Seedream V5.0 Pro Edit API

doubao/seedream-v5.0-pro/image-to-image

doubao/seedream-v5.0-pro/image-to-image. 이미지, 동영상, 얼굴 바꾸기 모델 API를 살펴보세요. 모델을 시험한 뒤 하나의 통합 REST API로 연결할 수 있습니다.

관련 모델

Seedream V5.0 Pro Edit API 관련 모델 1

전체 매개변수, 출력 스키마 및 실시간 요금

AI 모델 API 마켓하나의 플랫폼, 모든 기능가장 인기이용약관이미지, 동영상, 얼굴 바꾸기 모델 API를 살펴보세요. 모델을 시험한 뒤 하나의 통합 REST API로 연결할 수 있습니다.
prompt *Prompttextarea—≤ 5000 chars
images *Imagesimage_upload—image/* · 1–10 items
resolutionResolutionselect1k1k | 2k
aspect_ratioAspect Ratioselect—1:1 | 1:2 | 2:1 | 1:3 | 3:1 | 2:3 | 3:2 | 3:4 | …
output_formatOutput Formatselectjpegjpeg | png

전체 매개변수, 출력 스키마 및 실시간 요금

자세히 보기하나의 플랫폼, 모든 기능이미지, 동영상, 얼굴 바꾸기 모델 API를 살펴보세요. 모델을 시험한 뒤 하나의 통합 REST API로 연결할 수 있습니다.
imagesarray<string>

API

이미지, 동영상, 얼굴 바꾸기 모델 API를 살펴보세요. 모델을 시험한 뒤 하나의 통합 REST API로 연결할 수 있습니다.

cURL
# 1) Submit — returns { "task_uuid": "..." }
curl -X POST "https://www.namifusion.com/api/v1/marketplace/run/doubao/seedream-v5.0-pro/image-to-image" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "input": {
    "prompt": "Transform the input product photo into a polished premium e-commerce image with clean studio lighting, subtle realistic shadows, enhanced colors, sharper details, and a minimalist light gray background. Preserve the original product shape, materials, branding, and overall composition while improving clarity and visual appeal.",
    "images": [
      "https://kaito-1328216764.cos.ap-tokyo.myqcloud.com/uploads/images/2026-07-09/23c18ba5cb9d.png"
    ],
    "resolution": "1k",
    "aspect_ratio": "1:1",
    "output_format": "jpeg"
  }
}'

# 2) Poll until status is "completed", then read the output URLs
curl "https://www.namifusion.com/api/v1/marketplace/run/tasks/TASK_UUID" \
  -H "Authorization: Bearer YOUR_API_KEY"
Python
import time, requests

API_KEY = "YOUR_API_KEY"
HEADERS = {"Authorization": f"Bearer {API_KEY}"}

# 1) Submit
resp = requests.post(
    "https://www.namifusion.com/api/v1/marketplace/run/doubao/seedream-v5.0-pro/image-to-image",
    headers=HEADERS,
    json={
        "input": {
            "prompt": "Transform the input product photo into a polished premium e-commerce image with clean studio lighting, subtle realistic shadows, enhanced colors, sharper details, and a minimalist light gray background. Preserve the original product shape, materials, branding, and overall composition while improving clarity and visual appeal.",
            "images": [
                "https://kaito-1328216764.cos.ap-tokyo.myqcloud.com/uploads/images/2026-07-09/23c18ba5cb9d.png"
            ],
            "resolution": "1k",
            "aspect_ratio": "1:1",
            "output_format": "jpeg"
        }
    },
)
resp.raise_for_status()  # 401/402/429/5xx stop here instead of polling a bad task
task = resp.json()

