atlascloud/wan-2.2/image-to-video-lora

image-to-video

Open and Advanced Large-Scale Video Generative Models.

INPUT

Loading parameter configuration...

OUTPUT

Idle

Your generated videos will appear here

Configure your settings and click Run to get started

Your request will cost 0.04 per run. For $10 you can run this model approximately 250 times.

Here's what you can do next:

Video Upscaler Video extend

Parametri

Esempio di codice
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/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()

Installa

Installa il pacchetto richiesto per il tuo linguaggio.

bash

pip install requests

Autenticazione

Tutte le richieste API richiedono l'autenticazione tramite una chiave API. Puoi ottenere la tua chiave API dalla dashboard di Atlas Cloud.

bash

export ATLASCLOUD_API_KEY="your-api-key-here"

Header HTTP

python

import os

API_KEY = os.environ.get("ATLASCLOUD_API_KEY")
headers = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {API_KEY}"
}

Proteggi la tua chiave API

Non esporre mai la tua chiave API nel codice lato client o nei repository pubblici. Utilizza invece variabili d'ambiente o un proxy backend.

Invia una richiesta

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())

Invia una richiesta

Invia una richiesta di generazione asincrona. L'API restituisce un ID di previsione che puoi usare per controllare lo stato e recuperare il risultato.

POST/api/v1/model/generateVideo

Corpo della richiesta

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/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']}")

Risposta

{
  "id": "pred_abc123",
  "status": "processing",
  "model": "model-name",
  "created_at": "2025-01-01T00:00:00Z"
}

Controlla lo stato

Interroga l'endpoint di previsione per verificare lo stato attuale della tua richiesta.

GET/api/v1/model/prediction/{prediction_id}

Esempio di 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)

Valori di stato

processingLa richiesta è ancora in fase di elaborazione.

completedLa generazione è completata. I risultati sono disponibili.

succeededLa generazione è riuscita. I risultati sono disponibili.

failedLa generazione è fallita. Controlla il campo errore.

Risposta completata

{
  "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"
  }
}

Carica file

Carica file nello storage Atlas Cloud e ottieni un URL utilizzabile nelle tue richieste API. Usa multipart/form-data per il caricamento.

POST/api/v1/model/uploadMedia

Esempio di caricamento

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}")

Risposta

{
  "data": {
    "download_url": "https://storage.atlascloud.ai/uploads/abc123/image.png",
    "file_name": "image.png",
    "content_type": "image/png",
    "size": 1024000
  }
}

Schema di input

I seguenti parametri sono accettati nel corpo della richiesta.

Totale: 0Obbligatorio: 0Opzionale: 0

Nessun parametro disponibile.

Esempio di corpo della richiesta

json

{
  "model": "atlascloud/wan-2.2/image-to-video-lora"
}

Schema di output

L'API restituisce una risposta di previsione con gli URL degli output generati.

idstringrequired

Unique identifier for the prediction.

statusstringrequired

Current status of the prediction.

processingcompletedsucceededfailed

modelstringrequired

The model used for generation.

outputsarray[string]

Array of output URLs. Available when status is "completed".

errorstring

Error message if status is "failed".

metricsobject

Performance metrics.

predict_timenumber

Time taken for video generation in seconds.

created_atstringrequired

ISO 8601 timestamp when the prediction was created.

Format: date-time

completed_atstring

ISO 8601 timestamp when the prediction was completed.

Format: date-time

Esempio di risposta

json

{
  "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 oltre 300 modelli di IA direttamente nel tuo assistente di codifica IA. Un comando per installare, poi usa il linguaggio naturale per generare immagini, video e chattare con LLM.

Client supportati

Claude Code

OpenAI Codex

Gemini CLI

Cursor

Windsurf

VS Code

Trae

GitHub Copilot

Cline

Roo Code

Amp

Goose

Replit

40+ client supportati

Installa

bash

npx skills add AtlasCloudAI/atlas-cloud-skills

Configura chiave API

Ottieni la tua chiave API dalla dashboard di Atlas Cloud e impostala come variabile d'ambiente.

bash

export ATLASCLOUD_API_KEY="your-api-key-here"

Funzionalità

Una volta installato, puoi usare il linguaggio naturale nel tuo assistente IA per accedere a tutti i modelli Atlas Cloud.

Generazione di immaginiGenera immagini con modelli come Nano Banana 2, Z-Image e altri.

Creazione di videoCrea video da testo o immagini con Kling, Vidu, Veo, ecc.

Chat LLMChatta con Qwen, DeepSeek e altri grandi modelli linguistici.

Caricamento mediaCarica file locali per la modifica di immagini e flussi di lavoro da immagine a video.

