kwaivgi/kling-video-o3-pro/reference-to-video

gambar-ke-video

PRO

Kling Video O3 Pro Reference-to-Video API by Kuaishou

kwaivgi/kling-video-o3-pro/reference-to-video

Reference-to-video

Kling Omni Video O3 Reference-to-Video generates creative videos using character, prop, or scene references. Professional quality with up to 7 reference images and optional video input.

INPUT

Prompt

Ketik @ untuk merujuk subjek.

Video

Anda dapat drag & drop file atau klik untuk mengunggah

MAX:1

Gambar(0/7)

Anda dapat drag & drop file atau klik untuk mengunggah

MAX:7

Multi-Shot

Subjek

MAKS: 6

Pengaturan Tambahan

OUTPUT

Menunggu

Video yang dihasilkan akan muncul di sini

Konfigurasikan pengaturan Anda dan klik Jalankan untuk memulai

Permintaan Anda akan dikenakan biaya $0.095 per eksekusi. Dengan $10 Anda dapat menjalankan model ini sekitar 105 kali.

Berikut yang dapat Anda lakukan selanjutnya:

Seedance 2.0 Kling v3 Vidu Wan2.7

Parameter

Contoh kode
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": "kwaivgi/kling-video-o3-pro/reference-to-video",  # Required. model name. default: "kwaivgi/kling-video-o3-pro/reference-to-video-test"
    "aspect_ratio": "16:9",  # The aspect ratio of the generated video. options: 16:9 | 9:16 | 1:1
    "duration": 5,  # The duration of the generated media in seconds (3-15)
    "images": [
        "https://example.com/image1.jpg"
    ],  # Reference images
    "keep_original_sound": True,  # Whether to keep the original sound from the reference video
    "prompt": "A beautiful sunset over the ocean with gentle waves",  # The positive prompt for the generation
    "sound": False,  # Whether to generate audio for the video
    "video": "example_value",  # The reference video URL
    "multi_shot": False,  # Whether to enable multi-shot generation
    "shot_type": "example_value",  # Multi-shot mode. options: customize | intelligence
    "multi_prompt": [
        {
            "prompt": "example_prompt",
            "duration": 1
        }
    ],  # Per-shot storyboards
    "elements": [
        {
            "reference_type": "image_refer",
            "frontal_image": "example_frontal_image",
            "refer_images": [
                "https://example.com/image1.jpg"
            ],
            "refer_videos": [
                "https://example.com/image1.jpg"
            ],
            "element_name": "example_element_name",
            "element_description": "example_element_description",
            "element_id": 0
        }
    ],  # Subject references (Atlas naming; maps to Kling 'element_list')
}

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()

Instalasi

Instal paket dependensi yang diperlukan.

pip install requests

Autentikasi

Semua permintaan API memerlukan autentikasi melalui API key. Anda bisa mendapatkan API key dari dasbor Atlas Cloud.

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}"
}

Jaga keamanan API key Anda

Jangan pernah mengekspos API key Anda di kode sisi klien atau repositori publik. Gunakan variabel lingkungan atau proxy backend sebagai gantinya.

Kirim permintaan

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())

Kirim Permintaan

Kirim permintaan pembuatan asinkron. API mengembalikan prediction ID yang dapat Anda gunakan untuk memeriksa status dan mengambil hasil.

POST/api/v1/model/generateVideo

Isi Permintaan

import requests

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

data = {
    "model": "kwaivgi/kling-video-o3-pro/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']}")

Respons

{
  "code": 200,
  "data": {
    "id": "pred_abc123",
    "status": "processing",
    "model": "model-name",
    "created_at": "2025-01-01T00:00:00Z"
  }
}

Periksa Status

Polling prediction endpoint untuk memeriksa status permintaan Anda saat ini.

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

Contoh 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)

Nilai Status

processingPermintaan masih diproses.

completedPembuatan selesai. Output tersedia.

succeededPembuatan berhasil. Output tersedia.

failedPembuatan gagal. Periksa field error.

