Seedream v4.5 Sequential API by ByteDance
ByteDance latest image generation model with batch generation support. Generate up to 15 images in a single request.
코드 예시
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-v4.5/sequential",
"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()설치
사용하는 언어에 필요한 패키지를 설치하세요.
pip install requests인증
모든 API 요청에는 API 키를 통한 인증이 필요합니다. Atlas Cloud 대시보드에서 API 키를 받을 수 있습니다.
export ATLASCLOUD_API_KEY="your-api-key-here"HTTP 헤더
import os
API_KEY = os.environ.get("ATLASCLOUD_API_KEY")
headers = {
"Content-Type": "application/json",
"Authorization": f"Bearer {API_KEY}"
}클라이언트 측 코드나 공개 저장소에 API 키를 노출하지 마세요. 대신 환경 변수 또는 백엔드 프록시를 사용하세요.
요청 제출
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())요청 제출
비동기 생성 요청을 제출합니다. API는 상태 확인 및 결과 조회에 사용할 수 있는 예측 ID를 반환합니다.
/api/v1/model/generateImage요청 본문
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-v4.5/sequential",
"input": {
"prompt": "A beautiful landscape with mountains and lake"
}
}
response = requests.post(url, headers=headers, json=data)
result = response.json()
print(f"Prediction ID: {result['id']}")
print(f"Status: {result['status']}")응답
{
"id": "pred_abc123",
"status": "processing",
"model": "model-name",
"created_at": "2025-01-01T00:00:00Z"
}상태 확인
예측 엔드포인트를 폴링하여 요청의 현재 상태를 확인합니다.
/api/v1/model/prediction/{prediction_id}폴링 예시
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)상태 값
processing요청이 아직 처리 중입니다.completed생성이 완료되었습니다. 출력을 사용할 수 있습니다.succeeded생성이 성공했습니다. 출력을 사용할 수 있습니다.failed생성에 실패했습니다. 오류 필드를 확인하세요.완료 응답
{
"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"
}
}파일 업로드
Atlas Cloud 스토리지에 파일을 업로드하고 API 요청에 사용할 수 있는 URL을 받습니다. multipart/form-data를 사용하여 업로드합니다.
/api/v1/model/uploadMedia업로드 예시
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}")응답
{
"data": {
"download_url": "https://storage.atlascloud.ai/uploads/abc123/image.png",
"file_name": "image.png",
"content_type": "image/png",
"size": 1024000
}
}입력 Schema
다음 매개변수가 요청 본문에서 사용 가능합니다.
사용 가능한 매개변수가 없습니다.
요청 본문 예시
{
"model": "bytedance/seedream-v4.5/sequential"
}출력 Schema
API는 생성된 출력 URL이 포함된 예측 응답을 반환합니다.
응답 예시
{
"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 Skills는 300개 이상의 AI 모델을 AI 코딩 어시스턴트에 직접 통합합니다. 한 번의 명령으로 설치하고 자연어로 이미지, 동영상 생성 및 LLM과 대화할 수 있습니다.
지원 클라이언트
설치
npx skills add AtlasCloudAI/atlas-cloud-skillsAPI 키 설정
Atlas Cloud 대시보드에서 API 키를 받아 환경 변수로 설정하세요.
export ATLASCLOUD_API_KEY="your-api-key-here"기능
설치 후 AI 어시스턴트에서 자연어를 사용하여 모든 Atlas Cloud 모델에 접근할 수 있습니다.
MCP Server
Atlas Cloud MCP Server는 Model Context Protocol을 통해 IDE와 300개 이상의 AI 모델을 연결합니다. MCP 호환 클라이언트에서 사용할 수 있습니다.
지원 클라이언트
설치
npx -y atlascloud-mcp설정
다음 설정을 IDE의 MCP 설정 파일에 추가하세요.
{
"mcpServers": {
"atlascloud": {
"command": "npx",
"args": [
"-y",
"atlascloud-mcp"
],
"env": {
"ATLASCLOUD_API_KEY": "your-api-key-here"
}
}
}
}사용 가능한 도구
API 스키마
스키마를 사용할 수 없음Seedream사운드와 비전, 원테이크로 완벽 동기화
ByteDance의 혁신적인 AI 모델로 단일 통합 프로세스에서 완벽하게 동기화된 오디오와 비디오를 동시에 생성합니다. 8개 이상의 언어에서 밀리초 단위 정밀도의 립싱크를 제공하는 진정한 네이티브 오디오-비주얼 생성을 경험하세요.
Key Updates
Experience the next level of AI-powered visual creation
Superior Aesthetics
Produces cinematic visuals with refined lighting and rendering for professional-grade output.
Higher Consistency
Maintains stable subjects, clear details, and coherent scenes across multiple images.
Smarter Instruction Following
Accurately responds to complex prompts with precise visual control and interactive editing.
Stronger Spatial Understanding
Generates realistic proportions, object placement, and scene layout with accuracy.
Richer World Knowledge
Creates knowledge-based visuals with accurate scientific and technical reasoning.
Deeper Industry Application
Supports professional workflows for e-commerce, film, advertising, gaming, and more.