# 2) Poll until a terminal state (completed / failed / cancelled).
#    This model is allowed up to 300s server-side.
deadline = time.time() + 360
while task.get("status") not in ("completed", "failed", "cancelled"):
    if time.time() > deadline:
        raise TimeoutError(f"still {task.get('status')} — keep the task_uuid and poll later")
    time.sleep(3)
    poll = requests.get(f"https://www.namifusion.com/api/v1/marketplace/run/tasks/{task['task_uuid']}", headers=HEADERS)
    poll.raise_for_status()
    task = poll.json()

print(task["status"], task.get("output"))
JavaScript
const API_KEY = "YOUR_API_KEY";
const HEADERS = { Authorization: `Bearer ${API_KEY}` };

// 1) Submit
const resp = await fetch("https://www.namifusion.com/api/v1/marketplace/run/doubao/seedream-v5.0-pro/image-to-image", {
  method: "POST",
  headers: { ...HEADERS, "Content-Type": "application/json" },
  body: JSON.stringify({
    "input": {
      "prompt": "Transform the input product photo into a polished premium e-commerce image with clean studio lighting, subtle realistic shadows, enhanced colors, sharper details, and a minimalist light gray background. Preserve the original product shape, materials, branding, and overall composition while improving clarity and visual appeal.",
      "images": [
        "https://kaito-1328216764.cos.ap-tokyo.myqcloud.com/uploads/images/2026-07-09/23c18ba5cb9d.png"
      ],
      "resolution": "1k",
      "aspect_ratio": "1:1",
      "output_format": "jpeg"
    }
  }),
});
if (!resp.ok) throw new Error(`submit failed: ${resp.status} ${await resp.text()}`);
let task = await resp.json();

// 2) Poll until a terminal state (completed / failed / cancelled).
//    This model is allowed up to 300s server-side.
const deadline = Date.now() + 360 * 1000;
while (!["completed", "failed", "cancelled"].includes(task.status)) {
  if (Date.now() > deadline) throw new Error(`still ${task.status} — keep the task_uuid and poll later`);
  await new Promise((r) => setTimeout(r, 3000));
  const poll = await fetch(`https://www.namifusion.com/api/v1/marketplace/run/tasks/${task.task_uuid}`, { headers: HEADERS });
  if (!poll.ok) throw new Error(`poll failed: ${poll.status}`);
  task = await poll.json();
}

console.log(task.status, task.output);

API 문서

Seedream V5.0 Pro Edit API

High-quality image editing from single or multi-reference inputs, with up to 10 reference images and 2K output.

Seedream V5.0 Pro Edit is ByteDance’s advanced image editing model for controlled generation from one or more reference images. It combines strong prompt adherence, flexible aspect ratio support, and production-ready performance with no cold starts, making it well suited for creative workflows, e-commerce pipelines, and iterative visual development.

🚀 Key Features

  • Multi-reference image editing: Use up to 10 reference images for complex compositions, identity preservation, product detail control, and style guidance.
  • Natural language editing: Describe what should change and what should remain intact using a simple prompt.
  • Professional image quality: Designed for polished visual output with strong prompt following and reliable editing performance.
  • Flexible aspect ratios: Supports square, portrait, landscape, tall, and wide formats for a broad range of publishing needs.
  • 1K and 2K output tiers: Choose lower-cost 1K for fast iteration or 2K for higher-resolution final assets.
  • No cold starts: Delivers a more consistent production experience for real-time and batch image workflows.

🛠️ Technical Specifications

ItemDetails
Model architectureImage editing / multi-reference conditional image generation model
Task typetext-to-image(image-guided editing generation)
InputPrompt + 1 to 10 reference images
Output1 edited image
Max reference images10
Aspect Ratio1:1, 1:2, 2:1, 1:3, 3:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 9:21, 21:9
Aspect Ratio behaviorIf left empty, the model automatically uses the closest supported ratio based on the first input image
Resolution1k, 2k
Output Formatjpeg, png
Quality profileProfessional-grade image editing with multi-image guidance
LatencyNo cold start; actual inference time varies by input complexity and output tier

Sample Prompts

  • Keep the subject’s facial features unchanged, replace the background with a modern minimalist cafe, natural lighting, realistic photography style.
  • Use the reference product images to generate a clean e-commerce hero shot with a white background, consistent lighting, and premium material detail.
  • Preserve the outfit design and colors, change the model pose to a side-standing position, optimized for a 9:16 poster composition.

