replicate as a fallback.