Respons Selesai

{
  "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"
  }
}

Unggah File

Unggah file ke penyimpanan Atlas Cloud dan dapatkan URL yang dapat Anda gunakan dalam permintaan API Anda. Gunakan multipart/form-data untuk mengunggah.

POST/api/v1/model/uploadMedia

Contoh Unggah

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}")

Respons

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

Input Schema

Parameter berikut diterima di isi permintaan.

Total: 12Wajib: 1Opsional: 11

modelstringrequired

model name

Default: "kwaivgi/kling-video-o3-pro/reference-to-video-test"

aspect_ratiostring

The aspect ratio of the generated video.

Default: "16:9"

16:99:161:1

durationinteger

The duration of the generated media in seconds (3-15).

Default: 5

3456789101112131415

imagesarray[string]

Reference images. With a reference video: image elements ≤ 4; without a reference video: ≤ 7

Max items: 7

keep_original_soundboolean

Whether to keep the original sound from the reference video.

Default: true

promptstring

The positive prompt for the generation.

soundboolean

Whether to generate audio for the video.

Default: false

videostring

The reference video URL.

multi_shotboolean

Whether to enable multi-shot generation.

Default: false

shot_typestring

Multi-shot mode. customize = caller provides per-shot prompts; intelligence = model auto-splits the top-level prompt into shots. Required when multi_shot=true.

customizeintelligence

multi_promptarray[object]

Per-shot storyboards. Required when multi_shot=true and shot_type=customize. Sum of each shot's duration must equal the top-level duration; each shot duration must be >= 1.

Min items: 1Max items: 6

promptstringrequired

Prompt for this shot. Supports subject mentions like <<<element_1>>>.

durationintegerrequired

Duration of this shot in seconds (string, '1'~'15'). Sum of all shots must equal the top-level duration. Each shot duration >= 1.

Min: 1

elementsarray[object]

Subject references (Atlas naming; maps to Kling 'element_list'). Each item either references an existing subject by element_id, or creates a new one inline with element_name + reference_type + frontal_image / refer_images / refer_videos (Atlas wrapper feature — backend creates the element via Kling's element API, then injects the resulting element_id). Mention subjects in prompt with <<<element_N>>> (1-based, matches array position). For kling-v3-omni: up to 3 elements.

Max items: 6

reference_typestring

Reference media type for the new subject (Atlas wrapper).

Default: "image_refer"

image_refervideo_refer

frontal_imagestring

Frontal image URL of the new subject (required when reference_type=image_refer).

refer_imagesarray[string]

Reference image URLs of the new subject (used with reference_type=image_refer).

Max items: 4

refer_videosarray[string]

Reference video URLs of the new subject (used with reference_type=video_refer).

Max items: 4

element_namestring

Name of the new subject to create inline (Atlas wrapper). Mutually exclusive with element_id.

element_descriptionstring

Optional description of the new subject (Atlas wrapper).

element_idinteger

ID of an existing subject from the Kling element library (long / 64-bit integer). Mutually exclusive with element_name.

Contoh Isi Permintaan

{
  "model": "kwaivgi/kling-video-o3-pro/reference-to-video",
  "aspect_ratio": "16:9",
  "duration": 5,
  "keep_original_sound": true,
  "sound": false,
  "multi_shot": false
}

Output Schema

API mengembalikan respons prediction dengan URL output yang dihasilkan.

created_atstring

ISO timestamp of when the request was created.

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.

Contoh Respons

{
  "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 mengintegrasikan 400+ model AI langsung ke asisten pengkodean AI Anda. Satu perintah untuk menginstal, lalu gunakan bahasa alami untuk menghasilkan gambar, video, dan mengobrol dengan LLM.

