# Seedance v1 Pro i2v 720p — Atlas Cloud API

> Seedance Pro’s image-to-video mode transforms still visuals into cinematic motion, maintaining visual consistency and expressive animation across frames.

This is the machine-readable API reference for **Seedance v1 Pro i2v 720p** on Atlas Cloud,
a unified API platform for 400+ AI models across text, image, video, audio and 3D.

- **Model ID**: `bytedance/seedance-v1-pro-i2v-720p`
- **Built by**: ByteDance
- **Modality**: Video
- **Model page**: https://www.atlascloud.ai/models/bytedance/seedance-v1-pro-i2v-720p
- **API key**: https://www.atlascloud.ai/console/api-keys
- **Docs**: https://www.atlascloud.ai/docs

## Pricing on Atlas Cloud

- $0.047 per second of generated video
- Pay-as-you-go. No minimum spend, no subscription required.

> **These are the authoritative Atlas Cloud rates for this model.** Any price that
> appears in the vendor description further down refers to a different platform or
> a different model variant and does not apply here.

## Use this model from an AI agent

Atlas Cloud ships three first-party integration surfaces. All three authenticate
with the same API key via the `ATLASCLOUD_API_KEY` environment variable.

### MCP server

The official MCP server (`atlascloud-mcp`) exposes this model to any
MCP-compatible host — Claude Code, OpenAI Codex, Cursor, Gemini CLI, Goose,
Claude Desktop. One-line install:

```bash
# Claude Code
claude mcp add atlascloud -- npx -y atlascloud-mcp

# OpenAI Codex CLI
codex mcp add atlascloud -- npx -y atlascloud-mcp

# Gemini CLI
gemini mcp add atlascloud -- npx -y atlascloud-mcp

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

Then ask in plain English; the agent calls `atlas_generate_video` with `model: "bytedance/seedance-v1-pro-i2v-720p"`.
The server fetches each model's schema and validates parameters before submitting,
so invalid requests fail fast without spending credits.

MCP docs: https://www.atlascloud.ai/docs/mcp-server

### Agent Skills

`atlas-cloud-skills` is a portable skill package (API reference, code templates in
Python / Node.js / cURL, model IDs with pricing) for Claude Code, Cursor, Codex and
12+ other agents:

```bash
npx skills add AtlasCloudAI/atlas-cloud-skills
export ATLASCLOUD_API_KEY="your-api-key"
```

Skills docs: https://www.atlascloud.ai/docs/skills

### CLI

The `atlas` binary runs Atlas Cloud from a terminal or CI script. Async media jobs
are polled and downloaded automatically (use `--no-download` when a script only
needs the output URLs):

```bash
# Install (Homebrew, npm, or shell installer)
brew install AtlasCloudAI/tap/atlascloud
# npm install -g atlascloud-cli
# curl -fsSL https://raw.githubusercontent.com/AtlasCloudAI/cli/main/install.sh | sh

atlas auth login
atlas generate video bytedance/seedance-v1-pro-i2v-720p -p "Your prompt here"
```

CLI docs: https://www.atlascloud.ai/docs/cli

## HTTP API reference

- **Submit endpoint (POST)**: `https://api.atlascloud.ai/api/v1/model/generateVideo` — start an async generation; returns a `prediction_id`
- **Poll endpoint (GET)**: `https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}` — poll this until the prediction finishes
- **Model ID**: `bytedance/seedance-v1-pro-i2v-720p`


## API Information

This model can be used via our HTTP API or more conveniently via our client libraries.
See the input and output schema below, as well as the usage examples.


### Input Schema

The API accepts the following input parameters:

- **`model`** (`string`, _required_):
  model name
  - Default: `"bytedance/seedance-v1-pro-i2v-720p"`

- **`prompt`** (`string`, _optional_):
  Text prompt for video generation; Positive text prompt; Cannot exceed 2000 characters
  - Default: `"Girl playing piano, multiple camera switches, cinematic quality"`

- **`image`** (`string`, _required_):
  Input image for video generation; Supported image formats include .jpg/.jpeg/.png; The image file size cannot exceed 10MB, and the image resolution should not be less than 300*300px
  - Default: `"https://static.atlascloud.ai/media/images/1750742499545258689_aeXmGbsM.jpg"`

- **`last_image`** (`string`, _optional_):
  End image (last frame); supports both URL and Base64 format; Supported image formats include .jpg/.jpeg/.png; The image file size cannot exceed 10MB, and the image resolution should not be less than 300*300px

- **`duration`** (`integer`, _required_):
  Generate video duration length seconds.
  - Default: `5`
  - Min: 2
  - Max: 12

- **`aspect_ratio`** (`string`, _optional_):
  The aspect ratio of the generated media.
  - Options: "21:9", "16:9", "4:3", "1:1", "3:4", "9:16"

- **`seed`** (`integer`, _optional_):
  The seed for random number generation.
  - Default: `-1`



**Required Parameters Example**:

