Seedream 4.5

Specs & limits

• Released December 2025 (version date 251128 encoded in the model id)
• no dedicated docs model page (console-only detail)

per ByteDance official docs ↗

One prompt, measured through the gateway

PROMPT A weathered enamel diner mug on a steel counter, the words "OPEN 24H" stencilled on the mug in worn paint, low winter sun raking in from the left, shallow depth of field.

Seedream 4.5

Model returned 2048×2048 latency 9 s

One prompt, one request per model, no retries and no cherry-picking - the first result each model returned. Neither size nor duration was pinned: each model used its own default, because a request shaped to fit all of them would flatter none. Files here are re-encoded for the web, so judge composition and prompt adherence, not compression.

Use Seedream 4.5 in 30 seconds

OpenAI-compatible: swap the base_url, keep your SDK. POST /v1/images/generations

from openai import OpenAI

client = OpenAI(
    base_url="https://synthorai.io/v1",
    api_key="sk-syn-...",
)

resp = client.images.generate(
    model="seedream-4-5-251128",
    prompt="a watercolor lighthouse at dawn",
    size="1024x1024",
)
print(resp.data[0].b64_json[:80])

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://synthorai.io/v1",
  apiKey: "sk-syn-...",
});

const resp = await client.images.generate({
  model: "seedream-4-5-251128",
  prompt: "a watercolor lighthouse at dawn",
  size: "1024x1024",
});
console.log(resp.data?.[0]?.b64_json?.slice(0, 80));

curl https://synthorai.io/v1/images/generations \
  -H "Authorization: Bearer sk-syn-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedream-4-5-251128",
    "prompt": "a watercolor lighthouse at dawn",
    "size": "1024x1024"
  }'

package main

import (
	"context"
	"fmt"

	"github.com/openai/openai-go/v3"
	"github.com/openai/openai-go/v3/option"
)

func main() {
	client := openai.NewClient(
		option.WithBaseURL("https://synthorai.io/v1"),
		option.WithAPIKey("sk-syn-..."),
	)
	resp, _ := client.Images.Generate(context.TODO(), openai.ImageGenerateParams{
		Model:  "seedream-4-5-251128",
		Prompt: "a watercolor lighthouse at dawn",
		Size:   "1024x1024",
	})
	fmt.Println(resp.Data[0].B64JSON[:80])
}

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.images.*;

OpenAIClient client = OpenAIOkHttpClient.builder()
    .baseUrl("https://synthorai.io/v1")
    .apiKey("sk-syn-...")
    .build();

ImagesResponse resp = client.images().generate(
    ImageGenerateParams.builder()
        .model("seedream-4-5-251128")
        .prompt("a watercolor lighthouse at dawn")
        .size("1024x1024")
        .build());
System.out.println(resp.data().orElseThrow().get(0).b64Json().orElseThrow().substring(0, 80));

About Seedream 4.5

• The official release notes cite significant improvements in editing consistency, such as preserving subject details and lighting or color tones, plus portrait enhancement and small-text generation; BytePlus classifies the release as a version update rather than a new model, and those three areas are the whole of its officially claimed advance over 4.0.
• It supports text-to-image, single and multi-reference image-to-image with up to 14 reference images, batch image generation, streaming output, and 2K or 4K results, focusing on high-quality standard-mode generation.
• That focus is literal: 4.5 drops both the 1K tier and the faster prompt-optimization mode 4.0 offers, so the minimum output rises to roughly 2560x1440 and every request runs in standard mode.
• The batch rule carries over, with reference images plus generated images capped at fifteen, and output remains JPEG with no format choice.
• BytePlus's prompt guide adds two practical habits for this generation: wrap literal strings in double quotation marks so they render as written, and mark up a reference image with arrows or boxes to point an edit at a region.
• It also notes that 4.0 and 4.5 need less description than earlier versions to hit the intended image.
• Synthorai makes it available through the OpenAI-compatible image generation endpoint.

FAQ

Related models

Compare