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
feat(helper): plumb video_skip_step + audio_skip_step into HQ pipe
mrbizarroda87af122cb9
diff --git a/mlx_warm_helper.py b/mlx_warm_helper.pyindex 6874e83..3a21793 100644--- a/mlx_warm_helper.py+++ b/mlx_warm_helper.py@@ -1591,6 +1591,11 @@ for line in sys.__stdin__:# the cap IS the iteration count (not just a safety bound).# Each iter is pure latent algebra — no model forwards.bongmath_max_iter=int(p.get("bongmath_max_iter", 100)),+ # Upstream HQ exposes skip_step for each modality. The MLX+ # res_2s path now honors it as an opt-in experimental speed+ # knob; 0 preserves the locked recipe.+ video_skip_step=int(p.get("video_skip_step", 0)),+ audio_skip_step=int(p.get("audio_skip_step", 0)),# Stage-2 image-conditioning mode for I2V (HQ).# "full" = re-encode reference at full res (upstream default)# "off" = skip the full-res re-encode; saves the biggest