Vidu Q3 Mix Reference-to-Video API by Vidu
Vidu Q3-Mix Reference-to-Video generates videos from 1-4 reference images with consistent subjects. Offers strong visual quality with intelligent scene transitions, smooth dynamic effects, and audio support up to 1080p.
Entrada
Salida
InactivoCada ejecución costará $0.106. Con $10 puedes ejecutar aproximadamente 94 veces.
Puedes continuar con:
Ejemplo 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": "vidu/q3-mix/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()Instalar
Instala el paquete necesario para tu lenguaje de programación.
pip install requestsAutenticación
Todas las solicitudes de API requieren autenticación mediante una clave de API. Puedes obtener tu clave de API desde el panel de Atlas Cloud.
export ATLASCLOUD_API_KEY="your-api-key-here"Encabezados HTTP
import os
API_KEY = os.environ.get("ATLASCLOUD_API_KEY")
headers = {
"Content-Type": "application/json",
"Authorization": f"Bearer {API_KEY}"
}Nunca expongas tu clave de API en código del lado del cliente ni en repositorios públicos. Usa variables de entorno o un proxy de backend en su lugar.
Enviar una solicitud
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 una solicitud
Envía una solicitud de generación asíncrona. La API devuelve un ID de predicción que puedes usar para verificar el estado y obtener el resultado.
/api/v1/model/generateVideoCuerpo de la solicitud
import requests
url = "https://api.atlascloud.ai/api/v1/model/generateVideo"
headers = {
"Content-Type": "application/json",
"Authorization": "Bearer $ATLASCLOUD_API_KEY"
}
data = {
"model": "vidu/q3-mix/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']}")Respuesta
{
"id": "pred_abc123",
"status": "processing",
"model": "model-name",
"created_at": "2025-01-01T00:00:00Z"
}Verificar estado
Consulta el endpoint de predicción para verificar el estado actual de tu solicitud.
/api/v1/model/prediction/{prediction_id}Ejemplo 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 estado
processingLa solicitud aún se está procesando.completedLa generación está completa. Las salidas están disponibles.succeededLa generación fue exitosa. Las salidas están disponibles.failedLa generación falló. Verifica el campo de error.Respuesta completada
{
"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"
}
}Subir archivos
Sube archivos al almacenamiento de Atlas Cloud y obtén una URL que puedes usar en tus solicitudes de API. Usa multipart/form-data para subir.
/api/v1/model/uploadMediaEjemplo de carga
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}")Respuesta
{
"data": {
"download_url": "https://storage.atlascloud.ai/uploads/abc123/image.png",
"file_name": "image.png",
"content_type": "image/png",
"size": 1024000
}
}Schema de entrada
Los siguientes parámetros se aceptan en el cuerpo de la solicitud.
No hay parámetros disponibles.
Ejemplo de cuerpo de solicitud
{
"model": "vidu/q3-mix/reference-to-video"
}Schema de salida
La API devuelve una respuesta de predicción con las URL de salida generadas.
Ejemplo de respuesta
{
"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 integra más de 300 modelos de IA directamente en tu asistente de codificación con IA. Un solo comando para instalar y luego usa lenguaje natural para generar imágenes, videos y chatear con LLM.
Clientes compatibles
Instalar
npx skills add AtlasCloudAI/atlas-cloud-skillsConfigurar clave de API
Obtén tu clave de API desde el panel de Atlas Cloud y configúrala como variable de entorno.
export ATLASCLOUD_API_KEY="your-api-key-here"Funcionalidades
Una vez instalado, puedes usar lenguaje natural en tu asistente de IA para acceder a todos los modelos de Atlas Cloud.
MCP Server
Atlas Cloud MCP Server conecta tu IDE con más de 300 modelos de IA a través del Model Context Protocol. Funciona con cualquier cliente compatible con MCP.
Clientes compatibles
Instalar
npx -y atlascloud-mcpConfiguración
Agrega la siguiente configuración al archivo de configuración de MCP de tu IDE.
{
"mcpServers": {
"atlascloud": {
"command": "npx",
"args": [
"-y",
"atlascloud-mcp"
],
"env": {
"ATLASCLOUD_API_KEY": "your-api-key-here"
}
}
}
}Herramientas disponibles
API Schema
Schema no disponibleSin ejemplos disponibles
Por favor inicia sesión para ver el historial de solicitudes
Necesitas iniciar sesión para acceder al historial de solicitudes del modelo.
Iniciar Sesión1. Introduction
Vidu Q3 is an advanced AI video generation model developed by Shengshu Technology (生数科技) in collaboration with Tsinghua University. Released on January 30, 2026, Vidu Q3 is designed to produce high-fidelity, synchronized audio-visual content with industry-leading continuous video length and native support for integrated audio generation.
