bytedance/seedance-v1.5-pro/image-to-video-spicy

image-to-video

PRO

Seedance v1.5 Pro Image-to-Video Spicy API by ByteDance

bytedance/seedance-v1.5-pro/image-to-video-spicy

Image-to-video-spicy

Seedance V1.5 Pro Spicy transforms images into high-quality cinematic video with smooth motion and expressive animations, optimized for creative content at scale.

INPUT

Loading parameter configuration...

OUTPUT

Idle

Your generated videos will appear here

Configure your settings and click Run to get started

Your request will cost $0.049 per run. For $10 you can run this model approximately 204 times.

Here's what you can do next:

Seedance 2.0 Kling v3 Vidu Wan2.7

Parameters

Code Example
import requests
import time

# Step 1: Start video generation
generate_url = "https://api.atlascloud.ai/api/v1/model/generateVideo"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer $ATLASCLOUD_API_KEY"
}
data = {
    "model": "bytedance/seedance-v1.5-pro/image-to-video-spicy",
    "prompt": "A beautiful sunset over the ocean with gentle waves",
    "width": 512,
    "height": 512,
    "duration": 3,
    "fps": 24,
}

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"] in ["completed", "succeeded"]:
            print("Generated video:", 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)

video_url = check_status()

Install

Install the required package for your language.

bash

pip install requests

Authentication

All API requests require authentication via an API key. You can get your API key from the Atlas Cloud dashboard.

bash

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

HTTP Headers

python

import os

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

Keep your API key secure

Never expose your API key in client-side code or public repositories. Use environment variables or a backend proxy instead.

Submit a request

import requests

url = "https://api.atlascloud.ai/api/v1/model/generateVideo"
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())

Submit a Request

Submit an asynchronous generation request. The API returns a prediction ID that you can use to check the status and retrieve the result.

POST/api/v1/model/generateVideo

Request Body

import requests

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

data = {
    "model": "bytedance/seedance-v1.5-pro/image-to-video-spicy",
    "input": {
        "prompt": "A beautiful sunset over the ocean with gentle waves"
    }
}

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

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

Response

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

Check Status

Poll the prediction endpoint to check the current status of your request.

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

Polling Example

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)

Status Values

processingThe request is still being processed.

completedGeneration is complete. Outputs are available.

succeededGeneration succeeded. Outputs are available.

failedGeneration failed. Check the error field.

Completed Response

{
  "data": {
    "id": "pred_abc123",
    "status": "completed",
    "outputs": [
      "https://storage.atlascloud.ai/outputs/result.mp4"
    ],
    "metrics": {
      "predict_time": 45.2
    },
    "created_at": "2025-01-01T00:00:00Z",
    "completed_at": "2025-01-01T00:00:10Z"
  }
}

Upload Files

Upload files to Atlas Cloud storage and get a URL you can use in your API requests. Use multipart/form-data to upload.

POST/api/v1/model/uploadMedia

Upload Example

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}")

Response

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

Input Schema

The following parameters are accepted in the request body.

Total: 0Required: 0Optional: 0

No parameters available.

Example Request Body

json

{
  "model": "bytedance/seedance-v1.5-pro/image-to-video-spicy"
}

Output Schema

The API returns a prediction response with the generated output URLs.

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 video 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

Example Response

json

{
  "id": "pred_abc123",
  "status": "completed",
  "model": "model-name",
  "outputs": [
    "https://storage.atlascloud.ai/outputs/result.mp4"
  ],
  "metrics": {
    "predict_time": 45.2
  },
  "created_at": "2025-01-01T00:00:00Z",
  "completed_at": "2025-01-01T00:00:10Z"
}

Atlas Cloud Skills

Atlas Cloud Skills integrates 300+ AI models directly into your AI coding assistant. One command to install, then use natural language to generate images, videos, and chat with LLMs.

Supported Clients

Claude Code

OpenAI Codex

Gemini CLI

Cursor

Windsurf

VS Code

Trae

GitHub Copilot

Cline

Roo Code

Amp

Goose

Replit

40+ supported clients

Install

bash

npx skills add AtlasCloudAI/atlas-cloud-skills

Setup API Key

Get your API key from the Atlas Cloud dashboard and set it as an environment variable.

bash

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

Capabilities

Once installed, you can use natural language in your AI assistant to access all Atlas Cloud models.

Image GenerationGenerate images with models like Nano Banana 2, Z-Image, and more.

Video CreationCreate videos from text or images with Kling, Vidu, Veo, etc.

LLM ChatChat with Qwen, DeepSeek, and other large language models.

Media UploadUpload local files for image editing and image-to-video workflows.

Learn more

github.com/AtlasCloudAI/atlas-cloud-skills

MCP Server

Atlas Cloud MCP Server connects your IDE with 300+ AI models via the Model Context Protocol. Works with any MCP-compatible client.

