bytedance/seedream-v4/edit

圖生圖

Seedream v4 Edit API by ByteDance

bytedance/seedream-v4/edit

Edit

Open and Advanced Large-Scale Image Generative Models.

輸入

正在載入參數設定...

輸出

閒置

生成的圖片將在這裡顯示

設定參數後點擊執行開始生成

每次執行將花費 $0.027。$10 可執行約 370 次。

你可以繼續：

圖生影片圖生圖

參數

程式碼範例
import requests
import time

# Step 1: Start image generation
generate_url = "https://api.atlascloud.ai/api/v1/model/generateImage"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer $ATLASCLOUD_API_KEY"
}
data = {
    "model": "bytedance/seedream-v4/edit",
    "prompt": "A beautiful landscape with mountains and lake",
    "width": 512,
    "height": 512,
    "steps": 20,
    "guidance_scale": 7.5,
}

generate_response = requests.post(generate_url, headers=headers, json=data)
generate_result = generate_response.json()
prediction_id = generate_result["data"]["id"]

# Step 2: Poll for result
poll_url = f"https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}"

def check_status():
    while True:
        response = requests.get(poll_url, headers={"Authorization": "Bearer $ATLASCLOUD_API_KEY"})
        result = response.json()

        if result["data"]["status"] == "completed":
            print("Generated image:", result["data"]["outputs"][0])
            return result["data"]["outputs"][0]
        elif result["data"]["status"] == "failed":
            raise Exception(result["data"]["error"] or "Generation failed")
        else:
            # Still processing, wait 2 seconds
            time.sleep(2)

image_url = check_status()

安裝

安裝所需的相依套件。

pip install requests

驗證

所有 API 請求都需要透過 API Key 進行認證。您可以在 Atlas Cloud 控制台取得 API Key。

export ATLASCLOUD_API_KEY="your-api-key-here"

HTTP 標頭

import os

API_KEY = os.environ.get("ATLASCLOUD_API_KEY")
headers = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {API_KEY}"
}

保護好您的 API Key

切勿在客戶端程式碼或公開儲存庫中暴露您的 API Key。請使用環境變數或後端代理。

提交請求

import requests

url = "https://api.atlascloud.ai/api/v1/model/generateImage"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer $ATLASCLOUD_API_KEY"
}
data = {
    "model": "your-model",
    "prompt": "A beautiful landscape"
}

response = requests.post(url, headers=headers, json=data)
print(response.json())

提交請求

提交一個非同步生成請求。API 會傳回一個 prediction ID，您可以用它來檢查狀態與取得結果。

POST/api/v1/model/generateImage

請求主體

import requests

url = "https://api.atlascloud.ai/api/v1/model/generateImage"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer $ATLASCLOUD_API_KEY"
}

data = {
    "model": "bytedance/seedream-v4/edit",
    "prompt": "A beautiful landscape with mountains and lake"
}

response = requests.post(url, headers=headers, json=data)
result = response.json()

print(f"Prediction ID: {result['data']['id']}")
print(f"Status: {result['data']['status']}")

回應

{
  "code": 200,
  "data": {
    "id": "pred_abc123",
    "status": "processing",
    "model": "model-name",
    "created_at": "2025-01-01T00:00:00Z"
  }
}

檢查狀態

輪詢 prediction 端點以檢查請求的當前狀態。

GET/api/v1/model/prediction/{prediction_id}

輪詢範例

import requests
import time

prediction_id = "pred_abc123"
url = f"https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}"
headers = { "Authorization": "Bearer $ATLASCLOUD_API_KEY" }

while True:
    response = requests.get(url, headers=headers)
    result = response.json()
    status = result["data"]["status"]
    print(f"Status: {status}")

    if status in ["completed", "succeeded"]:
        output_url = result["data"]["outputs"][0]
        print(f"Output URL: {output_url}")
        break
    elif status == "failed":
        print(f"Error: {result['data'].get('error', 'Unknown')}")
        break

    time.sleep(3)

狀態值

processing請求仍在處理中。

completed生成完成，輸出可用。

succeeded生成成功，輸出可用。

failed生成失敗，請檢查 error 欄位。

完成回應

{
  "data": {
    "id": "pred_abc123",
    "status": "completed",
    "outputs": [
      "https://storage.atlascloud.ai/outputs/result.png"
    ],
    "metrics": {
      "predict_time": 8.3
    },
    "created_at": "2025-01-01T00:00:00Z",
    "completed_at": "2025-01-01T00:00:10Z"
  }
}

