
benjiyaya/ltx-2.5-agent-prompt-skill
Developer toolsこのページは AI により自動翻訳されています。技術的な詳細は原文をご確認ください。 原文を見る
A Hermes Agent skill that transforms rough video ideas + reference images/audio into production-grade (Lightricks) video generation prompts.
概要
A Hermes Agent skill that transforms rough video ideas + reference images/audio into production-grade (Lightricks) video generation prompts. Unlike structured-format skills (e.g., MiniMax H3), LTX 2.5 prompting is — one flowing cinematic paragraph that reads like a shot description for a cinematographer. No JSON, no field labels, no tags. Just prose. When you describe a video concept (with or without attached media), this skill: 1. — single-shot, multishot (NEW in 2.5), or screenplay-style 2. your idea across 6 cinematic dimensions 3. — ready to paste into ComfyUI or LTX Studio ⭐ Previous versions only produced a single continuous shot. Now you can generate 2–4 connected shots — holding character identity, environment, lighting, and voice across cuts — all from one prompt. Every prompt integrates these elements in order (models weight earliest tokens more heavily): 1. 🎥 — Cinematography terms, shot scale, angle, style markers 2.
README
以下は原文 README の抜粋です。原文を見る。
🎬 LTX 2.5 Video Prompt Agent Skill
A Hermes Agent skill that transforms rough video ideas + reference images/audio into production-grade LTX 2.5 (Lightricks) video generation prompts.
Unlike structured-format skills (e.g., MiniMax H3), LTX 2.5 prompting is pure natural language — one flowing cinematic paragraph that reads like a shot description for a cinematographer. No JSON, no field labels, no tags. Just prose.
What It Does
When you describe a video concept (with or without attached media), this skill:
- Detects the mode — single-shot, multishot (NEW in 2.5), or screenplay-style
- Creatively enhances your idea across 6 cinematic dimensions
- Outputs a natural-language prompt — ready to paste into ComfyUI or LTX Studio
LTX 2.5 Modes
| Mode | Use Case | Output Format |
|---|---|---|
| Single-Shot | One continuous take (T2V, I2V, A2V, V2V) | Flowing paragraph, 4–8 sentences |
| Multi-Shot ⭐ | Multiple connected cuts in one generation | Chronological prose with named transitions |
| Screenplay-Style | Dialogue-heavy scenes with character cues | Screenplay scene with acting directions |
⭐ Native multishot is the headline feature of LTX 2.5. Previous versions only produced a single continuous shot. Now you can generate 2–4 connected shots — holding character identity, environment, lighting, and voice across cuts — all from one prompt.
The 6-Part Prompt Structure
Every prompt integrates these elements in order (models weight earliest tokens more heavily):
- 🎥 Establish the Shot — Cinematography terms, shot scale, angle, style markers
- 💡 Set the Scene — Lighting, color palette, textures, atmosphere
- 🏃 Describe the Action — Core action as a flowing sequence, present tense
- 👤 Define Character(s) — Physical specifics, wardrobe, emotion via physical cues
- 📷 Camera Movement — How and when the camera moves, relative to subject
- 🔊 Describe the Audio — Ambient sound, action SFX, music, dialogue
Important: This structure is a mental model for the writer. The output is pure prose — the model never sees field labels or numbered sections.
Installation
For Hermes Agent Users
Copy the skill folder to your Hermes skills directory:
# Linux/macOS
cp -r ltx-2-5-prompter ~/.hermes/skills/creative/
# Windows
xcopy ltx-2-5-prompter %LOCALAPPDATA%\hermes\skills\creative\ /E /I
Restart Hermes Agent. The skill auto-triggers when you mention LTX, attach media, and describe a video idea.
For Other Agent Frameworks (Claude, Codex, etc.)
The SKILL.md and reference files are standard Markdown — load them as system context or project rules in any agent that supports file-based instructions.
File Structure
ltx-2-5-prompter/
├── README.md # You are here
├── SKILL.md # Main skill — workflow, rules, verification
└── references/
推奨ツール
別のキーワードを試すか、フィルタを外してください。
インストール
npx skillfish add benjiyaya/ltx-2.5-agent-prompt-skill