Ltx2

Wraps the LTX-2.3 22B model for generating 5-second video clips from text or animating still images. Runs on Modal with A100-80GB GPUs. You get text-to-video for b-roll and backgrounds, image-to-video for bringing stills to life, and a CRT terminal style LoRA preset for retro pixel art aesthetics. The docs are detailed about frame counts, resolutions, and prompting patterns. It's positioned as a SadTalker alternative for stylized or non-photoreal characters where you need atmospheric motion more than precise lip sync. Quality presets let you trade speed for fidelity. Good for stitching AI-generated clips into Remotion compositions or upscaling workflows.

skills.sh installs: 1.1K
GitHub stars: 2.5K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add digitalsamba/claude-code-video-toolkit --skill ltx2 --agent claude-code

Installs into .claude/skills of the current project.

Files

LTX-2.3 Video Generation

Generate ~5 second video clips from text prompts or images using the LTX-2.3 22B DiT model. Runs on Modal (A100-80GB). Requires MODAL_LTX2_ENDPOINT_URL in .env. LTX-2.5 is a deploy-time opt-in on the same endpoint; see LTX-2.5 (opt-in).

Quick Reference

# Text-to-video
uv run tools/ltx2.py --prompt "A sunset over the ocean, golden light on waves, cinematic" --output sunset.mp4

# Image-to-video (animate a still image)
uv run tools/ltx2.py --prompt "Gentle camera drift, soft ambient motion" --input photo.jpg --output animated.mp4

# Custom resolution and duration
uv run tools/ltx2.py --prompt "..." --width 1024 --height 576 --num-frames 161 --output wide.mp4

# Fast mode (fewer steps, quicker)
uv run tools/ltx2.py --prompt "..." --quality fast --output quick.mp4

# Reproducible output
uv run tools/ltx2.py --prompt "..." --seed 42 --output reproducible.mp4