Open and Advanced Large-Scale Video Generative Models.

Open and Advanced Large-Scale Video Generative Models.
แต่ละครั้งจะใช้ 0.032 ด้วย $10 คุณสามารถรันได้ประมาณ 312 ครั้ง
คุณสามารถทำต่อได้:
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": "alibaba/wan-2.2-spicy/video-extend",
"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()ติดตั้งแพ็คเกจที่จำเป็นสำหรับภาษาของคุณ
pip install requestsคำขอ API ทั้งหมดต้องมีการยืนยันตัวตนผ่าน API key คุณสามารถรับ API key ได้จากแดชบอร์ด Atlas Cloud
export ATLASCLOUD_API_KEY="your-api-key-here"import os
API_KEY = os.environ.get("ATLASCLOUD_API_KEY")
headers = {
"Content-Type": "application/json",
"Authorization": f"Bearer {API_KEY}"
}อย่าเปิดเผย API key ของคุณในโค้ดฝั่งไคลเอนต์หรือที่เก็บข้อมูลสาธารณะ ให้ใช้ตัวแปรสภาพแวดล้อมหรือพร็อกซีฝั่งเซิร์ฟเวอร์แทน
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())ส่งคำขอสร้างแบบอะซิงโครนัส API จะส่งคืน prediction ID ที่คุณสามารถใช้ตรวจสอบสถานะและดึงผลลัพธ์ได้
/api/v1/model/generateVideoimport requests
url = "https://api.atlascloud.ai/api/v1/model/generateVideo"
headers = {
"Content-Type": "application/json",
"Authorization": "Bearer $ATLASCLOUD_API_KEY"
}
data = {
"model": "alibaba/wan-2.2-spicy/video-extend",
"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']}"){
"id": "pred_abc123",
"status": "processing",
"model": "model-name",
"created_at": "2025-01-01T00:00:00Z"
}สำรวจ prediction endpoint เพื่อตรวจสอบสถานะปัจจุบันของคำขอ
/api/v1/model/prediction/{prediction_id}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)processingคำขอยังอยู่ระหว่างการประมวลผลcompletedการสร้างเสร็จสมบูรณ์แล้ว ผลลัพธ์พร้อมใช้งานsucceededการสร้างสำเร็จแล้ว ผลลัพธ์พร้อมใช้งานfailedการสร้างล้มเหลว ตรวจสอบฟิลด์ error{
"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"
}
}อัปโหลดไฟล์ไปยังที่เก็บข้อมูล Atlas Cloud และรับ URL ที่คุณสามารถใช้ในคำขอ API ของคุณ ใช้ multipart/form-data ในการอัปโหลด
/api/v1/model/uploadMediaimport 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}"){
"data": {
"download_url": "https://storage.atlascloud.ai/uploads/abc123/image.png",
"file_name": "image.png",
"content_type": "image/png",
"size": 1024000
}
}พารามิเตอร์ต่อไปนี้ยอมรับในเนื้อหาคำขอ
ไม่มีพารามิเตอร์ที่ใช้ได้
{
"model": "alibaba/wan-2.2-spicy/video-extend"
}API จะส่งคืนการตอบกลับ prediction พร้อม URL ของผลลัพธ์ที่สร้างขึ้น
{
"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 เชื่อมต่อโมเดล AI กว่า 300+ เข้ากับผู้ช่วยเขียนโค้ด AI ของคุณโดยตรง ติดตั้งด้วยคำสั่งเดียว จากนั้นใช้ภาษาธรรมชาติเพื่อสร้างรูปภาพ วิดีโอ และสนทนากับ LLM
npx skills add AtlasCloudAI/atlas-cloud-skillsรับ API key จากแดชบอร์ด Atlas Cloud และตั้งค่าเป็นตัวแปรสภาพแวดล้อม
export ATLASCLOUD_API_KEY="your-api-key-here"เมื่อติดตั้งแล้ว คุณสามารถใช้ภาษาธรรมชาติในผู้ช่วย AI ของคุณเพื่อเข้าถึงโมเดล Atlas Cloud ทั้งหมด
Atlas Cloud MCP Server เชื่อมต่อ IDE ของคุณกับโมเดล AI กว่า 300+ ผ่าน Model Context Protocol ใช้งานได้กับไคลเอนต์ที่รองรับ MCP ทุกตัว
npx -y atlascloud-mcpเพิ่มการกำหนดค่าต่อไปนี้ลงในไฟล์ตั้งค่า MCP ของ IDE ของคุณ
{
"mcpServers": {
"atlascloud": {
"command": "npx",
"args": [
"-y",
"atlascloud-mcp"
],
"env": {
"ATLASCLOUD_API_KEY": "your-api-key-here"
}
}
}
}ไม่มี Schema| Field | Description |
|---|---|
| Model Name | Wan 2.2 |
| Developed by | Alibaba Tongyi Wanxiang Lab |
| Release Date | July 28, 2025 |
| Model Type | Video Generation |
| Related Links | GitHub: https://github.com/Wan-Video/Wan2.2, Hugging Face: https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B, Paper (arXiv): https://arxiv.org/abs/2503.20314 |
