alibaba/wan-2.2/animate-mix

image-to-video

The Wan video character swap model replaces the main character in a video with a character from an image. This model preserves the scene, lighting, and tone of the original video to ensure a seamless result.

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 0.126 per run. For $10 you can run this model approximately 79 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": "alibaba/wan-2.2/animate-mix",
    "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": "alibaba/wan-2.2/animate-mix",
    "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": "alibaba/wan-2.2/animate-mix"
}

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.

Alibaba Wan 2.2 Animate Mix

An advanced, unified character animation and replacement model that transfers motion, expressions, and timing from a source clip while preserving the identity of a target character from a single reference image. Animate Mix is part of the Wan 2.2 Animate family and focuses on blending the target identity with source motion for coherent, high-quality video generation.

Overview

Purpose: Motion transfer and identity preservation from one image to a full video
Core capability: Mix mode fuses target appearance with source motion dynamics
Foundation: Built atop Wan2.2 innovations (e.g., MoE-driven diffusion, improved data, high-compression video)
Typical output: Smooth 24 fps video at up to 720p with holistic movement and expression replication
Use cases: Character animation, avatar replacement, lip-sync, dynamic explainer clips, social content

Key Features

One-image-to-video: Animate a character from a single, high-quality portrait or full-body image
Motion mix-in: Transfer pose, body motion, facial expressions, and timing from a source video
Identity retention: Preserve clothing, face, and hair of the target character while adopting motion
Holistic dynamics: Handles subtle micro-expressions, head motion, and body kinematics
Robustness: Works across varied camera motions and moderate occlusions with careful input selection
Motion + Identity Transfer: Applies actions and facial expressions from a reference video while preserving the target character’s face, hair, and clothing.
Dual Modes:
- Standard Mode (wan-std): Optimized for speed and cost; ideal for previews and basic outputs.
- Professional Mode (wan-pro): Smoother motion and higher fidelity for production use (higher time/cost).
Flexible Input Support: Handles wide image/video resolutions and aspect ratios for diverse pipelines.
Long Duration: Supports reference videos from 2 to 30 seconds.
Holistic Dynamics: Captures pose, micro‑expressions, head motion, and timing for coherent results.

Designed For

Content Creators: Identity-preserving avatar animation for social content.
Game Developers: Rapid prototyping of character motion with reference clips.
Marketing & Advertising: Transform static assets into dynamic character videos.
Animation Enthusiasts: Experiment with motion transfer and identity mixing.

Input Requirements

To achieve the best results, follow these guidelines:

Character Image

Content: One person, facing the camera, face fully visible and unobstructed; the subject should occupy a moderate portion of the frame.
Format: JPG, JPEG, PNG, BMP, WEBP.
Dimensions: Width and height between 200 and 4096 pixels.
Aspect Ratio: Between 1:3 and 3:1.
File Size: Max 5 MB.

Reference Video (Motion Source)

Content: One person with clearly visible face; stable framing improves motion transfer.
Format: MP4, AVI, MOV.
Duration: 2 to 30 seconds.
Dimensions: Width and height between 200 and 2048 pixels.
Aspect Ratio: Between 1:3 and 3:1.
File Size: Max 200 MB.
Recommendation: Higher resolution and frame rate yield better identity preservation and smoother motion.

Pricing

Billing is based on generated video duration and selected mode.

Billing Logic: Cost scales with video duration.
Mode Multiplier:
- Standard Mode: 1.0x base rate.
- Professional Mode: 1.5x base rate.
Service transitions to paid billing once the free quota is used; set up a payment method early to avoid interruptions.

How to Use

Upload Character Image: Provide a clear identity reference for the target character.
Upload Reference Video: Select a clip containing the desired motion and expressions.
Select Mode: Choose "Standard" (wan‑std) for speed or "Professional" (wan‑pro) for quality.
Generate: Submit to produce the identity‑preserving animated video.

Best Practices

Use high‑resolution, well‑lit images; avoid occlusions and heavy motion blur.
Choose a motion source with matching vibe (tempo, style, emotion) to your target.
Keep backgrounds simple to reduce artifacts and improve identity retention.
Prefer moderate motion complexity; extreme spins or strong occlusions may degrade quality.

Limitations

Identity drift may occur with occlusions, extreme camera motion, or low‑quality inputs.
Fast‑moving props or complex interactions can introduce artifacts and temporal instability.
Lip‑sync quality depends on clarity of the source clip and face visibility in the reference image.

Safety and Content

Respect privacy and consent when using identity transfer.
Follow platform policies and local regulations.
Avoid generating harmful or restricted content.

Version

Model: Alibaba Wan 2.2 Animate Mix
Family: Wan2.2 Animate (Move/Mix)
Technical context: Wan 2.2 with MoE‑driven video diffusion and improved training data