Vidu Q2-Pro Reference-to-Video is an advanced AI video generation model that brings static images to life. Upload a reference image and describe the motion you want — the model generates high-quality video with smooth animation, optional audio, and cinematic quality up to 1080p.
輸入
正在載入參數設定...
輸出
閒置生成的影片將在這裡顯示
設定參數後點擊執行開始生成
每次執行將花費 $0.085。$10 可執行約 117 次。
程式碼範例
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": "vidu/q2-pro/reference-to-video",
"prompt": "A beautiful sunset over the ocean with gentle waves",
"width": 512,
"height": 512,
"duration": 3,
"fps": 24,
}
generate_response = requests.post(generate_url, headers=headers, json=data)
generate_result = generate_response.json()
prediction_id = generate_result["data"]["id"]
# Step 2: Poll for result
poll_url = f"https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}"
def check_status():
while True:
response = requests.get(poll_url, headers={"Authorization": "Bearer $ATLASCLOUD_API_KEY"})
result = response.json()
if result["data"]["status"] in ["completed", "succeeded"]:
print("Generated video:", result["data"]["outputs"][0])
return result["data"]["outputs"][0]
elif result["data"]["status"] == "failed":
raise Exception(result["data"]["error"] or "Generation failed")
else:
# Still processing, wait 2 seconds
time.sleep(2)
video_url = check_status()安裝
為您的程式語言安裝所需的套件。
bash
pip install requests驗證
所有 API 請求都需要透過 API 金鑰進行驗證。您可以從 Atlas Cloud 儀表板取得 API 金鑰。
bash
export ATLASCLOUD_API_KEY="your-api-key-here"HTTP 標頭
python
import os
API_KEY = os.environ.get("ATLASCLOUD_API_KEY")
headers = {
"Content-Type": "application/json",
"Authorization": f"Bearer {API_KEY}"
}請妥善保管您的 API 金鑰
切勿在客戶端程式碼或公開儲存庫中暴露您的 API 金鑰。請改用環境變數或後端代理。
提交請求
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())提交請求
提交非同步生成請求。API 會傳回一個預測 ID，您可以用它來檢查狀態並取得結果。
POST
/api/v1/model/generateVideo請求主體
import requests
url = "https://api.atlascloud.ai/api/v1/model/generateVideo"
headers = {
"Content-Type": "application/json",
"Authorization": "Bearer $ATLASCLOUD_API_KEY"
}
data = {
"model": "vidu/q2-pro/reference-to-video",
"input": {
"prompt": "A beautiful sunset over the ocean with gentle waves"
}
}
response = requests.post(url, headers=headers, json=data)
result = response.json()
print(f"Prediction ID: {result['id']}")
print(f"Status: {result['status']}")回應
{
"id": "pred_abc123",
"status": "processing",
"model": "model-name",
"created_at": "2025-01-01T00:00:00Z"
}檢查狀態
輪詢預測端點以檢查請求的當前狀態。
GET
/api/v1/model/prediction/{prediction_id}輪詢範例
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)狀態值
processing請求仍在處理中。completed生成完成。輸出已可取得。succeeded生成成功。輸出已可取得。failed生成失敗。請檢查錯誤欄位。完成回應
{
"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"
}
}上傳檔案
上傳檔案至 Atlas Cloud 儲存空間並取得 URL，可用於您的 API 請求。使用 multipart/form-data 上傳。
POST
/api/v1/model/uploadMedia上傳範例
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}")回應
{
"data": {
"download_url": "https://storage.atlascloud.ai/uploads/abc123/image.png",
"file_name": "image.png",
"content_type": "image/png",
"size": 1024000
}
}輸入 Schema
以下參數可在請求主體中使用。
總計: 0必填: 0選填: 0
無可用參數。
範例請求主體
json
{
"model": "vidu/q2-pro/reference-to-video"
}輸出 Schema
API 傳回包含生成輸出 URL 的預測回應。
idstringrequired
Unique identifier for the prediction.
statusstringrequired
Current status of the prediction.
processingcompletedsucceededfailed
modelstringrequired
The model used for generation.
outputsarray[string]
Array of output URLs. Available when status is "completed".
errorstring
Error message if status is "failed".
metricsobject
Performance metrics.
predict_timenumber
Time taken for video generation in seconds.
created_atstringrequired
ISO 8601 timestamp when the prediction was created.
completed_atstring
ISO 8601 timestamp when the prediction was completed.
