Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add sandyup/comfyui-mcp --skill ltxv2-videogit clone --depth 1 https://github.com/sandyup/comfyui-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/sandyup/comfyui-mcp/ltxv2-video)<a href="https://agentmods.dev/skills/sandyup/comfyui-mcp/ltxv2-video"><img src="https://agentmods.dev/badge/skills/sandyup/comfyui-mcp/ltxv2-video.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00065 | $0.11049 |
| Opus 5 | $0.00032 | $0.05525 |
| Sonnet 5 | $0.00013 | $0.02210 |
| Haiku 4.5 | $0.00006 | $0.01105 |
Grade A, and why
ltxv2-video scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
88% identical to ltxv2-video — 211 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 596 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LTX-2 / LTX-2.3 Video Workflows
Version naming (read this first)
There is no "LTX 3.2" or "LTX2.3" as separate products — the user's shorthand refers to Lightricks LTX-2.3, a point release of the LTX-2 family. The lineage is:
- LTX-Video (2024) — first text-to-video model from Lightricks.
- LTX-2 / LTX-V2 (Oct 2025) — 19B-class DiT audio-video foundation model. Bundled checkpoint
ltx-2-19b-distilled.safetensors, Gemma 3 12B text encoder. - LTX-2.3 (released ~March 2026) — 22B-parameter DiT update. Rebuilt VAE (sharper textures/faces/hair/text), ~4x larger text connector (text projection) for prompt adherence, native 9:16 portrait, LoRA support, HiFi-GAN vocoder for cleaner synchronized audio, up to 4K@50fps / ~20s clips. Apache 2.0. Distributed primarily as GGUF UNets (community quants) plus separate VAE / text-encoder / text-projection files — NOT a single bundled checkpoint like LTX-2.
When the user says "LTX3.2" / "LTX2.3", treat it as LTX-2.3. This skill covers both LTX-2 (bundled checkpoint path) and LTX-2.3 (GGUF UNet path).
⭐ Render-verified correct setup (read this FIRST — 2026-06-19)
The GGUF-UNet +
DualCLIPLoader+gemma_3_12B_it_fp4_mixedpath documented later in this skill (the Aitrepreneur installer path) produces soft/mushy video with inaccurate faces and eyes. It runs, but it is NOT the quality path. The setup below is the official Comfy-Org template, render-proven sharp (1280×704, accurate faces, synchronized 48 kHz stereo audio).
Models (exact, render-verified)
| Component | File | Source repo | Folder | Notes |
|---|---|---|---|---|
| Checkpoint | ltx-2.3-22b-dev.safetensors (46 GB, max quality) or ltx-2.3-22b-dev-fp8.safetensors (~23 GB, official VRAM-friendly) |
Lightricks/LTX-2.3 / Lightricks/LTX-2.3-fp8 |
checkpoints/ (NOT unet/) |
The checkpoint carries the transformer and the audio VAE. Loaded by CheckpointLoaderSimple + reused by LTXVAudioVAELoader + LTXAVTextEncoderLoader. |
| Gemma text encoder | gemma_3_12B_it_fp8_scaled.safetensors (13 GB) |
Comfy-Org/ltx-2 → split_files/text_encoders/ |
text_encoders/ |
Use fp8_scaled (unpacked). The Aitrepreneur fp4_mixed mirror file is truncated (5.3 GB vs 9.4 GB) AND a packed-fp4 layout core can't reshape → shape [15360,1920] invalid for input 27582328. |
| Distilled speed LoRA | ltx_2.3_22b_distilled_1.1_lora_dynamic_fro09_avg_rank_111_bf16.safetensors @ 0.5 |
Comfy-Org/ltx-2.3 → split_files/loras/ |
loras/ |
The newer dynamic rank-111 distilled LoRA — NOT the older ...384-1.1. |
| Gemma abliterated LoRA ⭐ | gemma-3-12b-it-abliterated_lora_rank64_bf16.safetensors @ 1.0 |
Comfy-Org/ltx-2 → split_files/loras/ |
loras/ |
Applied to the text-encoder CLIP via a LoraLoader. This is the prompt-accuracy / correct-eyes fix. Missing this = subtly-wrong faces. |
| Spatial upscaler | ltx-2.3-spatial-upscaler-x2-1.1.safetensors |
Lightricks/LTX-2.3 |
latent_upscale_models/ |
Used by the stage-2 LTXVLatentUpsampler. Use x2-1.1, not x2-1.0. |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 596 lines · 65 tokens per session scan A dcfa99c149d8
ltxv2-video is a skill published in the GitHub repository sandyup/comfyui-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 65 tokens to every session and 11,049 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to ltxv2-video, differing in 211 lines, and is treated as a copy.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.