Wan 2.2 is a significant upgrade to the Wan series of foundational video models, designed to push the boundaries of generative AI in video creation. The primary goal of Wan 2.2 is to provide an open and advanced suite of tools for generating high-quality, cinematic videos from various inputs, including text, images, and audio. Its core contribution lies in making state-of-the-art video generation technology accessible to a broader community of researchers and creators through open-sourcing its models and code. The project emphasizes cinematic aesthetics, complex motion generation, and computational efficiency, introducing several key innovations to achieve these aims.
Wan 2.2 introduces several groundbreaking features that set it apart from previous models:
Effective MoE Architecture: Wan 2.2 is the first model to successfully integrate a Mixture-of-Experts (MoE) architecture into a video diffusion model. This design uses specialized expert models for different stages of the denoising process, which significantly increases the model's capacity without raising computational costs. The model has a total of 27B parameters, but only 14B are active during any given step.
Cinematic-Level Aesthetics: The model was trained on a meticulously curated dataset with detailed labels for cinematic properties like lighting, composition, and color tone. This allows users to generate videos with precise and controllable artistic styles, achieving a professional, cinematic look.
Complex Motion Generation: By training on a vastly expanded dataset (+65.6% more images and +83.2% more videos compared to Wan 2.1), Wan 2.2 demonstrates a superior ability to generate complex and realistic motion. It shows enhanced generalization across various motions, semantics, and aesthetics.
Efficient High-Definition Video: The suite includes a highly efficient 5B model (TI2V-5B) that utilizes an advanced VAE for high-compression video generation. It can produce 720p video at 24 fps and is capable of running on consumer-grade GPUs like the NVIDIA RTX 4090, making high-definition AI video generation more accessible.
The architecture of Wan 2.2 is built upon the Diffusion Transformer (DiT) paradigm and incorporates several key technical advancements.
The primary models in the Wan 2.2 suite, such as the T2V-A14B, employ a Mixture-of-Experts (MoE) architecture. This framework consists of two main expert models:
The transition between these experts is dynamically determined by the signal-to-noise ratio (SNR) during generation. This MoE design allows the model to have a large parameter count (27B total) while keeping the number of active parameters (14B) and computational load comparable to smaller models.
Wan 2.2 is offered in several variants, each tailored for different tasks and computational resources.
| Model Variant | Total Parameters | Key Feature | Supported Tasks |
|---|---|---|---|
| T2V-A14B | ~27B (14B active) | MoE for Text-to-Video | Text-to-Video |
| I2V-A14B | ~27B (14B active) | MoE for Image-to-Video | Image-to-Video |
| TI2V-5B | 5B | High-Compression VAE | Text-to-Video, Image-to-Video |
| S2V-14B | ~27B (14B active) | MoE for Speech-to-Video | Speech-to-Video |
| Animate-14B | ~27B (14B active) | MoE for Animation | Character Animation & Replacement |
Wan 2.2 is designed for a wide range of creative and academic applications. Its various models support a comprehensive set of downstream tasks, making it a versatile tool for digital artists, filmmakers, researchers, and developers.