Convert prompts into cinematic video clips with synchronized sound. Van 2.5 generates 720p/1080p outputs with stable motion, native audio sync, and prompt-faithful visual storytelling.
Eingabe
Ausgabe
InaktivJede Ausführung kostet $0.068. Für $10 können Sie ca. 147 Mal ausführen.
Sie können fortfahren mit:
Codebeispiel
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": "atlascloud/van-2.5/text-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()Installieren
Installieren Sie das erforderliche Paket für Ihre Programmiersprache.
pip install requestsAuthentifizierung
Alle API-Anfragen erfordern eine Authentifizierung über einen API-Schlüssel. Sie können Ihren API-Schlüssel über das Atlas Cloud Dashboard erhalten.
export ATLASCLOUD_API_KEY="your-api-key-here"HTTP-Header
import os
API_KEY = os.environ.get("ATLASCLOUD_API_KEY")
headers = {
"Content-Type": "application/json",
"Authorization": f"Bearer {API_KEY}"
}Geben Sie Ihren API-Schlüssel niemals in clientseitigem Code oder öffentlichen Repositories preis. Verwenden Sie stattdessen Umgebungsvariablen oder einen Backend-Proxy.
Anfrage senden
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())Anfrage senden
Senden Sie eine asynchrone Generierungsanfrage. Die API gibt eine Vorhersage-ID zurück, mit der Sie den Status prüfen und das Ergebnis abrufen können.
/api/v1/model/generateVideoAnfragekörper
import requests
url = "https://api.atlascloud.ai/api/v1/model/generateVideo"
headers = {
"Content-Type": "application/json",
"Authorization": "Bearer $ATLASCLOUD_API_KEY"
}
data = {
"model": "atlascloud/van-2.5/text-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']}")Antwort
{
"id": "pred_abc123",
"status": "processing",
"model": "model-name",
"created_at": "2025-01-01T00:00:00Z"
}Status prüfen
Fragen Sie den Vorhersage-Endpunkt ab, um den aktuellen Status Ihrer Anfrage zu überprüfen.
/api/v1/model/prediction/{prediction_id}Abfrage-Beispiel
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)Statuswerte
processingDie Anfrage wird noch verarbeitet.completedDie Generierung ist abgeschlossen. Ergebnisse sind verfügbar.succeededDie Generierung war erfolgreich. Ergebnisse sind verfügbar.failedDie Generierung ist fehlgeschlagen. Überprüfen Sie das Fehlerfeld.Abgeschlossene Antwort
{
"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"
}
}Dateien hochladen
Laden Sie Dateien in den Atlas Cloud Speicher hoch und erhalten Sie eine URL, die Sie in Ihren API-Anfragen verwenden können. Verwenden Sie multipart/form-data zum Hochladen.
/api/v1/model/uploadMediaUpload-Beispiel
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}")Antwort
{
"data": {
"download_url": "https://storage.atlascloud.ai/uploads/abc123/image.png",
"file_name": "image.png",
"content_type": "image/png",
"size": 1024000
}
}Eingabe-Schema
Die folgenden Parameter werden im Anfragekörper akzeptiert.
Keine Parameter verfügbar.
Beispiel-Anfragekörper
{
"model": "atlascloud/van-2.5/text-to-video"
}Ausgabe-Schema
Die API gibt eine Vorhersage-Antwort mit den generierten Ausgabe-URLs zurück.
Beispielantwort
{
"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 integriert über 300 KI-Modelle direkt in Ihren KI-Coding-Assistenten. Ein Befehl zur Installation, dann verwenden Sie natürliche Sprache, um Bilder, Videos zu generieren und mit LLMs zu chatten.
Unterstützte Clients
Installieren
npx skills add AtlasCloudAI/atlas-cloud-skillsAPI-Schlüssel einrichten
Erhalten Sie Ihren API-Schlüssel über das Atlas Cloud Dashboard und setzen Sie ihn als Umgebungsvariable.
export ATLASCLOUD_API_KEY="your-api-key-here"Funktionen
Nach der Installation können Sie natürliche Sprache in Ihrem KI-Assistenten verwenden, um auf alle Atlas Cloud Modelle zuzugreifen.
MCP-Server
Der Atlas Cloud MCP-Server verbindet Ihre IDE mit über 300 KI-Modellen über das Model Context Protocol. Funktioniert mit jedem MCP-kompatiblen Client.
