minimax/h3-developer/reference-to-video

image-to-video

DEV

MiniMax H3 Developer Reference-to-Video API by MiniMax

minimax/h3-developer/reference-to-video

Reference-to-video

MiniMax H3-Developer self-hosted reference-to-video: generate a video that keeps the subject from one or more reference images/videos, driven by a text prompt, with generated audio. Supports 480P768P/2K.

MiniMax H3 Developer Reference-to-Video is developed by MiniMax. Atlas Cloud (operated by Atlas Cloud AI LLC) provides access to it and does not own it. All trademarks belong to their respective owners.

INPUT

Prompt *

Reference Materials *(0/9)

You can drag and drop a file or click to upload

MAX:9

Resolution *

Duration *

Aspect Ratio

Prompt expansion

OUTPUT

Idle

Your generated videos will appear here

Configure your settings and click Run to get started

Your request will cost $0.015 per run. For $10 you can run this model approximately 666 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": "minimax/h3-developer/reference-to-video",  # Required. model name
    "prompt": "A beautiful sunset over the ocean with gentle waves",  # Required. The text prompt describing the video to generate
    "refers": [
        {
            "url": "example_url",
            "type": "example_type"
        }
    ],  # Required. Reference materials that anchor the generation
    "resolution": "768P",  # Required. The resolution of the generated video. options: 480P | 768P | 1440p-sr | 4k-sr
    "duration": 8,  # Required. The duration of the generated video in seconds
    "ratio": "adaptive",  # The aspect ratio of the generated video
    "prompt_expansion": False,  # Whether to expand the prompt for better results
}

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.

pip install requests

Authentication

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

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

HTTP Headers

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": "minimax/h3-developer/reference-to-video",
    "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['data']['id']}")
print(f"Status: {result['data']['status']}")

Response

{
  "code": 200,
  "data": {
    "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: 7Required: 5Optional: 2

modelstringrequired

model name

Default: "minimax/h3-developer/reference-to-video"

promptstringrequired

The text prompt describing the video to generate.

refersarray[object]required

Reference materials that anchor the generation. Any mix of reference images, videos, and audio, each as a public URL. At least one image OR video is required (audio alone is not allowed). Image formats: png, jpeg, jpg, webp; video: mp4, mov; audio: mp3, wav. 'type' is optional — when omitted it is inferred from the URL extension.

Min items: 1

urlstringrequired

Public URL of the reference image / video / audio.

typestring

Media kind. Optional; inferred from the URL when omitted.

imagevideoaudio

resolutionstringrequired

The resolution of the generated video.

Default: "768P"

480P768P1440p-sr4k-sr

durationnumberrequired

The duration of the generated video in seconds.

Default: 8

456789101112131415

ratiostring

The aspect ratio of the generated video. Use 'adaptive' to let the model choose.

Default: "adaptive"

adaptive21:916:94:31:13:49:16

prompt_expansionboolean

Whether to expand the prompt for better results.

Default: false

Example Request Body

{
  "model": "minimax/h3-developer/reference-to-video",
  "prompt": "A beautiful landscape",
  "refers": [
    {
      "url": "example_url",
      "type": "example_type"
    }
  ],
  "resolution": "768P",
  "duration": 8,
  "ratio": "adaptive",
  "prompt_expansion": false
}

Output Schema

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

created_atstring

ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”).

idstring

Unique identifier for the prediction, the ID of the prediction to get.

modelstring

Model ID used for the prediction.

outputsarray

Array of URLs to the generated content (empty when status is not completed).

statusstring

Status of the task: created, processing, completed, or failed.

Example Response

{
  "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 400+ 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

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.

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 400+ 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

npx -y atlascloud-mcp

Configuration

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

{
  "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 400+ 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