Klien yang Didukung

Claude Code

OpenAI Codex

Gemini CLI

Cursor

Windsurf

VS Code

Trae

GitHub Copilot

Cline

Roo Code

Amp

Goose

Replit

40+ klien yang didukung

Instalasi

npx skills add AtlasCloudAI/atlas-cloud-skills

Atur API Key

Dapatkan API key dari dasbor Atlas Cloud dan atur sebagai variabel lingkungan.

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

Kemampuan

Setelah diinstal, Anda dapat menggunakan bahasa alami di asisten AI Anda untuk mengakses semua model Atlas Cloud.

Pembuatan GambarBuat gambar dengan model seperti Nano Banana 2, Z-Image, dan lainnya.

Pembuatan VideoBuat video dari teks atau gambar dengan Kling, Vidu, Veo, dll.

Obrolan LLMMengobrol dengan Qwen, DeepSeek, dan model bahasa besar lainnya.

Unggah MediaUnggah file lokal untuk pengeditan gambar dan alur kerja gambar-ke-video.

Pelajari lebih lanjut

github.com/AtlasCloudAI/atlas-cloud-skills

MCP Server

Atlas Cloud MCP Server menghubungkan IDE Anda dengan 400+ model AI melalui Model Context Protocol. Berfungsi dengan klien apa pun yang kompatibel dengan MCP.

Klien yang Didukung

Cursor

VS Code

Windsurf

Claude Code

OpenAI Codex

Gemini CLI

Cline

Roo Code

100+ klien yang didukung

Instalasi

npx -y atlascloud-mcp

Konfigurasi

Tambahkan konfigurasi berikut ke file pengaturan MCP di IDE Anda.

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

Alat yang Tersedia

atlas_generate_imageBuat gambar dari prompt teks.

atlas_generate_videoBuat video dari teks atau gambar.

atlas_chatMengobrol dengan model bahasa besar.

atlas_list_modelsJelajahi 400+ model AI yang tersedia.

atlas_quick_generatePembuatan konten satu langkah dengan pemilihan model terbaik otomatis.

atlas_upload_mediaUnggah file lokal untuk alur kerja API.