Supported Clients

Cursor

VS Code

Windsurf

Claude Code

OpenAI Codex

Gemini CLI

Cline

Roo Code

100+ supported clients

Install

bash

npx -y atlascloud-mcp

Configuration

Add the following configuration to your IDE's MCP settings file.

json

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

Available Tools

atlas_generate_imageGenerate images from text prompts.

atlas_generate_videoCreate videos from text or images.

atlas_chatChat with large language models.

atlas_list_modelsBrowse 300+ available AI models.

atlas_quick_generateOne-step content creation with auto model selection.

atlas_upload_mediaUpload local files for API workflows.

Learn more

github.com/AtlasCloudAI/mcp-server

API Schema

Schema not available

Please log in to view request history

You need to be logged in to access your model request history.

⚡NATIVE AUDIO-VISUAL GENERATION

Seedance 1.5 ProSound and Vision, All in One Take

ByteDance's revolutionary AI model that generates perfectly synchronized audio and video simultaneously from a single unified process. Experience true native audio-visual generation with millisecond-precision lip-sync across 8+ languages.

Revolutionary Innovation

What makes SeeDANCE 1.5 Pro fundamentally different

Dual-Branch Architecture

Uses a 4.5 billion parameter Dual-Branch Diffusion Transformer (DB-DiT) that generates audio and video simultaneously—not sequentially—ensuring perfect synchronization from the start.

Phoneme-Level Lip Sync

Understands individual phonemes and maps them correctly to lip shapes across different languages, achieving millisecond-precision audio-visual synchronization.

Narrative Auto-Completion

Intelligently fills narrative gaps based on prompt intent, maintaining coherent storytelling across characters' emotions, expressions, and actions.

Core Capabilities

Native 1080p Quality

Professional HD video output with cinematic quality at 24fps, supporting 4-12 second durations

8+ Language Support

English, Mandarin, Japanese, Korean, Spanish, Portuguese, Indonesian, plus Chinese dialects

Cinematic Camera Control

Complex camera movements including dolly zooms, tracking shots, and professional film techniques

Multi-Speaker Dialogue

Natural conversations with multiple characters, distinct vocal identities, and realistic turn-taking

Physics-Accurate Motion

Realistic hair dynamics, fluid behaviors, and material interactions for lifelike visuals

Character Consistency

Maintains clothing, faces, and style across scenes for complete story continuity

Seedance 1.5 Pro vs Competition

See how Seedance stands out from other video generation models

Audio-Visual Sync

Native simultaneous generation

Sequential post-processing

Multi-Language

8+ languages with dialects

Limited language support

Lip Sync Accuracy

Phoneme-level precision

Basic synchronization

Duration

5-12 seconds optimized

Wan 2.6: Up to 15s

Camera Control

Professional cinematography

Standard camera movement

Perfect For

Short Drama Production

Create emotion-forward narrative clips with realistic character dialogue and cinematic lighting

Advertising Creatives

Performance-heavy ad content with natural acting, perfect lip-sync, and professional production value

Multilingual Content

Reach global audiences with native-quality audio-visual content in 8+ languages

Educational Videos

Engaging instructional content with clear narration and synchronized visual demonstrations

Social Media

Viral-ready short-form content with professional audio-visual quality for maximum engagement

Film Production

Pre-visualization and concept development with realistic character performances and dialogue

Seedance 1.5 Pro T2V and I2V API Integration

Powerful Text-to-Video (T2V) API and Image-to-Video (I2V) API endpoints for seamless integration

Text-to-Video API (T2V API)

Our Seedance 1.5 Pro T2V API transforms text prompts into complete cinematic videos with native audio-visual synchronization. Generate scenes, camera movements, character actions, and dialogue in a single Text-to-Video API call.

One-step generation with synchronized audio

Full control over duration, aspect ratio, and style

Multi-language dialogue with accurate lip-sync

Professional cinematography from text descriptions

Perfect for:

Automated video content creation at scale
Dynamic storytelling and narrative videos
Marketing campaign automation
Educational content generation

Image-to-Video API (I2V API)

Our Seedance 1.5 Pro I2V API brings still images to life with motion, camera movement, and synchronized audio. The Image-to-Video API features advanced frame control to define precise start and end points for your animations.

First frame control for character identity lock

Last frame control for transition endpoints

Preserves visual style and composition

Consistent character appearance across frames

Perfect for:

Photo animation and enhancement
Character consistency in video sequences
Product showcase with motion effects
Architectural visualization and walkthroughs

💡

Simple T2V and I2V API Integration

Both T2V API and I2V API modes support RESTful architecture with comprehensive documentation. Get started in minutes with SDKs for Python, Node.js, and more. All Seedance 1.5 Pro API endpoints include automatic audio generation with phoneme-level lip synchronization for seamless video creation.

