Seedream v4.5 Edit Sequential API by ByteDance
ByteDance advanced image editing model with batch generation support. Edit multiple images while preserving facial features and details.
Entrada
Saída
InativoCada execução custará $0.036. Com $10 você pode executar aproximadamente 277 vezes.
Você pode continuar com:
Exemplo de código
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/edit-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()Instalar
Instale o pacote necessário para a sua linguagem de programação.
pip install requestsAutenticação
Todas as solicitações de API requerem autenticação por meio de uma chave de API. Você pode obter sua chave de API no painel do Atlas Cloud.
export ATLASCLOUD_API_KEY="your-api-key-here"Cabeçalhos HTTP
import os
API_KEY = os.environ.get("ATLASCLOUD_API_KEY")
headers = {
"Content-Type": "application/json",
"Authorization": f"Bearer {API_KEY}"
}Nunca exponha sua chave de API em código do lado do cliente ou repositórios públicos. Use variáveis de ambiente ou um proxy de backend.
Enviar uma solicitação
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())Enviar uma solicitação
Envie uma solicitação de geração assíncrona. A API retorna um ID de predição que você pode usar para verificar o status e obter o resultado.
/api/v1/model/generateImageCorpo da solicitação
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/edit-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']}")Resposta
{
"id": "pred_abc123",
"status": "processing",
"model": "model-name",
"created_at": "2025-01-01T00:00:00Z"
}Verificar status
Consulte o endpoint de predição para verificar o status atual da sua solicitação.
/api/v1/model/prediction/{prediction_id}Exemplo de polling
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)Valores de status
processingA solicitação ainda está sendo processada.completedA geração está completa. As saídas estão disponíveis.succeededA geração foi bem-sucedida. As saídas estão disponíveis.failedA geração falhou. Verifique o campo de erro.Resposta concluída
{
"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"
}
}Enviar arquivos
Envie arquivos para o armazenamento do Atlas Cloud e obtenha uma URL que pode ser usada nas suas solicitações de API. Use multipart/form-data para enviar.
/api/v1/model/uploadMediaExemplo de upload
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}")Resposta
{
"data": {
"download_url": "https://storage.atlascloud.ai/uploads/abc123/image.png",
"file_name": "image.png",
"content_type": "image/png",
"size": 1024000
}
}Schema de entrada
Os seguintes parâmetros são aceitos no corpo da solicitação.
Nenhum parâmetro disponível.
Exemplo de corpo da solicitação
{
"model": "bytedance/seedream-v4.5/edit-sequential"
}Schema de saída
A API retorna uma resposta de predição com as URL de saída geradas.
Exemplo de resposta
{
"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
O Atlas Cloud Skills integra mais de 300 modelos de IA diretamente no seu assistente de codificação com IA. Um comando para instalar e depois use linguagem natural para gerar imagens, vídeos e conversar com LLM.
Clientes compatíveis
Instalar
npx skills add AtlasCloudAI/atlas-cloud-skillsConfigurar chave de API
Obtenha sua chave de API no painel do Atlas Cloud e defina-a como variável de ambiente.
export ATLASCLOUD_API_KEY="your-api-key-here"Funcionalidades
Após a instalação, você pode usar linguagem natural no seu assistente de IA para acessar todos os modelos do Atlas Cloud.
MCP Server
O Atlas Cloud MCP Server conecta seu IDE com mais de 300 modelos de IA através do Model Context Protocol. Funciona com qualquer cliente compatível com MCP.
Clientes compatíveis
Instalar
npx -y atlascloud-mcpConfiguração
Adicione a seguinte configuração ao arquivo de configuração de MCP do seu IDE.
{
"mcpServers": {
"atlascloud": {
"command": "npx",
"args": [
"-y",
"atlascloud-mcp"
],
"env": {
"ATLASCLOUD_API_KEY": "your-api-key-here"
}
}
}
}Ferramentas disponíveis
API Schema
Schema não disponívelFaça login para ver o histórico de solicitações
Você precisa fazer login para acessar o histórico de solicitações do modelo.
Fazer LoginSeedreamSom e Imagem, Tudo em Uma Única Tomada
O modelo de IA revolucionário da ByteDance que gera áudio e vídeo perfeitamente sincronizados simultaneamente a partir de um único processo unificado. Experimente a verdadeira geração nativa áudio-visual com sincronização labial de precisão milimétrica em mais de 8 idiomas.
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
Experimente a Geração Nativa Áudio-Visual
Junte-se a cineastas, anunciantes e criadores de todo o mundo que estão revolucionando a criação de conteúdo de vídeo com a tecnologia inovadora do Seedance 1.5 Pro.
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 |