{
  "components": {
    "schemas": {
      "Input": {
        "properties": {
          "model": {
            "type": "string",
            "description": "model name",
            "default": "minimax/h3-developer/reference-to-video"
          },
          "prompt": {
            "description": "The text prompt describing the video to generate.",
            "type": "string"
          },
          "refers": {
            "description": "Reference materials that anchor the generation. Any mix of reference images, videos, and audio, each as a public URL. At least one image OR video is required (audio alone is not allowed). Image formats: png, jpeg, jpg, webp; video: mp4, mov; audio: mp3, wav. 'type' is optional — when omitted it is inferred from the URL extension.",
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "url": {
                  "type": "string",
                  "description": "Public URL of the reference image / video / audio.",
                  "x-ui-component": "uploaders"
                },
                "type": {
                  "type": "string",
                  "description": "Media kind. Optional; inferred from the URL when omitted.",
                  "enum": [
                    "image",
                    "video",
                    "audio"
                  ]
                }
              },
              "required": [
                "url"
              ]
            },
            "minItems": 1,
            "x-ui-component": "uploaders"
          },
          "resolution": {
            "default": "768P",
            "description": "The resolution of the generated video.",
            "enum": [
              "480P",
              "768P",
              "1440p-sr",
              "4k-sr"
            ],
            "type": "string",
            "x-ui-component": "select"
          },
          "duration": {
            "default": 8,
            "description": "The duration of the generated video in seconds.",
            "enum": [
              4,
              5,
              6,
              7,
              8,
              9,
              10,
              11,
              12,
              13,
              14,
              15
            ],
            "type": "number",
            "x-ui-component": "select"
          },
          "ratio": {
            "default": "adaptive",
            "description": "The aspect ratio of the generated video. Use 'adaptive' to let the model choose.",
            "enum": [
              "adaptive",
              "21:9",
              "16:9",
              "4:3",
              "1:1",
              "3:4",
              "9:16"
            ],
            "type": "string",
            "x-ui-component": "select"
          },
          "prompt_expansion": {
            "default": false,
            "description": "Whether to expand the prompt for better results.",
            "type": "boolean",
            "x-ui-component": "switch"
          }
        },
        "required": [
          "model",
          "prompt",
          "resolution",
          "duration",
          "refers"
        ],
        "type": "object",
        "x-order-properties": [
          "model",
          "prompt",
          "refers",
          "resolution",
          "duration",
          "ratio",
          "prompt_expansion"
        ]
      },
      "PredictionResponse": {
        "properties": {
          "created_at": {
            "description": "ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”).",
            "format": "date-time",
            "type": "string"
          },
          "id": {
            "description": "Unique identifier for the prediction, the ID of the prediction to get.",
            "type": "string"
          },
          "model": {
            "description": "Model ID used for the prediction.",
            "type": "string"
          },
          "outputs": {
            "description": "Array of URLs to the generated content (empty when status is not completed).",
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "status": {
            "description": "Status of the task: created, processing, completed, or failed.",
            "type": "string"
          },
          "urls": {
            "description": "Object containing related API endpoints.",
            "type": "object"
          }
        },
        "type": "object"
      }
    },
    "securitySchemes": {
      "apiKeyAuth": {
        "in": "header",
        "name": "Authorization",
        "type": "apiKey"
      }
    }
  },
  "info": {
    "description": "The AtlasCloud API.",
    "title": "AtlasCloud API",
    "version": "1.0.0"
  },
  "openapi": "3.0.0",
  "paths": {
    "/api/v1/model/prediction/{request_id}": {
      "get": {
        "parameters": [
          {
            "in": "path",
            "name": "request_id",
            "required": true,
            "schema": {
              "description": "Request ID",
              "type": "string"
            }
          }
        ],
        "responses": {
          "200": {
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/PredictionResponse"
                }
              }
            },
            "description": "Result of the request."
          }
        }
      },
      "x-api-name": "model_result"
    },
    "/api/v1/model/generateVideo": {
      "post": {
        "requestBody": {
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/Input"
              }
            }
          },
          "required": true
        },
        "responses": {
          "200": {
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/PredictionResponse"
                }
              }
            },
            "description": "The request status."
          }
        }
      },
      "x-api-name": "model_run"
    }
  },
  "servers": [
    {
      "url": "https://api.atlascloud.ai"
    }
  ]
}

LLM-Friendly Prompt Template

# minimax/h3-developer/reference-to-video

> MiniMax H3-Developer self-hosted reference-to-video: generate a video that keeps the subject from one or more reference images/videos, driven by a text prompt, with generated audio. Supports 480P768P/2K.


## Overview

- **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**: `minimax/h3-developer/reference-to-video`


## 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: `"minimax/h3-developer/reference-to-video"`

- **`prompt`** (`string`, _required_):
  The text prompt describing the video to generate.

- **`refers`** (`array[object]`, _required_):
  Reference materials that anchor the generation. Any mix of reference images, videos, and audio, each as a public URL. At least one image OR video is required (audio alone is not allowed). Image formats: png, jpeg, jpg, webp; video: mp4, mov; audio: mp3, wav. 'type' is optional — when omitted it is inferred from the URL extension.
  - Min items: 1
  - Item properties:
    - **`url`** (`string`, _required_):
      Public URL of the reference image / video / audio.