How to Get Started

Start generating videos in minutes with two simple paths

API Integration

For developers building applications

Sign Up & Login

Create your Atlas Cloud account or login to access the console

Add Payment Method

Bind your credit card in the Billing section to fund your account

Generate API Key

Navigate to Console → API Keys and create your authentication key

Start Building

Use the API key to make requests and integrate SeeDANCE into your application

Playground Experience

For quick testing and experimentation

Sign Up & Login

Create your Atlas Cloud account or login to access the platform

Add Payment Method

Bind your credit card in the Billing section to get started

Use Playground

Go to the model playground, enter your prompt, and generate videos instantly with an intuitive interface

💡

Quick Tip: Start with the Playground to test prompts and explore features, then move to API integration when you're ready to scale your production workflow.

Frequently Asked Questions

What makes Seedance 1.5 Pro's audio-visual sync unique?

Unlike other models that generate video first and add audio later, Seedance 1.5 Pro uses a dual-branch architecture to generate both simultaneously. This ensures perfect synchronization from the start, with phoneme-level lip-sync accuracy across all supported languages.

How does it compare to Wan 2.5 or Wan 2.6?

While Wan 2.6 supports longer durations (up to 15s) and text rendering, Seedance 1.5 Pro excels in cinematic camera control, multi-language/dialect support with spatial audio, and physics-accurate motion. Choose based on your needs: Seedance for storytelling and multilingual content, Wan for product demos with text.

What video formats and resolutions are supported?

Seedance 1.5 Pro generates native 1080p videos at 24fps. Supported aspect ratios include 16:9, 9:16, 4:3, 3:4, 1:1, and 21:9. Duration ranges from 4-12 seconds, with Smart Duration allowing the model to select the optimal length automatically.

Which languages are supported for audio generation?

Seedance 1.5 Pro supports 8+ languages including English, Mandarin Chinese, Japanese, Korean, Spanish, Portuguese, Indonesian, and Chinese dialects like Cantonese and Sichuanese. Each language features accurate lip-sync and natural pronunciation.

Can I control specific camera movements?

Yes! Seedance understands technical film grammar. You can specify camera techniques like "Dolly Zoom on the subject" (Hitchcock effect), tracking shots, close-ups, or wide shots. The model interprets these to create professional cinematic results.

What's the difference between Text-to-Video and Image-to-Video?

Text-to-Video generates complete videos from text prompts. Image-to-Video uses a "First Frame" to lock character identity and lighting, with optional "Last Frame" control for precise beginning and end-point transitions. Both modes support full audio generation.

Why Use Seedance 1.5 Pro on Atlas Cloud?

Experience unmatched performance, reliability, and support for your AI video generation needs

Purpose-Built Infrastructure

Our system is specifically optimized for AI model deployment. Run Seedance 1.5 Pro with maximum performance on infrastructure tailored for demanding AI workloads and video generation.

Unified API for All Models

Access Seedance 1.5 Pro alongside 300+ AI models (LLMs, image, video, audio) through one unified API. Manage all your AI needs from a single platform with consistent authentication.

Competitive Pricing

Save up to 70% compared to AWS with transparent, pay-as-you-go pricing. No hidden fees, no minimum commitments—only pay for what you use with volume discounts available.

SOC I & II Certified Security

Your data and generated videos are protected with SOC I & II certifications and HIPAA compliance. Enterprise-grade security with encrypted data transmission and storage.

99.9% Uptime SLA

Enterprise-grade reliability with guaranteed 99.9% uptime. Your Seedance 1.5 Pro video generation is always available for production applications and critical workflows.

Easy Integration

Complete integration in minutes through our simple REST API and multi-language SDKs (Python, Node.js, Go). Comprehensive documentation and code examples get you started fast.

99.9%

Uptime

70%

Lower Cost vs AWS

300+

Gen AI Models

24/7

Pro Support

Technical Specifications

Architecture

Dual-Branch Diffusion Transformer (MMDiT)

Parameters

4.5 Billion

Resolution

Native 1080p (480p, 720p also supported)

Frame Rate

24 FPS

Duration

4-12 seconds (Smart Duration available)

Aspect Ratios

16:9, 9:16, 4:3, 3:4, 1:1, 21:9

Languages

8+ including dialects

Input Modes

Text-to-Video, Image-to-Video

Experience Native Audio-Visual Generation

Join filmmakers, advertisers, and creators worldwide who are revolutionizing video content creation with Seedance 1.5 Pro's groundbreaking technology.

1. Introduction

seedance-v1.5-pro-image-to-video-spicy is an advanced image-to-video generation model developed by ByteDance and offered via third-party platforms such as AtlasCloud.ai and WaveSpeed.ai. It specializes in producing high-quality cinematic video clips from static images, integrating smooth and expressive motion alongside optional synchronized audio output. Positioned as a scalable, unlimited-generation tier, it targets creative storytelling and content production at volume.