Industry Applications
E-commerce
Product photography & marketing
Film & TV
Concept art & storyboarding
Advertising
Campaign visuals & creatives
Gaming
Character & environment design
Education
Instructional illustrations
Interior Design
Space visualization
Architecture
Architectural rendering
Fashion
Virtual try-on & styling
Improvements from 4.0
See how Seedream 4.5 outperforms the previous version
Face Quality
Significant improvement when face proportion is small
Text Rendering
Enhanced small character rendering capability
ID Preservation
Stronger identity retention ability
네이티브 오디오-비주얼 생성 경험
Seedance 1.5 Pro의 획기적인 기술로 비디오 콘텐츠 제작을 혁신하고 있는 전 세계 영화 제작자, 광고주, 크리에이터들과 함께하세요.
Seedream 4.5 : A professional, high-fidelity multimodal image generation model by ByteDance Seed
Model Card Overview
| Field | Description |
|---|---|
| Model Name | Seedream 4.5 |
| Developed By | ByteDance Seed |
| Release Date | December 2025 |
| Model Type | Multimodal Image Generation |
| Related Links | Official Website,Technical Paper (arXiv), GitHub Repository |
Introduction
Seedream 4.5 is a state-of-the-art, multimodal generative model engineered for scalability, efficiency, and professional-grade output. As an advanced version of Seedream 4.0, it is built upon a unified framework that seamlessly integrates text-to-image synthesis, sophisticated image editing, and complex multi-image composition. The model's primary design goal is to deliver professional visual creatives with exceptional consistency and fidelity. This is achieved through a significant scaling of the model architecture and training data, which enhances its ability to preserve reference details, render dense text and typography accurately, and understand nuanced user instructions.
Key Features & Innovations
- Unified Multimodal Framework: Integrates text-to-image (T2I), single-image editing, and multi-image composition into a single, cohesive model, allowing for diverse and flexible creative workflows.
- High-Fidelity & High-Resolution Generation: Capable of generating native high-resolution images (up to 4K), capturing fine details, realistic textures, and accurate lighting for professional use cases.
- Advanced Image Editing: Excels at preserving the core structure, lighting, and color tone of reference images while applying precise edits based on natural language instructions.
- Enhanced Multi-Image Composition: Accurately identifies and blends main subjects from multiple reference images, enabling complex creative compositions and style fusions.
- Superior Typography and Text Rendering: Features significantly improved capabilities for rendering clear, legible, and contextually integrated text within images.
- Efficient and Scalable Architecture: Built on a highly efficient Diffusion Transformer (DiT) and a powerful Variational Autoencoder (VAE), enabling fast inference and effective scalability.
- Optimized for Professional Use: Demonstrates strong performance in generating structured, knowledge-based content such as design materials, posters, and product visualizations, bridging the gap between creative generation and practical industry applications.
Model Architecture & Technical Details
Seedream 4.5's architecture is an extension of the foundation laid by Seedream 4.0. The core of the model is a highly efficient and scalable Diffusion Transformer (DiT), which significantly increases model capacity while reducing computational requirements for training and inference. This is paired with a powerful Variational Autoencoder (VAE) with a high compression ratio, which minimizes the number of image tokens processed in the latent space, further boosting efficiency.
Training and Data: The model was pre-trained on billions of text-image pairs, covering a vast range of taxonomies and knowledge-centric concepts. Training was conducted in multiple stages, starting at a 512x512 resolution and fine-tuning at progressively higher resolutions up to 4K. The post-training phase is extensive, incorporating Continuing Training (CT) for foundational knowledge, Supervised Fine-Tuning (SFT) for artistic quality, and Reinforcement Learning from Human Feedback (RLHF) to align outputs with human preferences. A sophisticated Prompt Engineering (PE) module, built upon the Seed1.5-VL vision-language model, is used to process user inputs and enhance instruction following.
Intended Use & Applications
Seedream 4.5 is designed for professional creators and applications demanding high-quality, consistent, and controllable image generation. Its intended uses include:
- Professional Content Creation: Generating cinematic-quality visuals for digital advertising, social media, and print.
- Advanced Photo Editing: Performing complex edits, such as changing clothing materials, modifying backgrounds, or adjusting lighting, while maintaining subject integrity.
- E-commerce and Product Visualization: Creating high-quality product showcases and marketing materials.
- Graphic Design: Designing posters, key visuals, and other materials that require the integration of stylized text and typography.
- Creative Storytelling: Producing sequential, thematically related images for storyboards or visual narratives.
Performance
Seedream 4.5 and its predecessor, Seedream 4.0, have demonstrated top-tier performance on public benchmarks. The models are evaluated on the Artificial Analysis Arena, a real-time competitive leaderboard that ranks models based on blind user votes.
Text-to-Image Leaderboard (December 2025)
| Rank | Model | Developer | ELO Score | Release Date |
|---|---|---|---|---|
| 1 | GPT Image 1.5 (high) | OpenAI | 1,252 | Dec 2025 |
| 2 | Nano Banana Pro | 1,223 | Nov 2025 | |
| 5 | Seedream 4.0 | ByteDance Seed | 1,193 | Sept 2025 |
| 7 | Seedream 4.5 | ByteDance Seed | 1,169 | Dec 2025 |
