google/veo3.1-lite/image-to-video

Imagem para Vídeo

Veo 3.1 Lite Image-to-Video API by Google

google/veo3.1-lite/image-to-video

Image-to-video

High-efficiency Veo 3.1 Lite image-to-video: animate an input image into video with synchronized audio. Cost-effective for scalable workflows; supports 720p/1080p and common aspect ratios. Does not support 4K outputs or Extension.

Entrada

Prompt *

Imagem *

Arraste arquivos aqui ou clique para fazer upload

MAX:1

Proporção

Duração

Resolução

Semente

Saída

Inativo

Os vídeos gerados serão exibidos aqui

Configure os parâmetros e clique em executar para começar a gerar

Cada execução custará $0.05. Com $10 você pode executar aproximadamente 200 vezes.

Você pode continuar com:

Seedance 2.0 Kling v3 Vidu Wan2.7

Parâmetros

Exemplo de código
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": "google/veo3.1-lite/image-to-video",  # Required. model name
    "prompt": "A beautiful sunset over the ocean with gentle waves",  # Required. Text description for the video
    "image": "example_value",  # Required. Initial image to animate (instance image)
    "aspect_ratio": "16:9",  # The aspect ratio of the generated video. options: 16:9 | 9:16
    "duration": 8,  # Length of the generated video in seconds (durationSeconds). options: 4 | 6 | 8
    "resolution": "720p",  # Output resolution. options: 720p | 1080p
    "seed": -1,  # Random seed
}

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()

Instalar

Instale o pacote necessário para a sua linguagem de programação.

pip install requests

Autenticação

Todas as solicitações de API requerem autenticação por meio de uma chave de API. Você pode obter sua chave de API no painel do Atlas Cloud.

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

Cabeçalhos HTTP

import os

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

Mantenha sua chave de API segura

Nunca exponha sua chave de API em código do lado do cliente ou repositórios públicos. Use variáveis de ambiente ou um proxy de backend.

Enviar uma solicitação

import requests

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

Enviar uma solicitação

Envie uma solicitação de geração assíncrona. A API retorna um ID de predição que você pode usar para verificar o status e obter o resultado.

POST/api/v1/model/generateVideo

Corpo da solicitação

import requests

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

data = {
    "model": "google/veo3.1-lite/image-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']}")

Resposta

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

Verificar status

Consulte o endpoint de predição para verificar o status atual da sua solicitação.

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

Exemplo de polling

import requests
import time

prediction_id = "pred_abc123"
url = f"https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}"
headers = { "Authorization": "Bearer $ATLASCLOUD_API_KEY" }

while True:
    response = requests.get(url, headers=headers)
    result = response.json()
    status = result["data"]["status"]
    print(f"Status: {status}")

    if status in ["completed", "succeeded"]:
        output_url = result["data"]["outputs"][0]
        print(f"Output URL: {output_url}")
        break
    elif status == "failed":
        print(f"Error: {result['data'].get('error', 'Unknown')}")
        break

    time.sleep(3)

Valores de status

processingA solicitação ainda está sendo processada.

completedA geração está completa. As saídas estão disponíveis.

succeededA geração foi bem-sucedida. As saídas estão disponíveis.

failedA geração falhou. Verifique o campo de erro.

Resposta concluída

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

Enviar arquivos

Envie arquivos para o armazenamento do Atlas Cloud e obtenha uma URL que pode ser usada nas suas solicitações de API. Use multipart/form-data para enviar.

POST/api/v1/model/uploadMedia

Exemplo de upload

import requests

url = "https://api.atlascloud.ai/api/v1/model/uploadMedia"
headers = { "Authorization": "Bearer $ATLASCLOUD_API_KEY" }

with open("image.png", "rb") as f:
    files = {"file": ("image.png", f, "image/png")}
    response = requests.post(url, headers=headers, files=files)

result = response.json()
download_url = result["data"]["download_url"]
print(f"File URL: {download_url}")

Resposta

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

Schema de entrada

Os seguintes parâmetros são aceitos no corpo da solicitação.