範例回應
json
{
"id": "pred_abc123",
"status": "completed",
"model": "model-name",
"outputs": [
"https://storage.atlascloud.ai/outputs/result.mp4"
],
"metrics": {
"predict_time": 45.2
},
"created_at": "2025-01-01T00:00:00Z",
"completed_at": "2025-01-01T00:00:10Z"
}Atlas Cloud Skills
Atlas Cloud Skills 將 300 多個 AI 模型直接整合至您的 AI 程式碼助手。一鍵安裝，即可使用自然語言生成圖片、影片，以及與 LLM 對話。
支援的客戶端
Claude Code
OpenAI Codex
Gemini CLI
Cursor
Windsurf
VS Code
Trae
GitHub Copilot
Cline
Roo Code
Amp
Goose
Replit
40+ 支援的客戶端
安裝
bash
npx skills add AtlasCloudAI/atlas-cloud-skills設定 API 金鑰
從 Atlas Cloud 儀表板取得 API 金鑰，並設為環境變數。
bash
export ATLASCLOUD_API_KEY="your-api-key-here"功能
安裝完成後，您可以在 AI 助手中使用自然語言存取所有 Atlas Cloud 模型。
圖片生成使用 Nano Banana 2、Z-Image 等模型生成圖片。
影片創作使用 Kling、Vidu、Veo 等從文字或圖片創建影片。
LLM 對話與 Qwen、DeepSeek 及其他大型語言模型對話。
媒體上傳上傳本機檔案，用於圖片編輯和圖片轉影片工作流程。
MCP Server
Atlas Cloud MCP Server 透過 Model Context Protocol 將您的 IDE 與 300 多個 AI 模型連接。支援任何 MCP 相容的客戶端。
支援的客戶端
Cursor
VS Code
Windsurf
Claude Code
OpenAI Codex
Gemini CLI
Cline
Roo Code
100+ 支援的客戶端
安裝
bash
npx -y atlascloud-mcp設定
將以下設定新增至您 IDE 的 MCP 設定檔中。
json
{
"mcpServers": {
"atlascloud": {
"command": "npx",
"args": [
"-y",
"atlascloud-mcp"
],
"env": {
"ATLASCLOUD_API_KEY": "your-api-key-here"
}
}
}
}可用工具
atlas_generate_image根據文字提示生成圖片。
atlas_generate_video從文字或圖片創建影片。
atlas_chat與大型語言模型對話。
atlas_list_models瀏覽 300 多個可用的 AI 模型。
atlas_quick_generate一步完成內容創建，自動選擇模型。
atlas_upload_media上傳本機檔案用於 API 工作流程。
API Schema
Schema 不可用Vidu Q2-Pro Reference-to-Video
Vidu Q2-Pro Reference-to-Video is a professional-grade AI video generation model that generates video featuring specific subjects with cinematic precision. Provide subject images alongside a motion prompt, and the model delivers up to 1080p video with rich detail, strict subject fidelity, and smooth natural motion — ideal for high-end creative, brand, and production workflows.
Why Choose This?
-
Professional quality Cinematic detail and smooth motion with faithful subject preservation at up to 1080p.
-
Subject-driven generation Feature specific characters or objects with strict visual fidelity throughout the video.
-
Flexible duration Create videos up to 10 seconds in length.
-
Audio generation Optional audio with configurable type: full audio, speech only, or sound effects only.
-
Motion control Adjust movement amplitude for subtle or dynamic animations.
-
Prompt Enhancer Built-in tool to automatically improve your motion descriptions.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the desired motion and action |
| subjects | Yes | One or more subject images to feature in the video (URL or upload) |
| resolution | No | Output quality: 540p, 720p (default), 1080p |
| duration | No | Video length in seconds (1-10, default: 5) |
| aspect_ratio | No | Aspect ratio of the output: 16:9 (default), 9:16, 1:1, 4:3, 3:4 |
| movement_amplitude | No | Motion intensity: auto (default), small, medium, large |
| generate_audio | No | Whether to generate audio for the video (default: true) |
| audio_type | No | Audio type when generate_audio is true: all (default), speech_only, sound_effect_only |
| seed | No | Seed for generation (default: 0); use -1 for a random seed |
How to Use
- Upload your subject images — provide one or more images of the subjects to feature in the video.
- Write your prompt — describe the motion, camera movement, and desired action.
- Set resolution — higher resolution for better quality, lower for faster processing.
- Adjust duration — set video length up to 10 seconds.
- Configure audio (optional) — enable audio and select the audio type: all, speech_only, or sound_effect_only.
- Set motion intensity (optional) — adjust movement_amplitude for subtle or dynamic animations.
- Run — submit and download your video.
Pricing
| Resolution | Cost |
|---|---|
| 540p | Starts at 0.0250/sec |
| 720p | Starts at 0.0250/sec |
| 1080p | Starts at 0.0500/sec |
Best Use Cases
- Character Consistency — Generate high-quality video featuring a specific character or subject with strict visual fidelity.
- Brand & Product Videos — Produce professional-grade product animations while preserving brand identity.
- Film & Narrative Production — Animate reference imagery for previs, concept reels, or final narrative content.
- Style-Consistent Campaigns — Create multiple video assets that maintain a unified visual style across a campaign.
- Premium Social Media Content — Publish cinematic, reference-guided video for high-visibility channels.
Pro Tips
- Use the Prompt Enhancer to refine your motion descriptions.
- Provide high-resolution, well-composed subject images for the strongest visual consistency.
- Be specific about movement direction, speed, camera angles, and framing in your prompt.
- Use multiple subject images to define different characters or scene elements independently.
- Set movement_amplitude to "small" for precise, controlled motion or "large" for expressive action.
- Set audio_type to speech_only when the scene involves dialogue, or sound_effect_only for purely ambient audio.
- Describe lighting, atmosphere, and environmental effects in the prompt for richer scene quality.
Notes
- Both prompt and subjects are required fields.
- Maximum video duration is 10 seconds.
- When generate_audio is true, audio_type controls what is generated: all includes speech and sound effects, speech_only generates voice audio, sound_effect_only generates ambient and environmental sounds.
- Ensure uploaded subject image URLs are publicly accessible.
Related Models
- Vidu Q2-Pro-Fast Reference-to-Video — Pro quality reference-to-video with significantly faster generation speed.
- Vidu Q2-Pro Image-to-Video — Professional quality animation from a single reference image.
- Vidu Q2-Pro Start-End-to-Video — Professional quality video generation with precise start and end frame control.
