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.
INPUT
OUTPUT
IdleYour request will cost $0.068 per run. For $10 you can run this model approximately 147 times.
Here's what you can do next:
Code Example
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()Install
Install the required package for your language.
pip install requestsAuthentication
All API requests require authentication via an API key. You can get your API key from the Atlas Cloud dashboard.
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}"
}Never expose your API key in client-side code or public repositories. Use environment variables or a backend proxy instead.
Submit a request
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())Submit a Request
Submit an asynchronous generation request. The API returns a prediction ID that you can use to check the status and retrieve the result.
/api/v1/model/generateVideoRequest Body
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']}")Response
{
"id": "pred_abc123",
"status": "processing",
"model": "model-name",
"created_at": "2025-01-01T00:00:00Z"
}Check Status
Poll the prediction endpoint to check the current status of your request.
/api/v1/model/prediction/{prediction_id}Polling Example
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)Status Values
processingThe request is still being processed.completedGeneration is complete. Outputs are available.succeededGeneration succeeded. Outputs are available.failedGeneration failed. Check the error field.Completed Response
{
"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"
}
}Upload Files
Upload files to Atlas Cloud storage and get a URL you can use in your API requests. Use multipart/form-data to upload.
/api/v1/model/uploadMediaUpload Example
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}")Response
{
"data": {
"download_url": "https://storage.atlascloud.ai/uploads/abc123/image.png",
"file_name": "image.png",
"content_type": "image/png",
"size": 1024000
}
}Input Schema
The following parameters are accepted in the request body.
No parameters available.
Example Request Body
{
"model": "atlascloud/van-2.5/text-to-video"
}Output Schema
The API returns a prediction response with the generated output URLs.
Example Response
{
"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 integrates 300+ AI models directly into your AI coding assistant. One command to install, then use natural language to generate images, videos, and chat with LLMs.
Supported Clients
Install
npx skills add AtlasCloudAI/atlas-cloud-skillsSetup API Key
Get your API key from the Atlas Cloud dashboard and set it as an environment variable.
export ATLASCLOUD_API_KEY="your-api-key-here"Capabilities
Once installed, you can use natural language in your AI assistant to access all Atlas Cloud models.
MCP Server
Atlas Cloud MCP Server connects your IDE with 300+ AI models via the Model Context Protocol. Works with any MCP-compatible client.
Supported Clients
Install
npx -y atlascloud-mcpConfiguration
Add the following configuration to your IDE's MCP settings file.
{
"mcpServers": {
"atlascloud": {
"command": "npx",
"args": [
"-y",
"atlascloud-mcp"
],
"env": {
"ATLASCLOUD_API_KEY": "your-api-key-here"
}
}
}
}Available Tools
API Schema
Schema not availablePlease log in to view request history
You need to be logged in to access your model request history.
Log InVan 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.