This model leverages a dual-branch diffusion transformer architecture to generate temporally coherent video frames and audio waveforms simultaneously. Its capability for bold, vivid motion with stable tonal contrast and multi-aspect ratio support makes it a practical tool for content creators seeking dynamic video renditions of still images. The "Spicy" variant is a platform-specific optimization tier for throughput-focused applications rather than an official ByteDance release.

2. Key Features & Innovations

Dual-Branch Diffusion Transformer Architecture: Employs a 4.5 billion parameter model that simultaneously generates video frames and synchronized audio waveforms through a cross-modal joint module, ensuring millisecond-level audiovisual alignment.
Unlimited-Generation Scalability: Optimized for high-volume production, this tier supports continuous video clip generation without preset usage caps, enabling batch processing at resolutions up to 1080p with durations ranging from 4 to 12 seconds.
Expressive Motion Rendering: Produces cinematic-quality animations with physics-accurate motion, including complex camera movements and natural transitions, enhancing storytelling and visual impact.
Flexible Output Specifications: Supports multiple resolutions (480p, 720p, 1080p), a variety of aspect ratios (21:9, 16:9, 4:3, 1:1, 3:4, 9:16), and duration control between 4 to 12 seconds, allowing customization per platform or project requirements.
Optional Synchronized Audio Generation: Generates multi-language audio with spatial sound effects aligned precisely with video frames, improving the completeness and immersion of audiovisual content.
Platform-Specific Pricing Integration: Available through third-party API aggregators with competitive pricing tiers based on resolution, duration, and audio inclusion, offering cost-effective alternatives to official BytePlus API services.

3. Model Architecture & Technical Details

The core of seedance-v1.5-pro-image-to-video-spicy is a dual-branch diffusion transformer architecture with approximately 4.5 billion parameters. It consists of two interconnected generative pathways: one for video frame sequences and another for audio waveform synthesis. These branches are linked by a cross-modal joint module responsible for millisecond-precise audio-visual synchronization.

The model was trained on a large-scale, diverse dataset containing roughly 100 million minutes of paired audio-video clips, spanning various cinematographic styles and languages. Training incorporates progressive multi-resolution inputs to enhance detail and temporal coherence. Post-training employed advanced fine-tuning approaches to stabilize video quality and support optional audio generation without latency or lip-sync issues.

Supported output formats include varying aspect ratios from ultra-widescreen (21:9) to vertical video (9:16), suited for different display contexts. Moreover, the architecture allows optional fixed-camera settings to simulate locked tripod shots, enhancing usability for specific creative workflows.

4. Performance Highlights

Seedance-v1.5-pro-image-to-video-spicy demonstrates a competitive balance of quality and efficiency in the 2026 AI video generation landscape. While direct benchmark scores are limited due to proprietary evaluations, qualitative assessments place it among leading models for synchronized audiovisual output and scalable batch generation.

Rank	Model	Developer	Pricing per Second (Approx.)	Release Date
1	Google Veo 3.1	Google	$0.75/s	Early 2026
2	Grok Imagine	Grok AI	$0.05/s	2025
3	Kling 3.0	Kling Labs	$0.12 -$ 0.15/s	Mid 2025
4	Seedance V1.5 Pro Spicy	ByteDance / 3rd Party	$0.012 -$ 0.104/s	Dec 2025
5	Runway Gen-4	Runway	Proprietary pricing	2026

Its strength lies in generating smooth cinematic clips with expressive, physics-informed motion and integrated audio, outperforming several models constrained to sequential or video-only synthesis. However, text rendering quality and longer clip durations beyond 15 seconds remain challenging.

Evaluation is typically conducted using proprietary audiovisual coherence metrics and user feedback from commercial deployments in e-commerce and social media content creation.

5. Intended Use & Applications

E-commerce Product Videos: Enables retailers and brands to produce dynamic product demonstrations and promotional clips from static images, enhancing engagement and conversion.
Marketing and Social Media Content: Facilitates the creation of vibrant short-form videos ideal for platforms such as Instagram Reels, TikTok, and YouTube Shorts, supporting scalable campaign generation.
Cinematic Content and Filmmaking: Provides filmmakers and creatives with tools to animate concept art or storyboard images into lifelike scenes with complex motion and audio.
Education and Training: Generates compelling audiovisual materials for instructional and educational purposes, enriching learning experiences with dynamic visual aids.
Content Creator Workflows: Assists creators in rapidly iterating visual concepts and animations with fine control over motion, resolution, and audio synchronization, improving productivity.

Sources: Based on ByteDance Seedance documentation and third-party platform data from AtlasCloud.ai, technical literature, and market analysis as of early 2026.