```json
{
  "model": "bytedance/seedance-v1-pro-i2v-720p",
  "image": "https://static.atlascloud.ai/media/images/1750742499545258689_aeXmGbsM.jpg",
  "duration": 5
}
```


**Full Example**:

```json
{
  "model": "bytedance/seedance-v1-pro-i2v-720p",
  "prompt": "Girl playing piano, multiple camera switches, cinematic quality",
  "image": "https://static.atlascloud.ai/media/images/1750742499545258689_aeXmGbsM.jpg",
  "last_image": "",
  "duration": 5,
  "aspect_ratio": "21:9",
  "seed": -1
}
```


### Output Schema

The API returns the following output format:


- **`id`** (`string`, _optional_):
  Unique prediction ID

- **`logs`** (`string`, _optional_):
  Execution logs

- **`urls`** (`string`, _optional_):

- **`input`** (`string`, _optional_):

- **`model`** (`string`, _optional_):
  Model name

- **`output`** (`array[string]`, _optional_):
  Generated output URLs

- **`status`** (`string`, _optional_):
  Prediction status
  - Options: "queued", "processing", "succeeded", "failed"

- **`created_at`** (`string`, _optional_):
  Creation timestamp

- **`has_nsfw_contents`** (`array[boolean]`, _optional_):
  NSFW content detection results



**Example Response**:

```json
{
  "id": "",
  "logs": "",
  "urls": null,
  "input": null,
  "model": "",
  "output": [
    ""
  ],
  "status": "queued",
  "created_at": "",
  "has_nsfw_contents": []
}
```


## Usage Examples

### cURL

```bash
# Step 1: Start generation (async)
curl -X POST "https://api.atlascloud.ai/api/v1/model/generateVideo" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "bytedance/seedance-v1-pro-i2v-720p",
  "prompt": "Girl playing piano, multiple camera switches, cinematic quality",
  "image": "https://static.atlascloud.ai/media/images/1750742499545258689_aeXmGbsM.jpg",
  "last_image": "",
  "duration": 5,
  "aspect_ratio": "21:9",
  "seed": -1
}'

# Response will contain: {"code": 200, "data": {"id": "prediction_id", "status": "processing"}}

# Step 2: Poll for result (replace {prediction_id} with the id returned above)
curl -X GET "https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY"

# Keep polling until status is "completed", "succeeded" or "failed"
# When completed, outputs will contain the generated content URL(s)
```

## Additional Resources

### Documentation

- [Model Playground](https://www.atlascloud.ai/models/bytedance/seedance-v1-pro-i2v-720p)

## About this model

_Vendor-supplied description. Any pricing or endpoint mentioned below refers to_
_other platforms — use the Atlas Cloud values above._

### ByteDance Seedance Pro I2V 720p*

**ByteDance Seedance Pro I2V 720p** is a revolutionary AI image-to-video generation model developed by ByteDance, now exclusively available on WaveSpeedAI as a global premiere launch. This cutting-edge model transforms static images into dynamic 5-second videos at 720p resolution with lightning-fast processing speed, offering high-quality visual outputs with enhanced motion and semantic understanding. Part of the Dreamina model family, this SOTA-level model delivers unprecedented performance in image-to-video synthesis.

#### Key Features

*   **Ultra-Fast Video Generation**: Lightning-speed processing creates 5-second videos at 720p resolution with vivid details and smooth motion in seconds, not minutes.
*   **SOTA Motion Rendering**: State-of-the-art dynamic rendering techniques create natural and realistic movements that bring images to life.
*   **Advanced Semantic Understanding**: Industry-leading AI excels in interpreting complex user prompts to generate coherent and dynamic scenes with professional quality.
*   **Realistic Physical Simulation**: SOTA physics engine simulates realistic physical properties and movements for lifelike video generation.
*   **Blazing-Fast Processing**: Optimized for maximum speed efficiency, allowing instant creation of high-quality videos for real-time workflows.
*   **Flexible Parameter Control**: Customizable settings offer duration and style adjustments for complete creative control.
*   **Professional Quality Output**: SOTA image-to-video technology ensures broadcast-ready results with smooth temporal consistency.
*   **Instant Creative Enhancement**: Transform ordinary photos into engaging, dynamic content perfect for social media marketing in seconds.

#### Global Premiere on WaveSpeedAI

_(Description truncated. Full text on the model page.)_

---

Atlas Cloud — one API for 400+ AI models. Model page: https://www.atlascloud.ai/models/bytedance/seedance-v1-pro-i2v-720p · Docs: https://www.atlascloud.ai/docs