Unterstützte Clients
Installieren
npx -y atlascloud-mcpKonfiguration
Fügen Sie die folgende Konfiguration zur MCP-Einstellungsdatei Ihrer IDE hinzu.
{
"mcpServers": {
"atlascloud": {
"command": "npx",
"args": [
"-y",
"atlascloud-mcp"
],
"env": {
"ATLASCLOUD_API_KEY": "your-api-key-here"
}
}
}
}Verfügbare Werkzeuge
API-Schema
Schema nicht verfügbarAnmelden, um Anfrageverlauf anzuzeigen
Sie müssen angemeldet sein, um auf Ihren Modellanfrageverlauf zuzugreifen.
AnmeldenVan 2.5: A next-generation AI video generation model developed by AtlasCloud.
Model Card Overview
| Field | Description |
|---|---|
| Model Name | Van 2.5 |
| Developed By | AtlasCloud |
| Model Type | Generative AI, Video Foundation Model |
Introduction
Van 2.5 is a state-of-the-art, open-source video foundation model developed by AtlasCloud. It is designed to generate high-quality, cinematic videos complete with synchronized audio directly from text or image prompts. The model represents a significant advancement in the field of generative AI, aiming to lower the barrier for creative video production. Its core contribution lies in its ability to produce coherent, dynamic, and narratively consistent video clips with a high degree of realism and integrated audio-visual elements, such as lip-sync and sound effects, in a single, streamlined process.
Key Features & Innovations
Van 2.5 introduces several key features that distinguish it from previous models and competitors:
- Unified Audio-Visual Synthesis: Unlike many models that require separate steps for video and audio generation, Van 2.5 creates video with natively synchronized audio, including voice, sound effects, and lip-sync, in one step.
- High-Fidelity, High-Resolution Output: The model is capable of generating videos in multiple resolutions, including 480p, 720p, and full 1080p HD, with significant improvements in visual quality and frame-to-frame stability over its predecessors.
- Extended Video Duration: Van 2.5 can generate video clips up to 10 seconds in length, offering more creative flexibility for storytelling compared to other models in its class.
- Advanced Cinematic Control: The model demonstrates a sophisticated understanding of cinematic language, allowing for precise control over camera movement, shot composition, and character consistency within scenes.
- Open-Source Commitment: Following the precedent set by earlier versions, the Van series of models, including Van 2.5, are open-sourced to encourage research, development, and innovation within the broader AI community.
Model Architecture & Technical Details
Van 2.5 is built upon the Diffusion Transformer (DiT) paradigm, which has become a mainstream approach for high-quality generative tasks. The technical framework for the Van model series outlines a suite of innovations that contribute to its performance.
The architecture includes a novel Variational Autoencoder (VAE) designed for high-efficiency video compression, enabling the model to handle high-resolution video data effectively. The Van series is available in multiple sizes to balance performance and computational requirements, such as the 1.3B and 14B parameter models detailed for Van 2.2. The model was trained on a massive, curated dataset comprising billions of images and videos, which enhances its ability to generalize across a wide range of motions, semantics, and aesthetic styles.
Intended Use & Applications
Van 2.5 is designed for a wide array of applications in creative and commercial fields. Its intended uses include:
- Content Creation: Generating short-form videos for social media, marketing campaigns, and digital advertising.
- Storytelling and Filmmaking: Creating cinematic scenes, character animations, and narrative sequences for short films and conceptual art.
- Prototyping: Rapidly visualizing scripts and storyboards for film, television, and game development.
- Personalized Media: Enabling users to create unique, personalized video content from their own ideas and images.
Performance
Van 2.5 has demonstrated significant performance improvements over previous versions and holds a competitive position against other leading video generation models. Independent reviews and benchmarks provide insight into its capabilities.
Benchmark Scores
A review conducted by industry laboratories evaluated the model's visual generation capabilities across several metrics.
| Metric | Score (out of 10) |
|---|---|
| Prompt Adherence | 7.0 |
| Temporal Consistency | 6.6 |
| Visual Fidelity | 6.5 |
| Motion Quality | 5.9 |
| Style & Cinematic Realism | 5.7 |
| Overall Score | 6.3 |
These scores indicate strong prompt understanding and a notable improvement in visual quality from Van 2.2, although it still shows limitations in complex motion and realism compared to top-tier commercial models.
