🟢 Live
🤖 Model Selection
🎨 Generation Mode
💡 Want to transform an existing photo? Switch to Image to Image →
💬 Prompt
Quick Prompts
🌸 Cherry blossom garden 🌆 Cyberpunk cityscape at night 🐉 Majestic dragon in clouds 🌊 Ocean waves at golden hour 🚀 Space station orbiting Earth 🏯 Ancient Japanese castle in snow
Auto-Enhance Prompt
AI optimizes your prompt for better results
⚙️ Parameters
1:1 Square 16:9 Wide 9:16 Tall 4:3 Standard 3:4 Portrait Custom
Submitting task...
🖼️ Generated Image
Generated image
⬇️ Download
🎬 Video Model Selection
🎥 Generation Mode
💡 Want to animate a photo or transition between frames? Switch to First & Last Frame Mode →
💬 Video Prompt
Quick Prompts for Video
🏎️ Cyberpunk supercar drift in neon rain 🦅 Eagle soaring through misty mountain canyon 🌊 Bioluminescent ocean waves slow-motion ☕ Hot coffee poured into ceramic cup in rain 🚀 Starship launching into stormy nebula 🌸 Cherry petals swirling in gentle breeze 🤖 Futuristic robot walking lively neon street
Auto-Enhance Prompt
Automatically enriches prompt with cinematic camera and motion cues
⚙️ Video Parameters
16:9 Landscape (YouTube) 9:16 Portrait (TikTok/Shorts) 1:1 Square 4:3 Standard 3:4 Tall
🔊 Auto-Generate Audio / Sound FX
AI generates sound effects & background audio matching the prompt
Submitting video task...
🎥 Generated Video
⬇️ Download MP4
Recent Generations
✨

No generations yet.
Create your first image or video!

📡 REST API Reference

Base URL: http://localhost:3000  |  Auth: Authorization: Bearer <API_KEY> or device session token.

GET /api/models (?type=image|video)
Returns supported AI models and versions for image and video generation.
Loading...
POST /api/generate-video NEW · Video
Submit an AIGC video generation task using Tencent Cloud VOD CreateAigcVideoTask.
Text to Video Example:
{
  "modelName": "Kling",
  "modelVersion": "3.0",
  "prompt": "Cinematic drone shot flying through a glowing futuristic neon metropolis, rain reflections, 4k",
  "negativePrompt": "blurry, low resolution, jittery",
  "enhancePrompt": true,
  "aspectRatio": "16:9",
  "duration": 5,
  "resolution": "1080p",
  "audioGeneration": "Enabled",
  "storageMode": "Temporary"
}
First & Last Frame Mode Example:
{
  "modelName": "GV",
  "modelVersion": "3.1-fast",
  "prompt": "Smooth transition zooming into the mountains",
  "firstFrameUrl": "https://example.com/frame-start.jpg",
  "lastFrameUrl": "https://example.com/frame-end.jpg",
  "aspectRatio": "16:9",
  "duration": 5,
  "audioGeneration": "Enabled"
}
Reference Media Mode Example:
{
  "modelName": "Vidu",
  "modelVersion": "q3",
  "prompt": "Character walking forward with dynamic lighting",
  "referenceFiles": [
    { "type": "Url", "url": "https://example.com/character.jpg", "usage": "Reference" }
  ],
  "aspectRatio": "16:9",
  "duration": 5
}
Response:
{
  "taskId": "251007502-AigcVideo-25dacdcef7dd2b20fdt",
  "requestId": "d68920a4-c989-4afe-ac4d-2f06de99368e"
}
POST /api/generate Image
Submit an image generation task (Text-to-Image or Image-to-Image). Returns a taskId.
{
  "modelName": "GG",
  "modelVersion": "3.1",
  "prompt": "A serene mountain lake at sunset, photorealistic, 8K",
  "negativePrompt": "blurry, noise",
  "enhancePrompt": true,
  "aspectRatio": "16:9",
  "storageMode": "Temporary",
  "referenceImageUrl": "https://example.com/source.jpg",
  "seed": 42
}
Response:
{
  "taskId": "1436636252-AigcImage-xxxxx",
  "requestId": "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}
GET /api/task/:taskId
Poll task status and result for either image or video tasks.
Video task response (with Progress %):
{
  "Status": "FINISH",
  "TaskType": "AigcVideo",
  "AigcVideoTask": {
    "Status": "FINISH",
    "Progress": 100,
    "Output": {
      "FileInfos": [
        {
          "FileType": "mp4",
          "FileUrl": "https://...cdn.../video.mp4",
          "StorageMode": "Temporary"
        }
      ]
    }
  }
}
GET /api/tasks (?type=image|video&limit=20)
List recent generation tasks. Use ?type=video to query video tasks or ?type=image for image tasks.
🛠️ cURL Examples
1. Video Generation (Text to Video):
curl -X POST http://localhost:3000/api/generate-video \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "modelName": "Kling",
    "modelVersion": "3.0",
    "prompt": "Cinematic slow-motion shot of a cybernetic tiger walking through rain, neon lights, 4k",
    "aspectRatio": "16:9",
    "duration": 5,
    "resolution": "1080p",
    "audioGeneration": "Enabled"
  }'
2. Video Generation (First & Last Frame):
curl -X POST http://localhost:3000/api/generate-video \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "modelName": "GV",
    "modelVersion": "3.1-fast",
    "prompt": "Smooth flight forward over the alpine lake",
    "firstFrameUrl": "https://images.unsplash.com/photo-1506744038136-46273834b3fb",
    "aspectRatio": "16:9",
    "duration": 5
  }'
3. Image Generation:
curl -X POST http://localhost:3000/api/generate \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "modelName": "GG",
    "modelVersion": "3.1",
    "prompt": "A serene mountain lake at sunset, photorealistic, 8K",
    "aspectRatio": "16:9",
    "enhancePrompt": true
  }'
🎬 Supported Video Models (CreateAigcVideoTask)
🖼️ Supported Image Models (CreateAigcImageTask)