Inicio
Explorar
atlascloud/wan-2.2-turbo/infinite-image-to-video-lora
Wan 2.2 Turbo Infinite Image-to-Video LoRA
Imagen a Video
TURBO

Wan 2.2 Turbo Infinite Image-to-Video LoRA API by Atlas Cloud

atlascloud/wan-2.2-turbo/infinite-image-to-video-lora
Infinite-image-to-video-lora

Image-to-video LoRA variant for segmented prompt video generation with stable motion and 30fps workflow post-processing.

Entrada

Cargando configuración de parámetros...

Salida

Inactivo
Los videos generados se mostrarán aquí
Configura los parámetros y haz clic en ejecutar para comenzar a generar

Cada ejecución costará $0.026. Con $10 puedes ejecutar aproximadamente 384 veces.

Puedes continuar con:

Parámetros

Ejemplo de código

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()

Instalar

Instala el paquete necesario para tu lenguaje de programación.

bash
pip install requests

Autenticación

Todas las solicitudes de API requieren autenticación mediante una clave de API. Puedes obtener tu clave de API desde el panel de Atlas Cloud.

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

Encabezados HTTP

python
import os

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

Nunca expongas tu clave de API en código del lado del cliente ni en repositorios públicos. Usa variables de entorno o un proxy de backend en su lugar.

Enviar una solicitud

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())

Enviar una solicitud

Envía una solicitud de generación asíncrona. La API devuelve un ID de predicción que puedes usar para verificar el estado y obtener el resultado.

POST/api/v1/model/generateVideo

Cuerpo de la solicitud

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']}")

Respuesta

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

Verificar estado

Consulta el endpoint de predicción para verificar el estado actual de tu solicitud.

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

Ejemplo de 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)

Valores de estado

processingLa solicitud aún se está procesando.
completedLa generación está completa. Las salidas están disponibles.
succeededLa generación fue exitosa. Las salidas están disponibles.
failedLa generación falló. Verifica el campo de error.

Respuesta completada

{
  "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"
  }
}

Subir archivos

Sube archivos al almacenamiento de Atlas Cloud y obtén una URL que puedes usar en tus solicitudes de API. Usa multipart/form-data para subir.

POST/api/v1/model/uploadMedia

Ejemplo de carga

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}")

Respuesta

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

Schema de entrada

Los siguientes parámetros se aceptan en el cuerpo de la solicitud.

Total: 0Obligatorio: 0Opcional: 0

No hay parámetros disponibles.

Ejemplo de cuerpo de solicitud

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

Schema de salida

La API devuelve una respuesta de predicción con las URL de salida generadas.

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

Ejemplo de respuesta

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 más de 300 modelos de IA directamente en tu asistente de codificación con IA. Un solo comando para instalar y luego usa lenguaje natural para generar imágenes, videos y chatear con LLM.

Clientes compatibles

Claude Code
OpenAI Codex
Gemini CLI
Cursor
Windsurf
VS Code
Trae
GitHub Copilot
Cline
Roo Code
Amp
Goose
Replit
40+ clientes compatibles

Instalar

bash
npx skills add AtlasCloudAI/atlas-cloud-skills

Configurar clave de API

Obtén tu clave de API desde el panel de Atlas Cloud y configúrala como variable de entorno.

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

Funcionalidades

Una vez instalado, puedes usar lenguaje natural en tu asistente de IA para acceder a todos los modelos de Atlas Cloud.

Generación de imágenesGenera imágenes con modelos como Nano Banana 2, Z-Image y más.
Creación de videosCrea videos a partir de texto o imágenes con Kling, Vidu, Veo, etc.
Chat con LLMChatea con Qwen, DeepSeek y otros modelos de lenguaje de gran escala.
Carga de mediosSube archivos locales para flujos de trabajo de edición de imágenes e imagen a video.

MCP Server

Atlas Cloud MCP Server conecta tu IDE con más de 300 modelos de IA a través del Model Context Protocol. Funciona con cualquier cliente compatible con MCP.

Clientes compatibles

Cursor
VS Code
Windsurf
Claude Code
OpenAI Codex
Gemini CLI
Cline
Roo Code
100+ clientes compatibles

Instalar

bash
npx -y atlascloud-mcp

Configuración

Agrega la siguiente configuración al archivo de configuración de MCP de tu IDE.

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

Herramientas disponibles

atlas_generate_imageGenera imágenes a partir de indicaciones de texto.
atlas_generate_videoCrea videos a partir de texto o imágenes.
atlas_chatChatea con modelos de lenguaje de gran escala.
atlas_list_modelsExplora más de 300 modelos de IA disponibles.
atlas_quick_generateCreación de contenido en un solo paso con selección automática de modelo.
atlas_upload_mediaSube archivos locales para flujos de trabajo de API.

API Schema

Schema no disponible

Por favor inicia sesión para ver el historial de solicitudes

Necesitas iniciar sesión para acceder al historial de solicitudes del modelo.

Iniciar Sesión

Wan 2.2 Turbo Infinite Image-to-Video — LoRA

Model Overview

FieldDescription
Model Nameatlascloud/wan-2.2-turbo/infinite-image-to-video-lora
Model TypeAdvanced Image-to-Video Generation
Core ArchitectureMixture-of-Experts (MoE)
Active Parameters14B + LoRA adapter
VariantLoRA

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.

PromptsPer-segmentTotal output
15 s5 s
35 s15 s
65 s30 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

FieldTypeRequiredNotes
modelstringatlascloud/wan-2.2-turbo/infinite-image-to-video-lora
imagestring (URL)Source frame; jpg/png
promptstring[]Must be a JSON array. Plain string is rejected.
durationnumberFixed at 5 s per segment.
resolutionstringoptional480p, 720p, or 1080p. Defaults to 720p.
seednumberoptional-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:

PromptsDurationResolutionTotal
15 s480 p$0.13
15 s720 p$0.26
15 s1080 p$0.39
35 s720 p$0.78
65 s720 p$1.56
65 s1080 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

  • prompt must 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.

  • 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.

Más de 300 Modelos, Comienza Ahora,

Explorar Todos los Modelos

Join our Discord community

Join the Discord community for the latest model updates, prompts, and support.