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
SHIP-BLOCKER: pin mlx==0.31.1 — 0.31.2 attenuates LTX 2.3 audio by 22 dB
mrbizarro202f3864c3ba
diff --git a/install.js b/install.jsindex 1819333..d7ed5a8 100644--- a/install.js+++ b/install.js@@ -107,11 +107,23 @@ module.exports = {// looks for video_vae.py.// Pin huggingface-hub>=1.0 explicitly so older Pinokio bundles still// get the v1+ `hf` CLI used by the download steps below.+ //+ // SHIP-BLOCKER: pin mlx==0.31.1 (NOT 0.31.2). LTX 2.3 audio regresses+ // by 22 dB on mlx 0.31.2 — output peaks at -37 dB instead of the+ // expected -9 to -15 dB. Verified empirically by downgrading mlx in a+ // working install and re-running the same prompt:+ // mlx 0.31.2 → max_volume -42.8 dB (broken)+ // mlx 0.31.1 → max_volume -9.2 dB (working)+ // Same packages, same weights, same seed; only mlx differs. Numerical+ // change in 0.31.2 attenuates the vocoder output.{method: "shell.run",params: {path: "ltx-2-mlx",message: [+ // Force the mlx pin BEFORE installing ltx-* packages so their deps+ // resolve to the pinned version instead of pulling latest 0.31.x.+ "uv pip install --python env/bin/python 'mlx==0.31.1' 'mlx-lm==0.31.1' 'mlx-metal==0.31.1'","uv pip install --python env/bin/python ./packages/ltx-core-mlx ./packages/ltx-pipelines-mlx","uv pip install --python env/bin/python pillow numpy 'huggingface-hub>=1.0'"]diff --git a/update.js b/update.jsindex 776fa15..cff5b07 100644--- a/update.js+++ b/update.js@@ -17,6 +17,18 @@ module.exports = {message: ["git fetch origin", "git checkout dcd639e"]}},+ // Force-downgrade mlx to 0.31.1 — fixes 22 dB audio regression on mlx+ // 0.31.2. Existing users who installed before this commit have mlx 0.31.2+ // and quiet audio; clicking Update reinstalls to the pinned version.+ // --force-reinstall + --no-deps so we change ONLY mlx without disturbing+ // ltx-* / transformers / etc. (some of which depend on mlx>=0.31.0).+ // See install.js for the full diagnostic note.+ {+ method: "shell.run",+ params: {+ message: "./ltx-2-mlx/env/bin/pip install --force-reinstall --no-deps 'mlx==0.31.1' 'mlx-lm==0.31.1' 'mlx-metal==0.31.1'"+ }+ },// Re-apply patches. Codec patch is required; I2V OOM patch is a no-op// on dcd639e (older I2V structure) and reports drift gracefully now.// Pin to the venv's python3.11 to match install.js — `python3` on