openmule

Generates images, videos, audio, speech, and music using MuleRouter or MuleRun multimodal APIs. Text-to-Image, Image-to-Image, Text-to-Video, Image-to-Video, Reference-to-Video, Video-to-Video, video editing (VACE, keyframe interpolation), Text-to-Speech, Text-to-Music. Use when the user wants to generate, edit, or transform images, videos, speech, or music using AI models like Wan2.6, Veo3, Nano Banana Pro, Midjourney, Kling V3, Kling V3 Omni, MiniMax Speech 2.8, MiniMax Music 2.5, ByteDance Seedance 2.0.