上傳檔案

將檔案上傳到 Atlas Cloud 儲存空間，取得可在 API 請求中使用的 URL。使用 multipart/form-data 上傳。

POST/api/v1/model/uploadMedia

上傳範例

import requests

url = "https://api.atlascloud.ai/api/v1/model/uploadMedia"
headers = { "Authorization": "Bearer $ATLASCLOUD_API_KEY" }

with open("image.png", "rb") as f:
    files = {"file": ("image.png", f, "image/png")}
    response = requests.post(url, headers=headers, files=files)

result = response.json()
download_url = result["data"]["download_url"]
print(f"File URL: {download_url}")

回應

{
  "data": {
    "download_url": "https://storage.atlascloud.ai/uploads/abc123/image.png",
    "file_name": "image.png",
    "content_type": "image/png",
    "size": 1024000
  }
}

Input Schema

以下參數在請求主體中被接受。

總計: 0必填: 0選填: 0

暫無可用參數。

範例請求主體

{
  "model": "bytedance/seedream-v4/edit"
}

Output Schema

API 傳回包含生成輸出 URL 的 prediction 回應。

idstringrequired

Unique identifier for the prediction.

statusstringrequired

Current status of the prediction.

processingcompletedsucceededfailed

modelstringrequired

The model used for generation.

outputsarray[string]

Array of output URLs. Available when status is "completed".

errorstring

Error message if status is "failed".

metricsobject

Performance metrics.

predict_timenumber

Time taken for image generation in seconds.

created_atstringrequired

ISO 8601 timestamp when the prediction was created.

Format: date-time

completed_atstring

ISO 8601 timestamp when the prediction was completed.

Format: date-time

範例回應

{
  "id": "pred_abc123",
  "status": "completed",
  "model": "model-name",
  "outputs": [
    "https://storage.atlascloud.ai/outputs/result.png"
  ],
  "metrics": {
    "predict_time": 8.3
  },
  "created_at": "2025-01-01T00:00:00Z",
  "completed_at": "2025-01-01T00:00:10Z"
}

Atlas Cloud Skills

Atlas Cloud Skills 將 300+ AI 模型直接整合到您的 AI 程式碼助手中。一條命令安裝，即可用自然語言生成圖片、影片，以及與 LLM 對話。

支援的客戶端

Claude Code

OpenAI Codex

Gemini CLI

Cursor

Windsurf

VS Code

Trae

GitHub Copilot

Cline

Roo Code

Amp

Goose

Replit

40+ 支援的客戶端

安裝

npx skills add AtlasCloudAI/atlas-cloud-skills

設定 API Key

從 Atlas Cloud 控制台取得 API Key，並將其設定為環境變數。

export ATLASCLOUD_API_KEY="your-api-key-here"

功能

安裝完成後，您可以在 AI 助手中使用自然語言存取所有 Atlas Cloud 模型。

圖片生成使用 Nano Banana 2、Z-Image 等模型生成圖片。

影片創作使用 Kling、Vidu、Veo 等從文字或圖片創建影片。

LLM 對話與 Qwen、DeepSeek 及其他大型語言模型對話。

媒體上傳上傳本機檔案用於圖片編輯和圖生影片工作流程。

MCP Server

Atlas Cloud MCP Server 透過 Model Context Protocol 將您的 IDE 與 300+ AI 模型連接。支援任何相容 MCP 的客戶端。

支援的客戶端

Cursor

VS Code

Windsurf

Claude Code

OpenAI Codex

Gemini CLI

Cline

Roo Code

100+ 支援的客戶端

安裝

npx -y atlascloud-mcp

設定

將以下設定新增到您的 IDE 的 MCP 設定檔中。

{
  "mcpServers": {
    "atlascloud": {
      "command": "npx",
      "args": [
        "-y",
        "atlascloud-mcp"
      ],
      "env": {
        "ATLASCLOUD_API_KEY": "your-api-key-here"
      }
    }
  }
}

可用工具

atlas_generate_image根據文字提示生成圖片。

atlas_generate_video從文字或圖片創建影片。

atlas_chat與大型語言模型對話。

atlas_list_models瀏覽 300+ 可用 AI 模型。

atlas_quick_generate一步式內容創建，自動選擇最佳模型。

atlas_upload_media上傳本機檔案用於 API 工作流程。

了解更多

github.com/AtlasCloudAI/mcp-server

API Schema

Schema 不可用

暫無可用範例

載入中...