💰 Pricing

ItemPrice
1k output$0.045
2k output$0.090
Additional reference image cost$0.003 per extra input image

Note: The first input image is included in the base price.

💡 Best Use Cases

  • E-commerce image editing: Refine product shots, replace backgrounds, standardize presentation, and create campaign-ready assets.
  • Brand and marketing creative: Generate polished visuals aligned with brand references and campaign direction.
  • Character and identity consistency: Maintain subject identity, outfit details, mood, or style across multiple iterations.
  • Social media content production: Create platform-ready visuals in different aspect ratios for ads, covers, and promotional posts.

🔗 Related Models

  • Seedream V5.0 Pro: Best suited for text-to-image generation without reference image inputs.
  • Seedream V5.0 Lite Edit: A lighter-weight image editing model for more cost- and speed-sensitive workflows.

관련 모델

xAI Grok Imagine Image v2.0 Edit
이미지 변환X Ai

xAI Grok Imagine Image v2.0 Edit

x-ai/grok-imagine-image-v2.0/edit. 이미지, 동영상, 얼굴 바꾸기 모델 API를 살펴보세요. 모델을 시험한 뒤 하나의 통합 REST API로 연결할 수 있습니다.

최저 $0.090 / 실행당
qwen-image-edit-spicy
이미지 변환

qwen-image-edit-spicy

qwen-image-edit-spicy. 이미지, 동영상, 얼굴 바꾸기 모델 API를 살펴보세요. 모델을 시험한 뒤 하나의 통합 REST API로 연결할 수 있습니다.

최저 $0.040 / 실행당
Qwen Image 3.0 Pro Edit | Fast Image Editing
이미지 변환Qwen Image 3.0 Pro

Qwen Image 3.0 Pro Edit | Fast Image Editing

qwen-image-3.0-pro/edit. 이미지, 동영상, 얼굴 바꾸기 모델 API를 살펴보세요. 모델을 시험한 뒤 하나의 통합 REST API로 연결할 수 있습니다.

최저 $0.078 / 실행당
OpenAI GPT Image 2.5 Sunburst Edit
이미지 변환OpenAI

OpenAI GPT Image 2.5 Sunburst Edit

openai/gpt-image-2.5-sunburst/edit. 이미지, 동영상, 얼굴 바꾸기 모델 API를 살펴보세요. 모델을 시험한 뒤 하나의 통합 REST API로 연결할 수 있습니다.

최저 $0.220 / 실행당
OpenAI GPT Image 2.5 Flare Edit
이미지 변환OpenAI

OpenAI GPT Image 2.5 Flare Edit

openai/gpt-image-2.5-flare/edit. 이미지, 동영상, 얼굴 바꾸기 모델 API를 살펴보세요. 모델을 시험한 뒤 하나의 통합 REST API로 연결할 수 있습니다.

최저 $0.220 / 실행당
이미지 변환
이미지 변환NamiFusion

Head Swap (Image)

namifusion/head-swap/image-edit. 이미지, 동영상, 얼굴 바꾸기 모델 API를 살펴보세요. 모델을 시험한 뒤 하나의 통합 REST API로 연결할 수 있습니다.

최저 $0.220 / 실행당
Nano Banana Image Edit
이미지 변환Google

Nano Banana Image Edit

google/nano-banana/edit. 이미지, 동영상, 얼굴 바꾸기 모델 API를 살펴보세요. 모델을 시험한 뒤 하나의 통합 REST API로 연결할 수 있습니다.

최저 $0.038 / 실행당
Nano Banana Pro Image Edit
이미지 변환Google

Nano Banana Pro Image Edit

google/nano-banana-pro/edit. 이미지, 동영상, 얼굴 바꾸기 모델 API를 살펴보세요. 모델을 시험한 뒤 하나의 통합 REST API로 연결할 수 있습니다.

최저 $0.140 / 실행당