The model represents a significant advancement in automated video synthesis by unifying multiple complex video generation tasks—such as lip-synced dialogue, dynamic camera movements, and multi-shot storytelling—into a single-pass framework. Leveraging a novel Transformer-based diffusion architecture, Vidu Q3 sets a new standard for cinematic and marketing video content creation with its combination of spatial-temporal coherence, multimodal input flexibility, and real-time directorial control.
2. Key Features & Innovations
-
Native Audio-Video Synchronization: Vidu Q3 generates lip-synced dialogue, sound effects, and background music simultaneously within a single pass, ensuring precise temporal alignment between audio tracks and visual lip movements without requiring post-processing.
-
Extended High-Definition Video Generation: Supports up to 16 seconds of continuous video at 1080p resolution and 24 frames per second—the longest continuous generation duration among leading competitors—enabling more complex storytelling sequences.
-
Smart Cuts for Scene Detection: Integrates automatic scene boundary detection and multi-shot narrative transitions, which facilitate the smooth generation of dynamic video scenes without manual intervention.
-
Native Camera Control: Allows frame-level directorial commands such as pans, push-ins, and tracking shots within the generation pipeline, granting users granular cinematic control over the resulting video composition.
-
Multimodal Input Flexibility: Accepts both text-to-video and image-to-video inputs with configurable start and end frame controls, enabling versatile use cases that range from scripted storyboarding to visual style transfer.
-
Transformer-based Diffusion Architecture with Spatiotemporal Attention: The underlying Universal Vision Transformer (U-ViT) utilizes spatiotemporal attention mechanisms instead of conventional convolutional U-Nets, improving motion consistency and temporal coherence across generated frames.
-
Model Variants Tailored for Fidelity and Speed: Offers differentiated configurations including Q3 Pro for maximum visual fidelity, Q3 Turbo optimized for higher generation speed, and the legacy Q2 Series focused on character consistency.
3. Model Architecture & Technical Details
Vidu Q3 is architected on the U-ViT (Universal Vision Transformer) framework, replacing traditional convolutional U-Net diffusion models with a Transformer-based diffusion approach. This design enables enhanced modeling of spatiotemporal dependencies essential for consistent video generation with coherent motion and scene dynamics.
The training utilized large-scale, multimodal datasets encompassing paired video, audio, and textual data to foster robust cross-modal understanding and synthesis. Multiple training stages refined resolution and temporal granularity, progressing toward 1080p, 24fps output over sequences up to 16 seconds.
Specialized modules incorporated include spatiotemporal attention layers for motion consistency and native audio-visual synchronization, alongside smart cut detection layers for automatic scene segmentation. The pipeline supports multimodal conditioning inputs (text and images) with frame-level temporal control allowing start and end frame specification.
Post-training refinement employed techniques such as supervised fine-tuning on domain-specific cinematic data and continuous evaluation on video generation benchmarks to optimize lip-sync accuracy and camera control responsiveness.
4. Performance Highlights
Vidu Q3 demonstrably leads in multiple benchmark categories, particularly for continuous video length and audiovisual integration quality. It achieves an ELO rating between approximately 1220–1244 on the Artificial Analysis Video Arena, outperforming contemporaries such as Runway Gen-4.5 and Kling 2.5 Turbo.
| Rank | Model | Developer | ELO Score | Release Date |
|---|---|---|---|---|
| 1 | Sora 2 | [Undisclosed] | ~1250+ | Pre-2026 |
| 2 | Vidu Q3 | Shengshu Tech & Tsinghua | 1220–1244 | Jan 30, 2026 |
| 3 | Runway Gen-4.5 | Runway | ~1200 | 2025 |
| 4 | Kling 2.5 Turbo | Kling AI | ~1190 | Late 2025 |
Qualitatively, Vidu Q3 delivers superior cinematics including advanced native camera motion and scene transitions compared to Veo 3.1 and Grok Imagine, while maintaining better audio integration than Sora 2 and Kling 3.0. Its 16-second generation duration notably surpasses the typical 8-15 second range of competitors, allowing more complex narratives per generation.
5. Intended Use & Applications
-
Commercial Advertising: Produces 12-16 second product demonstration videos with synchronized audio and high realism, suitable for digital marketing campaigns.
-
Marketing Videos: Generates videos combining dialogue, sound effects, and background music tailored for brand storytelling and promotional content.
-
Cinematic Short-Form Storytelling: Enables filmmakers and content creators to automatically craft multi-shot video sequences with directorial camera control and scene transitions.
-
Social Media Content Creation: Facilitates rapid production of engaging social videos with lip-synced speech and dynamic visuals optimized for platform consumption.
-
Architectural Visualization: Visualizes architectural designs with realistic camera movements and synchronized ambient sounds enhancing presentation fidelity.
-
Educational Video Production: Supports creation of instructional content blending narrated audio with synchronized visual demonstrations and scene changes.