模型亮點

具備五大核心能力：精準指令編輯、高特徵保留、深度意圖理解、多圖輸入輸出和超高清解析度。涵蓋多樣化創作場景，讓每一個靈感瞬間高品質呈現。

精準指令編輯

只需用通俗語言描述需求，即可精準執行增刪改換操作。支援商業設計、藝術創作和娛樂等領域應用。

高特徵保留

角色一致性：在不同創作風格（插畫/3D/攝影）下高度保持角色特徵，讓創作始終可控

場景保留：最大化保留原始圖像細節，不用擔心編輯後的「AI 油膩感」，實現無損編輯

深度意圖理解

知識升級：專家級知識庫，文本理解能力更上一層

靈感具象：從抽象到具體，將「天馬行空」的靈感化為現實

預測推理：更強的推理能力，模擬跨時空的預測，讓看不見的變得可見

自適應比例：開啟後自動為您的圖像匹配最佳寬高比

多圖輸入輸出

一次性輸入多張圖像，支援組合、遷移、替換、衍生等複雜編輯操作，實現高難度合成

超高清解析度

解析度再次升級，支援超高清輸出，專業級圖像品質

應用場景

🎨

商業設計

🖼️

藝術創作

📸

照片編輯

🎮

遊戲資源

👤

角色設計

🏗️

建築視覺化

📱

社群媒體

🎬

影視動畫

Precision Editing

Perspective & Composition Control

Transform camera angles, adjust scene distance, and modify aspect ratios with precision

Prompt Template

Change the camera angle from eye-level to bird's-eye view, adjust the scene from close-up to medium shot, and convert the image aspect ratio to 16:9. Maintain all original elements and lighting while adapting the composition for the new perspective and format.

Text & Formula Generation

Mathematical Whiteboard Creation

Generate clean whiteboard with precise mathematical formulas and equations

Prompt Template

Create a clean white whiteboard with the following mathematical equations written in clear, professional handwriting: E=mc², √(9)=3, and the quadratic formula (-b±√(b²-4ac))/2a. Use black or dark blue marker style, with proper spacing and mathematical notation.

Deep Intent Understanding

Sketch to Reality Transformation

Transform rough sketches into detailed realistic objects - bringing wild imagination to life

Prompt Template

Based on this rough sketch, generate a vintage television set from the 1950s-60s era. Transform the abstract lines and shapes into a realistic, detailed old-style TV with wooden cabinet, rounded screen, control knobs, and period-appropriate design elements. Make the vague concept concrete and lifelike.

High Feature Preservation

Lossless Detail Enhancement

Maximize original image detail retention, avoiding AI-generated artifacts for truly lossless editing

Prompt Template

Enhance this image while maximizing the preservation of original details. Avoid any AI-generated 'plastic' or 'oily' artifacts. Maintain authentic textures, natural lighting, and original image characteristics. Focus on clean, lossless enhancement that respects the source material's integrity.

Text Transformation

Creative Font Styling

Transform plain text into artistic, creative typography while maintaining readability

Prompt Template

Transform all the text in this image into creative, artistic fonts. Replace the standard typography with stylized lettering that matches the image's aesthetic - use decorative fonts, calligraphy styles, or artistic text treatments. Maintain the same text content and layout while making the typography more visually appealing and creative.

核心能力

生成

文生圖創作

先進的文本理解和圖像生成能力，支援各種藝術風格和專業需求，從概念到成品一步到位。

編輯

智能圖像編輯

基於自然語言的編輯命令，支援對象新增/移除、風格遷移、背景替換等更複雜的編輯操作。

合成

多圖組合

革命性的多圖輸入能力，實現複雜的圖像合成、風格遷移和創意組合，控制力前所未有。

為什麼選擇 Seedream 4.0？

🚀

一體化解決方案

單一模型處理生成、編輯和合成 - 無需在不同工具間切換

🎯

專業品質

商業級輸出品質，對每個細節精確控制

🔄

一致的風格

在多次生成和編輯中保持角色和風格的一致性

技術規格

模型架構：由 ByteDance 豆包 AI 提供支持

核心特性：生成 + 編輯整合

解析度支援：超高清輸出

輸入支援：文本、單圖/多圖

輸出格式：PNG、JPEG、WebP

API 整合：RESTful API 與 SDK 支援

體驗 Seedream 4.0 的強大功能

加入全球創作者行列，用 ByteDance 最先進的整合圖像 AI 模型革新視覺內容創作。

✨專業工具

⚡閃電般快速

🌐一體化平台

Seedream 4: A next-generation multimodal image generation system developed by ByteDance Seed

