ltxvideo

A Collection of Google Colab Notebooks for various projects

AI rotoscoping and video matting in ComfyUI: click one person, get a native 4K alpha with hair-level edges. SAM3 picks the subject, LTX-2.5 alpha-gen draws the edge. 12 GB VRAM, EXR in/out, open weights.

Gradio UI for training video models using finetrainers

LTX 2.5 serverless worker template with i2v t2v workflows and bundled frontend.

LTX-2.3 is an open-source generative video architecture based on the Diffusion Transformer (DiT). The model delivers commercial-grade generation quality (on par with Google Veo 3) but without the strict limitations of closed ecosystems. The project supports both fully autonomous local inference and hybrid cloud processing.

A local music video pipeline for ComfyUI that any agent can drive: Flux 3 Klein stills and character sheets, LTX 2.3 video, MiniMax Music 3 songs, edit, grade and overlay, plus an MCP server.

LTXvideo text-to-video and image-to-video as a Space in Forge2

SOTA Text-to-Video Generator with MuseTalk 1.5, LivePortrait, and LTX-Video. Cinema-grade lip-sync and animation.

A ComfyUI implementation of LTX-2.5 DFR