Pelajari lebih lanjut

github.com/AtlasCloudAI/mcp-server

Schema API

{
  "components": {
    "schemas": {
      "Input": {
        "properties": {
          "model": {
            "type": "string",
            "description": "model name",
            "default": "kwaivgi/kling-video-o3-pro/reference-to-video-test"
          },
          "aspect_ratio": {
            "default": "16:9",
            "description": "The aspect ratio of the generated video.",
            "enum": [
              "16:9",
              "9:16",
              "1:1"
            ],
            "type": "string"
          },
          "duration": {
            "default": 5,
            "description": "The duration of the generated media in seconds (3-15).",
            "enum": [
              3,
              4,
              5,
              6,
              7,
              8,
              9,
              10,
              11,
              12,
              13,
              14,
              15
            ],
            "type": "integer",
            "x-ui-component": "select"
          },
          "images": {
            "description": "Reference images. With a reference video: image elements ≤ 4; without a reference video: ≤ 7",
            "items": {
              "type": "string"
            },
            "maxItems": 7,
            "type": "array"
          },
          "keep_original_sound": {
            "default": true,
            "description": "Whether to keep the original sound from the reference video.",
            "type": "boolean"
          },
          "prompt": {
            "description": "The positive prompt for the generation.",
            "type": "string"
          },
          "sound": {
            "default": false,
            "description": "Whether to generate audio for the video.",
            "type": "boolean"
          },
          "video": {
            "description": "The reference video URL.",
            "type": "string",
            "x-ui-component": "uploader"
          },
          "multi_shot": {
            "type": "boolean",
            "description": "Whether to enable multi-shot generation.",
            "default": false
          },
          "shot_type": {
            "type": "string",
            "description": "Multi-shot mode. customize = caller provides per-shot prompts; intelligence = model auto-splits the top-level prompt into shots. Required when multi_shot=true.",
            "enum": [
              "customize",
              "intelligence"
            ],
            "x-ui-component": "select"
          },
          "multi_prompt": {
            "type": "array",
            "description": "Per-shot storyboards. Required when multi_shot=true and shot_type=customize. Sum of each shot's duration must equal the top-level duration; each shot duration must be >= 1.",
            "minItems": 1,
            "maxItems": 6,
            "items": {
              "type": "object",
              "required": [
                "prompt",
                "duration"
              ],
              "properties": {
                "prompt": {
                  "type": "string",
                  "description": "Prompt for this shot. Supports subject mentions like <<<element_1>>>.",
                  "maxLength": 512
                },
                "duration": {
                  "type": "integer",
                  "description": "Duration of this shot in seconds (string, '1'~'15'). Sum of all shots must equal the top-level duration. Each shot duration >= 1.",
                  "minimum": 1
                }
              }
            }
          },
          "elements": {
            "type": "array",
            "description": "Subject references (Atlas naming; maps to Kling 'element_list'). Each item either references an existing subject by element_id, or creates a new one inline with element_name + reference_type + frontal_image / refer_images / refer_videos (Atlas wrapper feature — backend creates the element via Kling's element API, then injects the resulting element_id). Mention subjects in prompt with <<<element_N>>> (1-based, matches array position). For kling-v3-omni: up to 3 elements.",
            "maxItems": 6,
            "items": {
              "type": "object",
              "properties": {
                "reference_type": {
                  "type": "string",
                  "description": "Reference media type for the new subject (Atlas wrapper).",
                  "enum": [
                    "image_refer",
                    "video_refer"
                  ],
                  "default": "image_refer"
                },
                "frontal_image": {
                  "type": "string",
                  "description": "Frontal image URL of the new subject (required when reference_type=image_refer)."
                },
                "refer_images": {
                  "type": "array",
                  "description": "Reference image URLs of the new subject (used with reference_type=image_refer).",
                  "items": {
                    "type": "string"
                  },
                  "maxItems": 4
                },
                "refer_videos": {
                  "type": "array",
                  "description": "Reference video URLs of the new subject (used with reference_type=video_refer).",
                  "items": {
                    "type": "string"
                  },
                  "maxItems": 4
                },
                "element_name": {
                  "type": "string",
                  "description": "Name of the new subject to create inline (Atlas wrapper). Mutually exclusive with element_id."
                },
                "element_description": {
                  "type": "string",
                  "description": "Optional description of the new subject (Atlas wrapper).",
                  "x-hidden": true
                },
                "element_id": {
                  "type": "integer",
                  "description": "ID of an existing subject from the Kling element library (long / 64-bit integer). Mutually exclusive with element_name.",
                  "x-hidden": true
                }
              },
              "allOf": [
                {
                  "if": {
                    "properties": {
                      "reference_type": {
                        "const": "video_refer"
                      }
                    },
                    "required": [
                      "reference_type"
                    ]
                  },
                  "then": {
                    "required": [
                      "refer_videos"
                    ],
                    "properties": {
                      "frontal_image": {
                        "x-hidden": true
                      },
                      "refer_images": {
                        "x-hidden": true
                      },
                      "refer_videos": {
                        "minItems": 1
                      }
                    }
                  },
                  "else": {
                    "required": [
                      "frontal_image",
                      "refer_images"
                    ],
                    "properties": {
                      "refer_videos": {
                        "x-hidden": true
                      },
                      "refer_images": {
                        "minItems": 1
                      }
                    }
                  }
                }
              ]
            }
          }
        },
        "allOf": [
          {
            "if": {
              "properties": {
                "multi_shot": {
                  "const": true
                }
              },
              "required": [
                "multi_shot"
              ]
            },
            "then": {
              "required": [
                "shot_type"
              ]
            },
            "else": {
              "required": [
                "prompt"
              ],
              "properties": {
                "shot_type": {
                  "x-hidden": true
                },
                "multi_prompt": {
                  "x-hidden": true
                }
              }
            }
          },
          {
            "if": {
              "properties": {
                "shot_type": {
                  "const": "customize"
                }
              },
              "required": [
                "shot_type"
              ]
            },
            "then": {
              "required": [
                "multi_prompt"
              ],
              "properties": {
                "prompt": {
                  "x-hidden": true,
                  "x-hidden-hint": "Customize mode uses the per-shot prompts below. Your prompt is saved and reappears when you leave Customize mode."
                }
              }
            }
          },
          {
            "if": {
              "properties": {
                "shot_type": {
                  "const": "intelligence"
                }
              },
              "required": [
                "shot_type"
              ]
            },
            "then": {
              "required": [
                "prompt"
              ],
              "properties": {
                "multi_prompt": {
                  "x-hidden": true
                }
              }
            }
          }
        ],
        "required": [
          "model"
        ],
        "type": "object",
        "x-order-properties": [
          "model",
          "prompt",
          "video",
          "images",
          "multi_shot",
          "shot_type",
          "multi_prompt",
          "elements",
          "aspect_ratio",
          "duration",
          "keep_original_sound",
          "sound"
        ]
      },
      "PredictionResponse": {
        "properties": {
          "created_at": {
            "description": "ISO timestamp of when the request was created.",
            "format": "date-time",
            "type": "string"
          },
          "has_nsfw_contents": {
            "description": "Array of boolean values indicating NSFW detection for each output.",
            "items": {
              "type": "boolean"
            },
            "type": "array"
          },
          "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/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"
    },
    "/api/v1/model/result/{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"
    }
  },
  "servers": [
    {
      "url": "https://api.atlascloud.ai"
    }
  ],
  "model": "kwaivgi/kling-video-o3-pro/reference-to-video"
}