Model Card Overview

Field	Description
Model Name	Seedream 4
Developed by	ByteDance Seed Team
Release Date	September 9, 2025
Model Type	Multimodal Image Generation
Related Links	Official Website, Technical Report (arXiv), GitHub Organization (ByteDance-Seed)

Introduction

Seedream 4 is a powerful, efficient, and high-performance multimodal image generation system that unifies text-to-image (T2I) synthesis, image editing, and multi-image composition within a single, integrated framework. Engineered for scalability and efficiency, the model introduces a novel diffusion transformer (DiT) architecture combined with a powerful Variational Autoencoder (VAE). This design enables the fast generation of native high-resolution images up to 4K, while significantly reducing computational requirements compared to its predecessors.

The primary goal of Seedream 4 is to extend traditional T2I systems into a more interactive and multidimensional creative tool. It is designed to handle complex tasks involving precise image editing, in-context reasoning, and multi-image referencing, pushing the boundaries of generative AI for both creative and professional applications.

Key Features & Innovations

Seedream 4 introduces several key advancements in image generation technology:

Unified Multimodal Architecture: It integrates T2I generation, image editing, and multi-image composition into a single model, allowing for seamless transitions between different creative workflows.
Efficient and Scalable Design: The model features a highly efficient DiT backbone and a high-compression VAE, achieving over 10x inference acceleration compared to Seedream 3.0 while delivering superior performance. This architecture is hardware-friendly and easily scalable.
Ultra-Fast, High-Resolution Output: Seedream 4 can generate native high-resolution images (from 1K to 4K) in as little as 1.4 to 1.8 seconds for a 2K image, greatly enhancing user interaction and production efficiency.
Advanced Multimodal Capabilities: The model excels at complex tasks such as precise, instruction-based image editing, in-context reasoning, and generating new images by blending elements from multiple reference images.
Professional and Knowledge-Based Content Generation: Beyond artistic imagery, Seedream 4 can generate structured and knowledge-based content, including charts, mathematical formulas, and professional design materials, bridging the gap between creative expression and practical application.
Advanced Training and Acceleration: The model is pre-trained on billions of text-image pairs and utilizes a multi-stage post-training process (CT, SFT, RLHF) to enhance its capabilities. Inference is accelerated through a combination of adversarial distillation, quantization, and speculative decoding.

Model Architecture & Technical Details

Seedream 4's architecture is a significant leap forward, focusing on efficiency and power. The core components are a diffusion transformer (DiT) and a Variational Autoencoder (VAE).

Pre-training Data: Billions of text-image pairs, including a specialized pipeline for knowledge-related data like instructional images and formulas.
Training Strategy: A multi-stage approach, starting at a 512x512 resolution and fine-tuning at higher resolutions up to 4K.
Post-training: A joint multi-task process involving Continuing Training (CT), Supervised Fine-Tuning (SFT), and Reinforcement Learning from Human Feedback (RLHF) to enhance instruction following and alignment.
Inference Acceleration: A holistic system combining an adversarial learning framework, hardware-aware quantization (adaptive 4/8-bit), and speculative decoding.

Intended Use & Applications

Seedream 4 is designed for a wide range of creative and professional applications, moving beyond simple image generation to become a comprehensive visual content creation tool.

Creative Content Generation: Creating high-quality, artistic images, illustrations, and concept art from text prompts.
Advanced Image Editing: Performing complex edits on existing images using natural language instructions, such as adding or removing objects, changing styles, and modifying backgrounds.
Design and Marketing: Generating professional design materials, product mockups, and marketing visuals with precise control over text and branding elements.
Educational and Technical Content: Creating structured, knowledge-based visuals like diagrams, charts, and mathematical formulas for educational or technical documentation.
Multi-Image Composition: Blending elements from multiple source images to create new compositions, such as virtual try-ons for fashion or combining characters with new scenes.

Performance

Seedream 4 has demonstrated state-of-the-art performance on both internal and public benchmarks as of September 18, often outperforming other leading models in text-to-image and image editing tasks.

MagicBench (Internal Benchmark)

Task	Performance Summary
Text-to-Image	Achieved high scores in prompt following, aesthetics, and text-rendering.
Single-Image Editing	Showed a good balance between prompt following and alignment with the source image.

探索類似模型

NEW

圖生3D

Seed3D 2.0 Image-to-3D

ByteDance Seed3D 2.0 — generates a textured, PBR-shaded 3D model (glb/obj/usd/usdz) from a single input image. Returns a downloadable .zip archive containing the 3D file.