Total: 7Obrigatório: 3Opcional: 4

modelstringrequired

model name

Default: "google/veo3.1-lite/image-to-video"

promptstringrequired

Text description for the video. Supports audio cues per Veo prompt guidance.

imagestringrequired

Initial image to animate (instance image). Accepts a public image URL, a data URL, or raw base64-encoded image bytes (e.g. PNG/JPEG inline data). Input image up to 8MB per Veo 3.1 Lite limits.

aspect_ratiostring

The aspect ratio of the generated video.

Default: "16:9"

16:99:16

durationinteger

Length of the generated video in seconds (durationSeconds). Must be 8 when using 1080p resolution.

Default: 8

468

resolutionstring

Output resolution. 1080p only supports 8s duration. Veo 3.1 Lite does not support 4K.

Default: "720p"

720p1080p

seedinteger

Random seed. Does not guarantee determinism but may improve repeatability. -1 means a random seed will be used.

Default: -1

Exemplo de corpo da solicitação

{
  "model": "google/veo3.1-lite/image-to-video",
  "prompt": "A beautiful landscape",
  "image": "example_image",
  "aspect_ratio": "16:9",
  "duration": 8,
  "resolution": "720p",
  "seed": -1
}

Schema de saída

A API retorna uma resposta de predição com as URLs de saída geradas.

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.

Exemplo de resposta

{
  "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

O Atlas Cloud Skills integra mais de 400 modelos de IA diretamente no seu assistente de codificação com IA. Um comando para instalar e depois use linguagem natural para gerar imagens, vídeos e conversar com LLM.

Clientes compatíveis

Claude Code

OpenAI Codex

Gemini CLI

Cursor

Windsurf

VS Code

Trae

GitHub Copilot

Cline

Roo Code

Amp

Goose

Replit

40+ clientes compatíveis

Instalar

npx skills add AtlasCloudAI/atlas-cloud-skills

Configurar chave de API

Obtenha sua chave de API no painel do Atlas Cloud e defina-a como variável de ambiente.

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

Funcionalidades

Após a instalação, você pode usar linguagem natural no seu assistente de IA para acessar todos os modelos do Atlas Cloud.

Geração de imagensGere imagens com modelos como Nano Banana 2, Z-Image e mais.

Criação de vídeosCrie vídeos a partir de texto ou imagens com Kling, Vidu, Veo, etc.

Chat com LLMConverse com Qwen, DeepSeek e outros grandes modelos de linguagem.

Upload de mídiaEnvie arquivos locais para fluxos de trabalho de edição de imagens e imagem para vídeo.

Saiba mais

github.com/AtlasCloudAI/atlas-cloud-skills

MCP Server

O Atlas Cloud MCP Server conecta seu IDE com mais de 400 modelos de IA através do Model Context Protocol. Funciona com qualquer cliente compatível com MCP.

Clientes compatíveis

Cursor

VS Code

Windsurf

Claude Code

OpenAI Codex

Gemini CLI

Cline

Roo Code

100+ clientes compatíveis

Instalar

npx -y atlascloud-mcp

Configuração

Adicione a seguinte configuração ao arquivo de configuração de MCP do seu IDE.

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

Ferramentas disponíveis

atlas_generate_imageGere imagens a partir de prompts de texto.

atlas_generate_videoCrie vídeos a partir de texto ou imagens.

atlas_chatConverse com grandes modelos de linguagem.

atlas_list_modelsExplore mais de 400 modelos de IA disponíveis.

atlas_quick_generateCriação de conteúdo em uma etapa com seleção automática de modelo.

atlas_upload_mediaEnvie arquivos locais para fluxos de trabalho de API.

