Seedream 4.0

doubao/seedream-4.0/image-to-image-sequential

Seedream 4.0: 4K image generation and editing with character and object consistency and sequential multi-image outputs. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Examples

Seedream 4.0 example 1

Parameters

NameTypeDefaultConstraintsDescription
images *Imagesimage_uploadimage/* · 1–10 itemsThe images to edit. A maximum of 10 reference images can be uploaded.
prompt *Prompttextarea≤ 5000 charsThe positive prompt for the generation.
sizeSizetext≤ 500 charsThe size of the generated media in pixels (width*height).
max_imagesMax Imagesslider11 ~ 15 · step 1The maximum number of images that can be generated (up to 15). This value must align with the number of images specified in the prompt above.

API

Call this model through one unified REST API. Get a key on the API Keys page.

cURL
# 1) Submit — returns { "task_uuid": "..." }
curl -X POST "https://www.namifusion.com/api/v1/marketplace/run/doubao/seedream-4.0/image-to-image-sequential" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "input": {
    "images": [
      "https://assets-public.namifusion.com/uploads/images/2026-04-21/04f96c6016ee.png",
      "https://assets-public.namifusion.com/uploads/images/2026-04-21/ee16c2ba0571.png"
    ],
    "prompt": "Generate a 4K image of a futuristic cityscape with sleek skyscrapers, flying cars, and glowing neon lights. Please generate a set of 5 images.",
    "size": "3840x2160",
    "max_images": 5
  }
}'

# 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-4.0/image-to-image-sequential",
    headers=HEADERS,
    json={
        "input": {
            "images": [
                "https://assets-public.namifusion.com/uploads/images/2026-04-21/04f96c6016ee.png",
                "https://assets-public.namifusion.com/uploads/images/2026-04-21/ee16c2ba0571.png"
            ],
            "prompt": "Generate a 4K image of a futuristic cityscape with sleek skyscrapers, flying cars, and glowing neon lights. Please generate a set of 5 images.",
            "size": "3840x2160",
            "max_images": 5
        }
    },
)
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-4.0/image-to-image-sequential", {
  method: "POST",
  headers: { ...HEADERS, "Content-Type": "application/json" },
  body: JSON.stringify({
    "input": {
      "images": [
        "https://assets-public.namifusion.com/uploads/images/2026-04-21/04f96c6016ee.png",
        "https://assets-public.namifusion.com/uploads/images/2026-04-21/ee16c2ba0571.png"
      ],
      "prompt": "Generate a 4K image of a futuristic cityscape with sleek skyscrapers, flying cars, and glowing neon lights. Please generate a set of 5 images.",
      "size": "3840x2160",
      "max_images": 5
    }
  }),
});
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);

Documentation

Seedream 4.0

4K Image Generation and Editing with Sequential Consistency

Seedream 4.0 is a state-of-the-art image-to-image model designed for high-resolution (up to 4K) image generation and editing. It excels in maintaining character and object consistency across sequential outputs, making it ideal for creating coherent multi-image sets. With ultra-fast inference, no cold starts, and affordable pricing, Seedream 4.0 is optimized for both performance and cost-efficiency.

🚀 Key Features

  • Sequential Multi-Image Outputs: Generate up to 15 consistent images in one pass, perfect for storyboards, product variants, or matched sets.
  • High Feature Retention: Ensures identity, logos, and layouts remain intact across all outputs.
  • Rich Editing Capabilities: Add/remove elements, adjust attributes or styles, and perform structural tweaks like pose or face swaps.
  • Ultra-High Resolution: Supports resolutions up to 8192×8192 pixels for professional-grade outputs.
  • Fast and Reliable: No cold starts and ultra-fast inference ensure a seamless user experience.
  • Consistency Controls: Strong identity and style preservation across all generated images.

🛠️ Technical Specifications

SpecificationDetails
Model ArchitectureImage-to-Image
Input FormatArray of images (max 10), positive prompt
Output FormatEdited images (up to 15)
Resolution512×512 to 8192×8192 pixels
Max ImagesUp to 15
Pricing$0.03 per image
LatencyUltra-fast inference

Example Prompts

  1. Product Variants: "Generate a series of 4 edited images (Panels 1–4) from the source photo, keeping the same shoe model and logo placement. Maintain identical angle, lighting, and background; change only the colorway per panel."
  2. Character Design: "Create a sequence of 3 images showing the same character in different outfits while preserving facial features and pose."

💰 Pricing

ResolutionPrice per Image
Up to 4K$0.03

Total Price Formula: Total Price = max_images × $0.03

💡 Best Use Cases

  • Commercial Design: Create posters, apparel designs, packaging visuals, or e-commerce product sets with consistent branding.
  • Entertainment IP: Develop character look-dev or key art sequences with locked identity and style.
  • Fine Art & Illustration: Produce multi-piece series with coherent palettes and linework.
  • Architecture: Generate material and lighting variations across consistent viewpoints.
  • Brand Content: Design campaign sets or social media carousels with fixed logos and palettes.

🔗 Related Models

  • Seedream 4.0 Pro: Enhanced editing capabilities with advanced style controls.
  • Seedream 4.0 Ultra: Optimized for ultra-high-resolution outputs beyond 4K.

Related models

xAI Grok Imagine Image v2.0 Edit
Image to ImageX Ai

xAI Grok Imagine Image v2.0 Edit

xAI Grok Imagine Image V2.0 Edit transforms input images with text prompts, with configurable resolution and quality for precise image editing, visual refinements, creative variations, social content, marketing assets, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

from $0.090 / per run
Qwen Image 3.0 Pro Edit | Fast Image Editing
Image to ImageQwen Image 3.0 Pro

Qwen Image 3.0 Pro Edit | Fast Image Editing

Qwen Image 3.0 Pro Edit is a professional-grade image editing model with superior quality and advanced instruction understanding. Up to 2k. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

from $0.080 / per run
Image to Image
Image to ImageNamiFusion

Head Swap (Image)

Swap the head in a photo with the head from a reference image. Upload the target photo first, then the head reference.

from $0.220 / per run
Nami Qwen I2I Spicy
Image to Image

Nami Qwen I2I Spicy

Edit a reference image with natural-language instructions while preserving the parts you do not ask to change.

from $0.040 / per run
Nano Banana Image Edit
Image to ImageGoogle

Nano Banana Image Edit

Fast & Affordable Editing. Intuitive object replacement and style transfer without manual masking.

from $0.040 / per run
Nano Banana Pro Image Edit
Image to ImageGoogle

Nano Banana Pro Image Edit

4K Semantic Editing.Modifies existing images via natural language with context awareness and multilingual text editing.

from $0.140 / per run
Nano Banana 2 Image Edit
Image to ImageGoogle

Nano Banana 2 Image Edit

4K Semantic Editing.Modifies existing images via natural language with context awareness and multilingual text editing.

from $0.070 / per run
Seedream V5.0 Pro Edit API
Image to ImageDoubao

Seedream V5.0 Pro Edit API

Seedream V5.0 Pro Edit by ByteDance edits and generates images from single-image or multi-reference inputs, supporting up to 10 reference images, aspect ratio selection, and 1K / 2K output tiers. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

from $0.050 / per run