
Wan 2.2 Turbo Infinite Image-to-Video LoRA API by Atlas Cloud
Image-to-video LoRA variant for segmented prompt video generation with stable motion and 30fps workflow post-processing.
입력
출력
대기요청당 $0.026가 소요됩니다. $10로 이 모델을 약 384번 실행할 수 있습니다.
다음으로 할 수 있는 작업:
코드 예시
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/wan-2.2-turbo/infinite-image-to-video-lora",
"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()설치
사용하는 언어에 필요한 패키지를 설치하세요.
pip install requests인증
모든 API 요청에는 API 키를 통한 인증이 필요합니다. Atlas Cloud 대시보드에서 API 키를 받을 수 있습니다.
export ATLASCLOUD_API_KEY="your-api-key-here"HTTP 헤더
import os
API_KEY = os.environ.get("ATLASCLOUD_API_KEY")
headers = {
"Content-Type": "application/json",
"Authorization": f"Bearer {API_KEY}"
}클라이언트 측 코드나 공개 저장소에 API 키를 노출하지 마세요. 대신 환경 변수 또는 백엔드 프록시를 사용하세요.
요청 제출
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())요청 제출
비동기 생성 요청을 제출합니다. API는 상태 확인 및 결과 조회에 사용할 수 있는 예측 ID를 반환합니다.
/api/v1/model/generateVideo요청 본문
import requests
url = "https://api.atlascloud.ai/api/v1/model/generateVideo"
headers = {
"Content-Type": "application/json",
"Authorization": "Bearer $ATLASCLOUD_API_KEY"
}
data = {
"model": "atlascloud/wan-2.2-turbo/infinite-image-to-video-lora",
"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']}")응답
{
"id": "pred_abc123",
"status": "processing",
"model": "model-name",
"created_at": "2025-01-01T00:00:00Z"
}상태 확인
예측 엔드포인트를 폴링하여 요청의 현재 상태를 확인합니다.
/api/v1/model/prediction/{prediction_id}폴링 예시
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)상태 값
processing요청이 아직 처리 중입니다.completed생성이 완료되었습니다. 출력을 사용할 수 있습니다.succeeded생성이 성공했습니다. 출력을 사용할 수 있습니다.failed생성에 실패했습니다. 오류 필드를 확인하세요.완료 응답
{
"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"
}
}파일 업로드
Atlas Cloud 스토리지에 파일을 업로드하고 API 요청에 사용할 수 있는 URL을 받습니다. multipart/form-data를 사용하여 업로드합니다.
/api/v1/model/uploadMedia업로드 예시
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}")응답
{
"data": {
"download_url": "https://storage.atlascloud.ai/uploads/abc123/image.png",
"file_name": "image.png",
"content_type": "image/png",
"size": 1024000
}
}입력 Schema
다음 매개변수가 요청 본문에서 사용 가능합니다.
사용 가능한 매개변수가 없습니다.
요청 본문 예시
{
"model": "atlascloud/wan-2.2-turbo/infinite-image-to-video-lora"
}출력 Schema
API는 생성된 출력 URL이 포함된 예측 응답을 반환합니다.
응답 예시
{
"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 Skills는 300개 이상의 AI 모델을 AI 코딩 어시스턴트에 직접 통합합니다. 한 번의 명령으로 설치하고 자연어로 이미지, 동영상 생성 및 LLM과 대화할 수 있습니다.
지원 클라이언트
설치
npx skills add AtlasCloudAI/atlas-cloud-skillsAPI 키 설정
Atlas Cloud 대시보드에서 API 키를 받아 환경 변수로 설정하세요.
export ATLASCLOUD_API_KEY="your-api-key-here"기능
설치 후 AI 어시스턴트에서 자연어를 사용하여 모든 Atlas Cloud 모델에 접근할 수 있습니다.
MCP Server
Atlas Cloud MCP Server는 Model Context Protocol을 통해 IDE와 300개 이상의 AI 모델을 연결합니다. MCP 호환 클라이언트에서 사용할 수 있습니다.
지원 클라이언트
설치
npx -y atlascloud-mcp설정
다음 설정을 IDE의 MCP 설정 파일에 추가하세요.
{
"mcpServers": {
"atlascloud": {
"command": "npx",
"args": [
"-y",
"atlascloud-mcp"
],
"env": {
"ATLASCLOUD_API_KEY": "your-api-key-here"
}
}
}
}사용 가능한 도구
API 스키마
스키마를 사용할 수 없음Wan 2.2 Turbo Infinite Image-to-Video — LoRA
Model Overview
| Field | Description |
|---|---|
| Model Name | atlascloud/wan-2.2-turbo/infinite-image-to-video-lora |
| Model Type | Advanced Image-to-Video Generation |
| Core Architecture | Mixture-of-Experts (MoE) |
| Active Parameters | 14B + LoRA adapter |
| Variant | LoRA |
The LoRA variant of Wan 2.2 Turbo Infinite Image-to-Video. Same Infinite segmented-prompt mechanic and acceleration stack as the base model, with LoRA-grade fidelity and motion stability for final renders. Built on the Wan 2.2 Mixture-of-Experts (MoE) foundation for unrestricted creative work.