Saiba mais

github.com/AtlasCloudAI/mcp-server

API Schema

{
  "info": {
    "title": "AtlasCloud API",
    "version": "1.0.0",
    "description": "The AtlasCloud API."
  },
  "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/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"
    }
  },
  "components": {
    "schemas": {
      "Input": {
        "properties": {
          "model": {
            "type": "string",
            "description": "model name",
            "default": "google/veo3.1-lite/image-to-video"
          },
          "prompt": {
            "description": "Text description for the video. Supports audio cues per Veo prompt guidance.",
            "type": "string"
          },
          "image": {
            "description": "Initial image to animate (instance image). Accepts a public image URL, a data URL, or raw base64-encoded image bytes (e.g. PNG/JPEG inline data). Input image up to 8MB per Veo 3.1 Lite limits.",
            "type": "string",
            "x-ui-component": "uploader"
          },
          "aspect_ratio": {
            "default": "16:9",
            "description": "The aspect ratio of the generated video.",
            "enum": [
              "16:9",
              "9:16"
            ],
            "type": "string",
            "x-ui-component": "select"
          },
          "duration": {
            "default": 8,
            "description": "Length of the generated video in seconds (durationSeconds). Must be 8 when using 1080p resolution.",
            "enum": [
              4,
              6,
              8
            ],
            "type": "integer",
            "x-ui-component": "select"
          },
          "resolution": {
            "default": "720p",
            "description": "Output resolution. 1080p only supports 8s duration. Veo 3.1 Lite does not support 4K.",
            "enum": [
              "720p",
              "1080p"
            ],
            "type": "string",
            "x-ui-component": "select"
          },
          "seed": {
            "default": -1,
            "description": "Random seed. Does not guarantee determinism but may improve repeatability. -1 means a random seed will be used.",
            "type": "integer"
          }
        },
        "required": [
          "model",
          "prompt",
          "image"
        ],
        "type": "object",
        "x-order-properties": [
          "model",
          "prompt",
          "image",
          "aspect_ratio",
          "duration",
          "resolution",
          "seed"
        ],
        "allOf": [
          {
            "description": "When resolution is 1080p, duration must be 8 (seconds).",
            "if": {
              "properties": {
                "resolution": {
                  "enum": [
                    "1080p"
                  ]
                }
              },
              "required": [
                "resolution"
              ]
            },
            "then": {
              "properties": {
                "duration": {
                  "enum": [
                    8
                  ]
                }
              }
            }
          }
        ]
      },
      "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"
          },
          "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"
      }
    }
  },
  "servers": [
    {
      "url": "https://api.atlascloud.ai"
    }
  ]
}

Template de Prompt Compatível com LLM

# google/veo3.1-lite/image-to-video

> High-efficiency Veo 3.1 Lite image-to-video: animate an input image into video with synchronized audio. Cost-effective for scalable workflows; supports 720p/1080p and common aspect ratios. Does not support 4K outputs or Extension.


## 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**: `google/veo3.1-lite/image-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: `"google/veo3.1-lite/image-to-video"`

- **`prompt`** (`string`, _required_):
  Text description for the video. Supports audio cues per Veo prompt guidance.

- **`image`** (`string`, _required_):
  Initial image to animate (instance image). Accepts a public image URL, a data URL, or raw base64-encoded image bytes (e.g. PNG/JPEG inline data). Input image up to 8MB per Veo 3.1 Lite limits.

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

- **`duration`** (`integer`, _optional_):
  Length of the generated video in seconds (durationSeconds). Must be 8 when using 1080p resolution.
  - Default: `8`
  - Options: 4, 6, 8

- **`resolution`** (`string`, _optional_):
  Output resolution. 1080p only supports 8s duration. Veo 3.1 Lite does not support 4K.
  - Default: `"720p"`
  - Options: "720p", "1080p"

- **`seed`** (`integer`, _optional_):
  Random seed. Does not guarantee determinism but may improve repeatability. -1 means a random seed will be used.
  - Default: `-1`



