IMA Studio
All-in-One AI Creation Skill
One Skill to unlock every top AI model. Images, videos, music, speech — unified entry, instant creation.
All Models at a Glance
🎨 Image Models
| Model | Feature | Resolution | Credits |
|---|---|---|---|
| SeeDream 4.5 ⭐ | Photorealistic, 8 aspect ratios | Up to 4K | 5 pts |
| Midjourney 🔥 | Strong artistic / illustration style | 1024×1024 | 8-10 pts |
| Nano Banana Pro | High quality, 5 aspect ratios | 1K / 2K / 4K | 10-18 pts |
| Nano Banana 2 | Fastest & cheapest | 512px ~ 4K | 4-13 pts |
🎬 Video Models
| Model | Feature | Tag |
|---|---|---|
| IMA Video Pro | IMA native quality model (Seedance 2.0) | 🆕 NEW |
| IMA Video Pro Fast | IMA native low-latency model (Seedance 2.0 Fast) | 🆕 NEW |
| Wan 2.6 | Best value, 720p/1080p, 5-15s | ⭐ |
| Google Veo 3.1 | Google flagship video model | 🔥 |
| Sora 2 Pro | OpenAI flagship video model | 🔥 |
| Kling O1 | Kuaishou high-quality video | |
| Kling 2.6 | Kuaishou latest version | 🆕 NEW |
| Hailuo 2.3 | MiniMax latest | 🆕 NEW |
| Hailuo 2.0 | MiniMax stable | |
| Pixverse | Stylized effects |
🎵 Music Models
| Model | Feature | Use Case |
|---|---|---|
| Suno sonic v5 | Full composing, lyrics + vocals | Songs, BGM, soundtracks |
| DouBao BGM | Pure background music | Video scoring, ambient |
| DouBao Song | Songs with vocals | Song creation |
🗣️ Speech Model
8 Creative Modes
Text to Image
Text prompt → Image
Image to Image
Reference + text → New image
Text to Video
Text prompt → Video
Image to Video
First frame → Animated video
First-Last Frame
Start + end → Transition video
Reference Video
Keep character/style consistency
Text to Music
Description → BGM/Song
Text to Speech
Text → Natural voice
Why IMA Skill
🎯Unified Entry
One Skill covers image/video/music/speech. No more juggling multiple tools.
🧠Smart Model Selection
Built-in knowledge base recommends the best model, remembers your preferences.
🔄Auto Retry & Fallback
3 automatic retries on API errors, auto-downgrades resolution (4K→2K→1K).
🎬Cross-Media Workflow
One prompt for the full pipeline: character → video → music → narration, fully orchestrated.
👤Character Consistency
Keep the same character across multiple images and video shots with reference mode.
🔐Secure & Transparent
API Key for auth only, no content stored. Logs auto-cleaned after 7 days.
Get Started
Two commands to unlock all AI creative powers
Run in your OpenClaw terminal
# Install knowledge base (recommended) git clone https://github.com/imastuido/ima-knowledge-ai.git # Install IMA all-in-one skill git clone https://github.com/imastuido/ima-all-ai.git