Key Features & Innovations
1. Ultra-Fast Inference: 4-Step Distillation with RCM
- RCM (Refined Consistency Model) Sampler — efficient ODE solver that improves single-step sampling quality.
- 4-Step Distillation — denoising compressed to 4 steps, enabling cinematic-grade generation at low latency. LoRA inference is ~10–20 % slower than base but stays well within interactive territory.
2. Infinite-Length Generation: Anchor-Frame Autoregressive Architecture
- Anchor-Frame Evolution — automatically extracts key "anchor frames" during generation as global temporal references.
- Dual-Frame Constraint (Anchor + Last Frame) — combines global structural consistency with motion continuity to construct video sequences autoregressively.
- Semantic Stability — LoRA further sharpens identity and detail consistency across multi-minute outputs.
3. Cinematic-Level Aesthetics (Inherited + LoRA-Enhanced)
- Precise Control — detailed labels for lighting, composition, color tone.
- Complex Motion — fluid motion across diverse semantics.
- Fine-Grained Fidelity — LoRA adapter delivers sharper textures, more stable identities, and stylistic depth that the base variant cannot match on its own.
Why Infinite?
Output duration equals prompt_count × duration_per_segment, up to 6 prompts x 5 s. Direct each segment with its own prompt; the API returns one server-stitched 30 fps MP4.
| Prompts | Per-segment | Total output |
|---|---|---|
| 1 | 5 s | 5 s |
| 3 | 5 s | 15 s |
| 6 | 5 s | 30 s |
When to Pick the LoRA Variant
- Final renders, not drafts — the quality margin is worth the +30 % price.
- Subjects with fine identity details that must stay consistent across segments.
- Stylized motion or lighting that the base model under-delivers on.
For early iteration / bulk drafts, use the base:
atlascloud/wan-2.2-turbo/infinite-image-to-video (cheaper, faster).
60-second Quickstart
curl -X POST https://api.atlascloud.ai/api/v1/model/generateVideo \ -H "Authorization: Bearer $APIKEY" \ -H "Content-Type: application/json" \ -d '{ "model": "atlascloud/wan-2.2-turbo/infinite-image-to-video-lora", "image": "https://static.atlascloud.ai/media/images/db548fe3bd5cafa4ef7e0141d69c8566.jpeg", "prompt": [ "A classic golden Cadillac speeds through a desert, kicking up a massive cloud of dust behind it.", "Camera pans to the passenger firing an assault rifle at monstrous dinosaurs hot on the trail.", "The roaring creatures close in as the driver grips the wheel, knuckles white." ], "duration": 5, "resolution": "720p" }'
Returns one MP4 — segments are stitched server-side at 30 fps.
Request Fields
| Field | Type | Required | Notes |
|---|---|---|---|
model | string | ✅ | atlascloud/wan-2.2-turbo/infinite-image-to-video-lora |
image | string (URL) | ✅ | Source frame; jpg/png |
prompt | string[] | ✅ | Must be a JSON array. Plain string is rejected. |
duration | number | ✅ | Fixed at 5 s per segment. |
resolution | string | optional | 480p, 720p, or 1080p. Defaults to 720p. |
seed | number | optional | -1 for random |
Pricing — at a glance
price = $0.026 × max(1, prompt_count) × max(5, duration_seconds) × resolution_factor 480p → 1 720p → 2 1080p → 3
Common combos:
| Prompts | Duration | Resolution | Total |
|---|---|---|---|
| 1 | 5 s | 480 p | $0.13 |
| 1 | 5 s | 720 p | $0.26 |
| 1 | 5 s | 1080 p | $0.39 |
| 3 | 5 s | 720 p | $0.78 |
| 6 | 5 s | 720 p | $1.56 |
| 6 | 5 s | 1080 p | $2.34 |
Output Spec
- Format: MP4 (H.264)
- Frame rate: 30 fps (post-processed)
- Resolution: 480 p / 720 p / 1080 p tiers, aspect-ratio preserving
- Audio: none
Intended Use & Applications
- Final cinematic renders with cross-segment identity stability.
- High-fidelity advertising / pre-visualization that depend on stylistic consistency.
- Identity-critical I2V where minor drift would break the narrative.
Usage Guidelines
This model is tuned for adult-oriented, unrestricted creative generation. By calling it you confirm:
- All depicted subjects are 18 +.
- You hold the rights to the source image.
- You will not generate content depicting real, identifiable people without their explicit consent.
Violations may result in account suspension.
Limitations
promptmust be a JSON array, never a plain string.- LoRA reduces but does not eliminate cross-segment identity drift.
- LoRA generation is ~10–20 % slower per segment than base.
Related
- Base variant:
atlascloud/wan-2.2-turbo/infinite-image-to-video
Note: This model is designed to empower the creative community. Users are expected to follow AI ethical guidelines and copyright regulations.