    - **`type`** (`string`, _optional_):
      Media kind. Optional; inferred from the URL when omitted.
      - Options: "image", "video", "audio"


- **`resolution`** (`string`, _required_):
  The resolution of the generated video.
  - Default: `"768P"`
  - Options: "480P", "768P", "1440p-sr", "4k-sr"

- **`duration`** (`number`, _required_):
  The duration of the generated video in seconds.
  - Default: `8`
  - Options: 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15

- **`ratio`** (`string`, _optional_):
  The aspect ratio of the generated video. Use 'adaptive' to let the model choose.
  - Default: `"adaptive"`
  - Options: "adaptive", "21:9", "16:9", "4:3", "1:1", "3:4", "9:16"

- **`prompt_expansion`** (`boolean`, _optional_):
  Whether to expand the prompt for better results.
  - Default: `false`



**Required Parameters Example**:

```json
{
  "model": "minimax/h3-developer/reference-to-video",
  "prompt": "",
  "resolution": "768P",
  "duration": 8,
  "refers": [
    {
      "url": "",
      "type": "image"
    }
  ]
}
```


**Full Example**:

```json
{
  "model": "minimax/h3-developer/reference-to-video",
  "prompt": "",
  "refers": [
    {
      "url": "",
      "type": "image"
    }
  ],
  "resolution": "768P",
  "duration": 8,
  "ratio": "adaptive",
  "prompt_expansion": false
}
```


### Output Schema

The API returns the following output format:


- **`created_at`** (`string`, _optional_):
  ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”).

- **`id`** (`string`, _optional_):
  Unique identifier for the prediction, the ID of the prediction to get.

- **`model`** (`string`, _optional_):
  Model ID used for the prediction.

- **`outputs`** (`array[string]`, _optional_):
  Array of URLs to the generated content (empty when status is not completed).

- **`status`** (`string`, _optional_):
  Status of the task: created, processing, completed, or failed.

- **`urls`** (`object`, _optional_):
  Object containing related API endpoints.



**Example Response**:

```json
{
  "created_at": "",
  "id": "",
  "model": "",
  "outputs": [
    ""
  ],
  "status": "",
  "urls": {}
}
```


## 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": "minimax/h3-developer/reference-to-video",
  "prompt": "",
  "refers": [
    {
      "url": "",
      "type": "image"
    }
  ],
  "resolution": "768P",
  "duration": 8,
  "ratio": "adaptive",
  "prompt_expansion": false
}'

# 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/minimax/h3-developer/reference-to-video)

The race car driver raises a hand in celebration of the victory.

MiniMax H3-Developer Reference-to-Video

MiniMax H3-Developer Reference-to-Video keeps a subject consistent — with sound. Provide one or more reference materials (images and/or videos of a person, animal, or object) plus a prompt. Generate native 480P or 768P video, or select an ESR tier to enhance the output to a 1080P, 1440P, or 4K short edge while preserving the referenced subject's identity, complete with a synchronized soundtrack generated from the described scene.

Why Choose This?

Subject-consistent generation Keep the referenced subject's identity across the whole shot.
Multi-modal references Drive generation with images and/or videos in a single request.
Native audio A matching soundtrack is generated alongside the video — no separate audio input needed.
Enhanced resolution output Generate native 480P or 768P video, or use ESR for a 1080P, 1440P, or 4K short edge.
Selectable duration Produce 5–15s clips.

Parameters

Parameter	Required	Description
prompt	No	Text description of the desired video while keeping the referenced subject's identity
refers	Yes	Array of reference materials. Each item is an object `{ "url": string, "type": "image" \| "video" \| "audio" }`. `type` is inferred from the URL extension when omitted. At least one image or video is required; audio alone is rejected
resolution	No	Video resolution. Available options: `768P` (default), `480P`, `1080p-esr`, `1440p-esr`, `4k-esr`. ESR tiers generate a native 768P source and enhance the output to the requested short edge.
duration	No	Duration of the generated video in seconds. Integer between 5 and 15 (default 5)
prompt_expansion	No	Enable AI prompt expansion via H3 Context-IR. When `true`, your prompt is first expanded into a rich, structured description (shot, soundscape, music) before generation, and an additional per-token Context-IR fee applies. Default `false`: the prompt is used as-is with no extra charge.

How to Use

Add your reference materials — pass one or more refers entries (image and/or video URLs).
Write your prompt — describe the desired scene, action, and sound while keeping the subject.
Set resolution and duration — balance quality against generation speed.
(Optional) Tune seed and steps — fix the seed for reproducibility, raise steps for quality.
Run — submit and download your video.

Best Use Cases

Character Consistency — Keep the same character across multiple shots.
Product Showcases — Feature a specific product while varying the scene.
Brand & IP — Reuse a mascot or signature subject in new content.
Storytelling — Build a narrative around a consistent subject, with matching sound.

Pro Tips

Use clear, high-quality reference images or videos of the subject.
Provide at least one image or video reference; audio-only requests are rejected.
Describe the scene's audio (traffic, music, crowd) to shape the generated soundtrack.
Keep the prompt focused on the scene and action; the subject's identity comes from the references.

Notes

At least one image or video reference is required.
The prompt is optional but strongly recommended.
ESR tiers add an enhancement stage after native generation and may take longer than native resolutions.
Ensure all reference URLs are publicly accessible.
Generation is asynchronous — submit, then poll for the finished video.