Template Prompt untuk LLM

# kwaivgi/kling-video-o3-pro/reference-to-video

> Kling Omni Video O3 Reference-to-Video generates creative videos using character, prop, or scene references. Professional quality with up to 7 reference images and optional video input.


## 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**: `kwaivgi/kling-video-o3-pro/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: `"kwaivgi/kling-video-o3-pro/reference-to-video-test"`

- **`prompt`** (`string`, _optional_):
  The positive prompt for the generation.

- **`video`** (`string`, _optional_):
  The reference video URL.

- **`images`** (`array[string]`, _optional_):
  Reference images. With a reference video: image elements ≤ 4; without a reference video: ≤ 7
  - Max items: 7

- **`multi_shot`** (`boolean`, _optional_):
  Whether to enable multi-shot generation.
  - Default: `false`

- **`shot_type`** (`string`, _optional_):
  Multi-shot mode. customize = caller provides per-shot prompts; intelligence = model auto-splits the top-level prompt into shots. Required when multi_shot=true.
  - Options: "customize", "intelligence"

- **`multi_prompt`** (`array[object]`, _optional_):
  Per-shot storyboards. Required when multi_shot=true and shot_type=customize. Sum of each shot's duration must equal the top-level duration; each shot duration must be >= 1.
  - Min items: 1
  - Max items: 6
  - Item properties:
    - **`prompt`** (`string`, _required_):
      Prompt for this shot. Supports subject mentions like <<<element_1>>>.

    - **`duration`** (`integer`, _required_):
      Duration of this shot in seconds (string, '1'~'15'). Sum of all shots must equal the top-level duration. Each shot duration >= 1.
      - Min: 1


- **`elements`** (`array[object]`, _optional_):
  Subject references (Atlas naming; maps to Kling 'element_list'). Each item either references an existing subject by element_id, or creates a new one inline with element_name + reference_type + frontal_image / refer_images / refer_videos (Atlas wrapper feature — backend creates the element via Kling's element API, then injects the resulting element_id). Mention subjects in prompt with <<<element_N>>> (1-based, matches array position). For kling-v3-omni: up to 3 elements.
  - Max items: 6
  - Item properties:
    - **`reference_type`** (`string`, _optional_):
      Reference media type for the new subject (Atlas wrapper).
      - Default: `"image_refer"`
      - Options: "image_refer", "video_refer"

    - **`frontal_image`** (`string`, _optional_):
      Frontal image URL of the new subject (required when reference_type=image_refer).