Scopri di più

github.com/AtlasCloudAI/atlas-cloud-skills

Server MCP

Il server MCP di Atlas Cloud collega il tuo IDE con oltre 300 modelli di IA tramite il Model Context Protocol. Funziona con qualsiasi client compatibile MCP.

Client supportati

Cursor

VS Code

Windsurf

Claude Code

OpenAI Codex

Gemini CLI

Cline

Roo Code

100+ client supportati

Installa

bash

npx -y atlascloud-mcp

Configurazione

Aggiungi la seguente configurazione al file delle impostazioni MCP del tuo IDE.

json

{
  "mcpServers": {
    "atlascloud": {
      "command": "npx",
      "args": [
        "-y",
        "atlascloud-mcp"
      ],
      "env": {
        "ATLASCLOUD_API_KEY": "your-api-key-here"
      }
    }
  }
}

Strumenti disponibili

atlas_generate_imageGenera immagini da prompt testuali.

atlas_generate_videoCrea video da testo o immagini.

atlas_chatChatta con grandi modelli linguistici.

atlas_list_modelsEsplora oltre 300 modelli di IA disponibili.

atlas_quick_generateCreazione di contenuti in un solo passaggio con selezione automatica del modello.

atlas_upload_mediaCarica file locali per i flussi di lavoro API.

Scopri di più

github.com/AtlasCloudAI/mcp-server

API Schema

Schema not available

Please log in to view request history

You need to be logged in to access your model request history.

Wan 2.2: Open and Advanced Large-Scale Video Generative Model by Alibaba Wanxiang

Model Card Overview

Field	Description
Model Name	Wan 2.2 Image-to-Video LoRA
Developed by	Alibaba Tongyi Wanxiang Lab
Model Type	Image-to-Video Generation with LoRA Support
Resolution	480p, 720p (via VSR upscaling)
Frame Rate	30 fps
Duration	3–10 seconds
Related Links	GitHub: https://github.com/Wan-Video/Wan2.2, Hugging Face: https://huggingface.co/Wan-AI/Wan2.2-I2V-A14B, Paper (arXiv): https://arxiv.org/abs/2503.20314

Introduction

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. This image-to-video LoRA variant takes a reference image as the first frame and generates a high-quality video, with full support for custom LoRA weights to fine-tune the generation style, motion characteristics, or subject identity.

The model generates videos at 480p natively and supports 720p output via Video Super Resolution (VSR) upscaling, delivering smooth 30 fps playback at both resolutions.

Key Features & Innovations

Effective MoE Architecture: Wan 2.2 integrates a Mixture-of-Experts (MoE) architecture into the video diffusion model. Specialized expert models handle different stages of the denoising process, increasing model capacity without raising computational costs. The model has 27B total parameters with only 14B active during any given step.
Cinematic-Level Aesthetics: Trained on a meticulously curated dataset with detailed labels for cinematic properties like lighting, composition, and color tone. This allows generation of videos with precise and controllable artistic styles, achieving a professional, cinematic look.
Complex Motion Generation: Trained on a vastly expanded dataset (+65.6% more images and +83.2% more videos compared to Wan 2.1), Wan 2.2 demonstrates superior ability to generate complex and realistic motion with enhanced generalization across motions, semantics, and aesthetics.
Custom LoRA Support: This variant supports user-provided LoRA weights for fine-grained style and motion control. Three separate LoRA input channels are available:
- high_noise_loras — Applied to the high-noise expert (transformer stage), influencing overall structure and layout.
- low_noise_loras — Applied to the low-noise expert (transformer_2 stage), influencing fine details and textures.
- loras — General-purpose LoRA input where the module is auto-inferred from the safetensors filename.
VSR-Enhanced Output: All output videos are delivered at 30 fps. When 720p resolution is selected, the model leverages Video Super Resolution to upscale from a 480p base generation, preserving fine details while achieving higher resolution output.

Model Architecture

The architecture is built upon the Diffusion Transformer (DiT) paradigm with a Mixture-of-Experts (MoE) framework:

High-Noise Expert: Activated during initial denoising stages, establishing overall structure and layout.
Low-Noise Expert: Activated in later stages, refining details, textures, and fine-grained motion.

The transition between experts is dynamically determined by the signal-to-noise ratio (SNR) during generation. Custom LoRA weights can be applied to each expert independently, enabling precise control over different aspects of the generation pipeline.

Intended Use & Applications

Stylized Video Production: Generating videos with custom visual styles by applying LoRA weights trained on specific aesthetic data.
Character & Subject Consistency: Using identity-preserving LoRAs to maintain consistent characters across multiple video generations.
Cinematic Video Production: Generating high-fidelity video clips from reference images for short films, advertisements, or social media content.
Creative Experimentation: Combining multiple LoRAs to explore novel visual effects and motion styles.
Academic Research: Serving as a powerful foundation model for researchers exploring LoRA-based fine-tuning techniques in video generation.