Agent skill · creative production · samuraigpt
muapi-photo-pack-generator
Generate a pack of professional or aesthetic photos from a single reference image while preserving the exact identity of the person.
Why this skill is useful
Adds an executable script for generating themed photo packs while preserving identity fidelity, which is not commonly found in public documentation.
What it needs
Requires bash installed locally. About 2k tokens when loaded. Last updated 2026-08-04. 3,990 stars on the source repository.
What this skill does
📸 Photo Pack Generator Expert Skill (Identity-Lock Edition) Transform a single reference photo into a collection of themed images while maintaining extremely high facial identity fidelity. This skill prioritizes identity preservation first, then applies stylistic transformations like LinkedIn portraits, dating photos, cinematic shots, or fantasy styles. The system uses Identity Lock Prompting instead of describing the person, preventing the model from generating a new face. --- Core Principles 1️⃣ Identity Lock (MOST IMPORTANT) The generated images must always depict the same person from the reference image. All prompts MUST include identity lock instructions. Required identity rules: Preserve the exact facial identity from the reference image Do not modify eye shape or spacing Do not modify nose structure Do not modify jawline or chin shape Do not modify cheekbones Do not modify face proportions Identity must remain identical to the reference photo --- 2️⃣ Vision-First Scene Analysis The agent MUST analyze the reference image before generation. However the analysis must NOT describe the person (age, ethnicity, hair etc). Allowed analysis fields: head orientation facial angle expression lighting direction framing (portrait / half body / full body) Example: Head orientation: slight left tilt Expression: neutral friendly Lighting: soft frontal light Framing: head and shoulders portrait --- Agent Execution Flow Step 1 — Grounding Check Ensure the user has provided a reference image. Supported inputs: local image URL uploaded file --- Step 2 — Vision Analysis Extract scene attributes only. DO NOT describe: age ethnicity beard hair body type Identity must come directly from the image. --- Step 3 — Category Selection If the user does not specify a category suggest: LinkedIn Tinder OldMoney --- Step 4 — Prompt Construction Use the reference image as the identity source. Preserve the exact facial identity from the reference image. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills samuraigpt/photo-pack-generator