Free, open-source AI video generator for Mac. Run LTX-2.5 and MiniMax H3 (Hailuo) locally on Apple Silicon: text-to-video and image-to-video with sound, lip-sync, character LoRA training, songs from lyrics (YuE2) and image editing (Qwen-Image-Edit). One-click install via Pinokio. Offline: no cloud, no API key, no NVIDIA GPU.
Python ai-filmmakingai-videoai-video-generatorapple-siliconhailuoimage-to-videolip-synclocal-ailora-trainingltx-2ltx-2-5ltx-videomacosminimax-h3mlxmusic-generationoffline-aipinokiotext-to-videovideo-generation
"""The panel's HTTP route handlers, one module per URL-prefix family.
Slice 4 of the restructuring (docs/ARCHITECTURE.md): the 101-route
if/elif chains in mlx_ltx_panel.py's do_GET/do_POST move here, a prefix
family at a time, registered in panel.routes' tables. The legacy chain
keeps serving whatever has not moved yet — dispatch tries the table
first and falls through.
Route modules never `import mlx_ltx_panel` (the panel usually runs as
__main__, and importing it by name would execute the whole 32k-line
module a second time — port bind, threads, everything). Instead each
module declares `P = None` and mlx_ltx_panel assigns the RUNNING module
object into it at import-wiring time, before the server starts.
"""