Seedream v5.0 Lite Edit Sequential

ByteDance next-generation image editing model with batch generation support. Edit multiple images while preserving facial features and details.

Seedream v5.0 Lite Sequential

ByteDance next-generation image model with batch generation support. Generate up to 15 related images in a single request.

Seedream v5.0 Lite Edit

ByteDance next-generation image editing model that preserves facial features, lighting, and color tones while enabling professional-quality modifications.

Seedream v5.0 Lite

ByteDance next-generation image model with enhanced quality, typography, and poster design. Supports PNG output and fast prompt optimization mode.

Seedream v4.5

ByteDance latest image generation model achieving all-round improvements. Excels at typography, poster design, and brand visual creation with superior prompt adherence.

Seedream v4.5 Edit

ByteDance advanced image editing model that preserves facial features, lighting, and color tones while enabling professional-quality modifications.

Seedream v4.5 Sequential

ByteDance latest image generation model with batch generation support. Generate up to 15 images in a single request.

Seedream v4.5 Edit Sequential

ByteDance advanced image editing model with batch generation support. Edit multiple images while preserving facial features and details.

Seedream v4

Open and Advanced Large-Scale Image Generative Models.

Seedream v4 Sequential

Open and Advanced Large-Scale Image Generative Models.

Seedream v4 Edit Sequential

Open and Advanced Large-Scale Image Generative Models.

Openai GPT Image 2 Text-to-Image

GPT Image 2 text to image is OpenAI's fast, cost-efficient text-to-image generator powered by GPT-5 guidance. Create photorealistic shots, product renders, concept art, and stylized graphics from natural-language prompts (optionally conditioned with an image). Supports custom aspect ratios, seeds, negative prompts, hex color hints, and style presets. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Openai GPT Image 2 Edit

GPT Image 2 Edit is OpenAI's image model for precise, natural-language edits. Add/remove objects, swap backgrounds, retouch faces, adjust colors/lighting, edit text/graphics, crop/resize, and apply hex color control. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

GPT Image 2 Developer Edit

GPT Image 2 Developer Edit applies natural-language instructions to one or more reference images, with common aspect ratios and 1k, 2k, or supported 4k output tiers. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

GPT Image 2 Developer Text-to-Image

GPT Image 2 Developer Text-to-Image generates polished visuals from natural-language prompts, with common aspect ratios and 1k, 2k, or supported 4k output tiers. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

From$0.009/張

$0.004/張

-50%

一個 API，暢享全模態 AI。

探索全部模型

Seedream v4 Edit API by ByteDance

輸入

輸出

參數

程式碼範例

安裝

驗證

HTTP 標頭

提交請求

提交請求

請求主體

回應

檢查狀態

輪詢範例

狀態值

完成回應

上傳檔案

上傳範例

回應

Input Schema

範例請求主體

Output Schema

範例回應

Atlas Cloud Skills

支援的客戶端

安裝

設定 API Key

功能

MCP Server

支援的客戶端

安裝

設定

可用工具

API Schema

Seedream 4.0 - ByteDance 一體化視覺創作模型

模型亮點

精準指令編輯

高特徵保留

深度意圖理解

多圖輸入輸出

超高清解析度

應用場景

Prompt Examples & Creative Templates

Perspective & Composition Control

Mathematical Whiteboard Creation

Sketch to Reality Transformation

Lossless Detail Enhancement

Creative Font Styling

核心能力

為什麼選擇 Seedream 4.0？

一體化解決方案

專業品質

一致的風格

技術規格

體驗 Seedream 4.0 的強大功能

Seedream 4: A next-generation multimodal image generation system developed by ByteDance Seed

Model Card Overview

Introduction

Key Features & Innovations

Model Architecture & Technical Details

Intended Use & Applications

Performance

探索類似模型

Seed3D 2.0 Image-to-3D

Seedream v5.0 Lite Edit Sequential

Seedream v5.0 Lite Sequential

Seedream v5.0 Lite Edit

Seedream v5.0 Lite

Seedream v4.5

Seedream v4.5 Edit

Seedream v4.5 Sequential

Seedream v4.5 Edit Sequential

Seedream v4

Seedream v4 Sequential

Seedream v4 Edit Sequential

Openai GPT Image 2 Text-to-Image

Openai GPT Image 2 Edit

GPT Image 2 Developer Edit

GPT Image 2 Developer Text-to-Image

一個 API，暢享全模態 AI。