    - **`refer_images`** (`array[string]`, _optional_):
      Reference image URLs of the new subject (used with reference_type=image_refer).
      - Max items: 4

    - **`refer_videos`** (`array[string]`, _optional_):
      Reference video URLs of the new subject (used with reference_type=video_refer).
      - Max items: 4

    - **`element_name`** (`string`, _optional_):
      Name of the new subject to create inline (Atlas wrapper). Mutually exclusive with element_id.

    - **`element_description`** (`string`, _optional_):
      Optional description of the new subject (Atlas wrapper).

    - **`element_id`** (`integer`, _optional_):
      ID of an existing subject from the Kling element library (long / 64-bit integer). Mutually exclusive with element_name.


- **`aspect_ratio`** (`string`, _optional_):
  The aspect ratio of the generated video.
  - Default: `"16:9"`
  - Options: "16:9", "9:16", "1:1"

- **`duration`** (`integer`, _optional_):
  The duration of the generated media in seconds (3-15).
  - Default: `5`
  - Options: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15

- **`keep_original_sound`** (`boolean`, _optional_):
  Whether to keep the original sound from the reference video.
  - Default: `true`

- **`sound`** (`boolean`, _optional_):
  Whether to generate audio for the video.
  - Default: `false`



**Required Parameters Example**:

```json
{
  "model": "kwaivgi/kling-video-o3-pro/reference-to-video"
}
```


**Full Example**:

```json
{
  "model": "kwaivgi/kling-video-o3-pro/reference-to-video",
  "prompt": "",
  "video": "",
  "images": [
    ""
  ],
  "multi_shot": false,
  "shot_type": "customize",
  "multi_prompt": [
    {
      "prompt": "",
      "duration": 1
    }
  ],
  "elements": [
    {
      "reference_type": "image_refer",
      "frontal_image": "",
      "refer_images": [
        ""
      ],
      "refer_videos": [
        ""
      ],
      "element_name": "",
      "element_description": "",
      "element_id": 0
    }
  ],
  "aspect_ratio": "16:9",
  "duration": 5,
  "keep_original_sound": true,
  "sound": false
}
```


### Output Schema

The API returns the following output format:


- **`created_at`** (`string`, _optional_):
  ISO timestamp of when the request was created.

- **`has_nsfw_contents`** (`array[boolean]`, _optional_):
  Array of boolean values indicating NSFW detection for each output.

- **`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": "",
  "has_nsfw_contents": [],
  "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": "kwaivgi/kling-video-o3-pro/reference-to-video",
  "prompt": "",
  "video": "",
  "images": [
    ""
  ],
  "multi_shot": false,
  "shot_type": "customize",
  "multi_prompt": [
    {
      "prompt": "",
      "duration": 1
    }
  ],
  "elements": [
    {
      "reference_type": "image_refer",
      "frontal_image": "",
      "refer_images": [
        ""
      ],
      "refer_videos": [
        ""
      ],
      "element_name": "",
      "element_description": "",
      "element_id": 0
    }
  ],
  "aspect_ratio": "16:9",
  "duration": 5,
  "keep_original_sound": true,
  "sound": 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/kwaivgi/kling-video-o3-pro/reference-to-video)

Tidak ada contoh yang tersedia

Memuat...

Kling Video O3 Pro Reference-to-Video

Kling Video O3 Pro Reference-to-Video generates premium video from reference images with optional video guidance. Upload reference images to establish character identity and appearance, optionally provide a reference video for motion guidance, and describe the scene — the model produces top-tier cinematic video with identity consistency.