**Required Parameters Example**:

```json
{
  "model": "google/veo3.1-lite/image-to-video",
  "prompt": "",
  "image": ""
}
```


**Full Example**:

```json
{
  "model": "google/veo3.1-lite/image-to-video",
  "prompt": "",
  "image": "",
  "aspect_ratio": "16:9",
  "duration": 8,
  "resolution": "720p",
  "seed": -1
}
```


### 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”).

- **`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": "google/veo3.1-lite/image-to-video",
  "prompt": "",
  "image": "",
  "aspect_ratio": "16:9",
  "duration": 8,
  "resolution": "720p",
  "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/google/veo3.1-lite/image-to-video)

A modern fighter jet ignites its afterburners and launches vertically into the sky at extreme speed, thick vapor trails forming behind the wings, clouds tearing apart as the jet pierces upward, cinematic camera tracking from below, dramatic lighting, ultra-realistic, IMAX-style aerial shot.

Carregando...

Google Veo 3.1 Lite — Image-to-Video

Veo 3.1 Lite Preview (veo-3.1-lite-generate-preview) is a high-efficiency, developer-oriented video model from Google, optimized for scalable, programmable image-driven workflows. It produces video with audio and is positioned as a cost-effective option for teams building high-volume video applications. According to the official model documentation, Veo 3.1 Lite Preview does not support 4K outputs or Extension; consult the Video generation docs for end-to-end features and limits.

Overview

Generate videos by animating an input image using Google's Veo 3.1 Lite model.

A lightweight, cost-effective variant of Veo 3.1 that always generates video with audio.

Supported options

The model supports:

Input images up to 8MB in size
720p or 1080p output resolution
4, 6, or 8 second duration (1080p requires 8s)
16:9 or 9:16 aspect ratio
Audio is always generated
Safety filters are applied to both input images and generated content

Veo 3.1 Lite Image-to-Video API by Google

Entrada

Saída

Parâmetros

Exemplo de código

Instalar

Autenticação

Cabeçalhos HTTP

Enviar uma solicitação

Enviar uma solicitação

Corpo da solicitação

Resposta

Verificar status

Exemplo de polling

Valores de status

Resposta concluída

Enviar arquivos

Exemplo de upload

Resposta

Schema de entrada

Exemplo de corpo da solicitação

Schema de saída

Exemplo de resposta

Atlas Cloud Skills

Clientes compatíveis

Instalar

Configurar chave de API

Funcionalidades

MCP Server

Clientes compatíveis

Instalar

Configuração

Ferramentas disponíveis

API Schema

Template de Prompt Compatível com LLM

Google Veo 3.1 Lite — Image-to-Video

Overview

Supported options

Reference

Explorar Modelos Semelhantes

Gemini Omni Flash Reference-to-Video

Gemini Omni Flash Image-to-Video

Gemini Omni Flash Video Edit

Gemini Omni Flash Text-to-Video

Gemini Omni Flash Reference-to-Video Developer

Gemini Omni Flash Image-to-Video Developer

Gemini Omni Flash Text-to-Video Developer

Veo 3.1 Lite Text-to-video

Veo 3.1 Lite Start-End Frame to Video

Veo3.1 Fast Image-to-video

Veo3.1 Fast Text-to-video

Veo3.1 Image-to-video

Veo3.1 Reference-to-video

Veo3.1 Text-to-video

Sync.so Lipsync v3

VEED Lipsync

Uma API para toda a IA de mídia.

Join our Discord community

Entrada

Saída

Parâmetros

Exemplo de código

Instalar

Autenticação

Cabeçalhos HTTP

Enviar uma solicitação

Enviar uma solicitação

Corpo da solicitação

Resposta

Verificar status

Exemplo de polling

Valores de status

Resposta concluída

Enviar arquivos

Exemplo de upload

Resposta

Schema de entrada

Exemplo de corpo da solicitação

Schema de saída

Exemplo de resposta