Skip to content

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.

Y1.038 docs: flag Extend's Q8 requirement in README Modes table

mrbizarro7c529564d422
diff --git a/README.md b/README.md
index daa3400..10330de 100644
--- a/README.md
+++ b/README.md
@@ -81,7 +81,7 @@ Four generation modes. All produce video + synced audio.
| **T2V** — text → video | prompt | The default. Type a scene, get 5 seconds with sound. |
| **I2V** — image → video | prompt + reference image | Animate a still. Auto cover-crop to model dimensions. |
| **FFLF** — first / last frame | prompt + start image + end image | Two images bookend the clip; the model fills the motion between. Requires Q8. |
-| **Extend** — continue a clip | existing mp4 + prompt | Append seconds onto a previous render. Audio continuous across the join. |
+| **Extend** — continue a clip | existing mp4 + prompt | Append seconds onto a previous render. Audio continuous across the join. Requires Q8. |
Plus a **Prompt Enhance** button that uses Gemma 3 12B (4-bit, locally)
to rewrite your prompt in the structure LTX 2.3 was trained on.
diff --git a/VERSION b/VERSION
index 0afc7c4..1882f7c 100644
--- a/VERSION
+++ b/VERSION
@@ -1 +1 @@
-Y1.037
+Y1.038