Why Choose This?

O3 Pro quality The highest visual fidelity and motion realism in the Kling family.

Multi-reference images Upload up to 7 reference images (or up to 4 with a reference video).

Video-guided generation Optional reference video for motion and scene guidance.

Keep original sound Preserve the audio from the reference video in the output.

Sound generation Optional AI-generated sound effects when no reference video is provided.

Parameters

Parameter	Required	Description
prompt	Yes	Text description of the video scene and motion
video	No	Reference video for motion guidance
images	No	Reference images: up to 4 with video, up to 7 without (click "+ Add Item")
keep_original_sound	No	Keep audio from the reference video (default: enabled)
sound	No	Generate AI audio (only when no reference video, default: disabled)
aspect_ratio	No	Output ratio: 16:9 (default), 9:16, 1:1
duration	No	Video length: 3-15 seconds (default: 5)

How to Use

Run — submit and download your video.
Set duration — choose any length from 3 to 15 seconds.
Select aspect ratio — match your target platform.
Configure audio — keep original sound from video, or enable AI sound generation.
Upload reference images — add character or scene references.
Upload reference video (optional) — provide a video for motion guidance.
Write your prompt — describe the scene, characters, and action.

Best Use Cases

Long-Form Scenes — Up to 15 seconds for extended scene development.
Storytelling — Produce narrative scenes with consistent character appearance.
Marketing & Ads — Create promotional videos featuring specific people or products.
Video Remixing — Use reference video for motion guidance with new characters.
Character Consistency — Generate videos with identity-consistent characters.

Pro Tips

Match aspect ratio to your platform: 16:9 for YouTube, 9:16 for TikTok/Reels, 1:1 for Instagram.
Use shorter durations (3-5s) for testing, longer (10-15s) for final production.
Sound generation is only available when no reference video is provided.
Enable keep_original_sound to preserve audio from your reference video.
When using a reference video, the image limit is 4; without a video, you can use up to 7.
Use multiple reference images from different angles for better identity preservation.

Notes

Ensure uploaded image and video URLs are publicly accessible.
When a reference video is provided, sound generation is replaced by keep_original_sound.
Reference images limit: up to 4 with video, up to 7 without.
Duration supports any value from 3 to 15 seconds.
Only prompt is required; other parameters are optional.

Kling V3.0 Pro Text-to-Video — Pro quality text-to-video.
Kling V3.0 Pro Image-to-Video — V3.0 Pro quality at lower cost.
Kling Video O3 Pro Image-to-Video — O3 Pro quality single image to video.

Jelajahi Model Serupa

NEW

teks-ke-video

TURBO

Kling V3.0 Turbo Text-to-Video

Kling V3.0 Turbo Text-to-Video generates dynamic cinematic videos from text prompts using MVL technology. Supports first/last frame control and audio generation.

Kling V3.0 Turbo Image-to-Video

Kling V3.0 Turbo Image-to-Video transforms static images into dynamic cinematic videos using MVL technology. Supports first/last frame control and audio generation.

Kling Video O3 4K Text-to-Video

Kling Omni Video O3 (4K) is Kuaishou advanced unified multi-modal video model with MVL (Multi-modal Visual Language) technology. Generates high-quality videos from text prompts with natural motion and audio generation support.

Kling Video O3 4K Image-to-Video

Kling Omni Video O3 (4K) Image-to-Video transforms static images into dynamic cinematic videos using MVL technology. Supports first/last frame control and audio generation.

Kling v3.0 4K Image-to-Video

Kling v3.0 4K Image-to-Video model by Kuaishou. High-quality video generation from images.

Kling v3.0 Std Image-to-Video

Kling v3.0 Standard Image-to-Video model by Kuaishou. High-quality video generation from images.

Kling v3.0 Pro Image-to-Video

Kling v3.0 Professional Image-to-Video model by Kuaishou. Premium quality video generation from images with advanced features.

