Models
MuAPI provides access to 100+ state-of-the-art generative AI models across image, video, audio, and enhancement categories — all through a single unified API.
Image Generation
| Model | Description |
|---|---|
flux-dev | High-quality text-to-image, great for creative work |
flux-schnell | Fast FLUX variant for rapid iteration |
flux-kontext-dev / flux-kontext-pro / flux-kontext-max | Contextual image editing and generation |
hidream-fast / hidream-dev / hidream-full | HiDream image generation tiers |
midjourney | Midjourney v7 via API |
gpt4o | OpenAI GPT-4o image generation |
seedream | Seedream image model |
reve | Reve image generation |
qwen | Qwen image generation |
Text-to-Video
| Model | Description |
|---|---|
veo3 / veo3-fast | Google Veo 3 — photorealistic video |
kling-master | Kling Master — cinematic quality |
wan2.1 / wan2.2 | Wan video generation |
seedance-pro / seedance-lite | Seedance video models |
hunyuan | Hunyuan video |
runway | Runway Gen video |
pixverse | PixVerse video |
vidu | Vidu video |
minimax-hailuo-02-std / minimax-hailuo-02-pro | MiniMax Hailuo video |
Image-to-Video
All major T2V models also support image-to-video input. Additional I2V-specific models:
kling-std/kling-pro/kling-masterseedance(reference-based withomni_referencemode)midjourney(video from image)
Audio
| Model | Description |
|---|---|
suno-create / suno-remix / suno-extend | Suno V5 music generation |
mmaudio-t2a | Text-to-audio |
mmaudio-v2v | Video-to-audio |
Image Enhancement
- Upscale, background removal, face swap, skin enhancement
- Colorization, Ghibli/anime style transfer
- Outpainting, product shots, object erasure
Video Editing
- Effects, lipsync, dance, dress change, face swap
- Luma modify/reframe, WAN effects
Explore Models
Browse all available models interactively in the Playground.