Kling v3.0 Pro Text-to-Video

Kling v3.0 Professional Text-to-Video model by Kuaishou. Premium quality video generation from text prompts with advanced features.

Kling v3.0 4K Text-to-Video

Kling v3.0 4K Text-to-Video model by Kuaishou. High-quality video generation from text prompts.

Kling v3.0 Std Text-to-Video

Kling v3.0 Standard Text-to-Video model by Kuaishou. High-quality video generation from text prompts.

Kling v2.6 Pro Avatar

Kling V2 AI Avatar Pro generates high-quality AI avatar videos with clean detail, stable motion, and strong identity consistency—ideal for profiles, intros, and social content.

Kling v2.6 Std Avatar

Kling AI Avatar generates high-quality AI avatar videos for profiles, intros, and social content, delivering clean detail and cinematic motion with reliable prompt adherence.

Kling v2.6 Pro Motion Control

Kling 2.6 Pro Motion Control turns reference motion clips (dance, action, gesture) into smooth, realistic animations. Upload a character image (or source video) and a motion video; the model transfers the movement while preserving identity and temporal consistency.

Kling v2.6 Std Motion Control

Kling 2.6 Standard Motion Control transfers motion from reference videos to animate still images. Upload a character image and a motion clip (dance, action, gesture), and the model extracts the movement to generate smooth, realistic video.

Kling Video O3 Pro Video-Edit

Kling Omni Video O3 Video-Edit enables conversational video editing through natural language commands. Professional quality with object removal/replacement, background changes, and effects.

Kling Video O3 Pro Text-to-Video

Kling Omni Video O3 is Kuaishou's advanced unified multi-modal video model with MVL (Multi-modal Visual Language) technology. Professional quality with enhanced motion and detail.

From$0.112/DETIK

$0.095/DETIK

-15%

Satu API untuk semua AI multimedia.

Jelajahi semua model

Kling Video O3 Pro Reference-to-Video API by Kuaishou

INPUT

OUTPUT

Parameter

Contoh kode

Instalasi

Autentikasi

HTTP Headers

Kirim permintaan

Kirim Permintaan

Isi Permintaan

Respons

Periksa Status

Contoh Polling

Nilai Status

Respons Selesai

Unggah File

Contoh Unggah

Respons

Input Schema

Contoh Isi Permintaan

Output Schema

Contoh Respons

Atlas Cloud Skills

Klien yang Didukung

Instalasi

Atur API Key

Kemampuan

MCP Server

Klien yang Didukung

Instalasi

Konfigurasi

Alat yang Tersedia

Schema API

Template Prompt untuk LLM

Kling Video O3 Pro Reference-to-Video

Why Choose This?

Parameters

How to Use

Best Use Cases

Pro Tips

Notes

Related Models

Jelajahi Model Serupa

Kling V3.0 Turbo Text-to-Video

Kling V3.0 Turbo Image-to-Video

Kling Video O3 4K Text-to-Video

Kling Video O3 4K Image-to-Video

Kling v3.0 4K Image-to-Video

Kling v3.0 Std Image-to-Video

Kling v3.0 Pro Image-to-Video

Kling v3.0 Pro Text-to-Video

Kling v3.0 4K Text-to-Video

Kling v3.0 Std Text-to-Video

Kling v2.6 Pro Avatar

Kling v2.6 Std Avatar

Kling v2.6 Pro Motion Control

Kling v2.6 Std Motion Control

Kling Video O3 Pro Video-Edit

Kling Video O3 Pro Text-to-Video

Satu API untuk semua AI multimedia.

Join our Discord community

INPUT

OUTPUT

Parameter

Contoh kode

Instalasi

Autentikasi

HTTP Headers

Kirim permintaan

Kirim Permintaan

Isi Permintaan

Respons

Periksa Status

Contoh Polling

Nilai Status

Respons Selesai

Unggah File

Contoh Unggah

Respons