Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
samuraigpt avatar

Muapi Photo Pack Generator

  • 870 installs
  • 4k repo stars
  • Updated August 4, 2026
  • samuraigpt/generative-media-skills

muapi-photo-pack-generator is a bash-based agent skill that turns one reference photo into a consistent branded image pack for developers who need LinkedIn, Twitter, or product marketing visuals without manual design wor

About

muapi-photo-pack-generator is a generative-media skill in samuraigpt/generative-media-skills that runs a bash script to produce multiple images from a single reference photo. The script accepts --image or --image-url, a --category such as LinkedIn, the nano-banana-edit model, and defaults to NUM_IMAGES=5 outputs saved under media_outputs via upload.sh and generate-image.sh helpers. Developers reach for muapi-photo-pack-generator when they need a cohesive set of branded portraits or product shots for social profiles or marketing collateral from one source image. Optional flags include --likeness, --json-only, and --view-local for inspecting results during iteration.

  • Generates 5+ variant images from a single reference photo and chosen category
  • Supports both local files and remote image URLs as input
  • Built-in upload step that converts local images to hosted URLs automatically
  • Configurable model selection and likeness strength controls
  • Outputs both local files and structured JSON metadata

Muapi Photo Pack Generator by the numbers

  • 870 all-time installs (skills.sh)
  • +36 installs in the week ending Aug 5, 2026 (Skillselion tracking)
  • Ranked #308 of 1,335 Generative Media skills by installs in the Skillselion catalog
  • Security screen: MEDIUM risk (skills.sh audit)
  • Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/samuraigpt/generative-media-skills --skill muapi-photo-pack-generator

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs870
repo stars4k
Security audit2 / 3 scanners passed
Last updatedAugust 4, 2026
Repositorysamuraigpt/generative-media-skills

How do you batch-generate branded images from one photo?

Quickly turn one reference photo into a consistent set of branded images for LinkedIn, Twitter, or product assets.

Who is it for?

Developers automating branded social profile or product image packs from a single reference photo using the nano-banana-edit model.

Skip if: Teams needing fine-grained manual Photoshop edits, video assets, or workflows without shell script execution and image API access.

When should I use this skill?

User wants a photo pack, branded LinkedIn/Twitter images, or multiple consistent visuals generated from one reference image.

What you get

A pack of 5 consistent generated images in media_outputs, optionally uploaded via the bundled upload.sh script.

  • 5-image branded photo pack
  • media_outputs directory files

By the numbers

  • Default NUM_IMAGES=5 per generation run
  • Uses nano-banana-edit model with bundled upload.sh and generate-image.sh scripts

Files

SKILL.mdMarkdownGitHub ↗

📸 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.

Identity must remain identical to the reference photo.

Do not change:

  • eye shape
  • eye spacing
  • nose structure
  • jawline
  • cheekbones
  • face proportions

Maintain similar head orientation as the reference.

Scene example:

Outdoor café portrait Soft natural daylight 35mm portrait lens Shallow depth of field Photorealistic skin texture

---

Step 5 — Negative Prompt

Always include:

different person altered face changed facial features new identity generic face beautified face plastic skin face distortion

---

Step 6 — Execution

Example:

bash scripts/generate-pack.sh \ --image "./my_face.jpg" \ --category "LinkedIn" \ --identity-lock true \ --num 5

---

Supported Categories

CategoryBest ForAesthetic
LinkedInProfessionalStudio
CEOFoundersOffice
TinderDatingLifestyle
OldMoneyLuxuryEstate
CyberpunkFantasyNeon
FitnessGymAthletic
TravelSocialBali/Paris
90sRetroVintage
HolidaySeasonalFestive

---

Guardrails

Fidelity First

Identity preservation is always more important than style.

Never Re-Describe the Person

Avoid prompts like:

"Indian man in his 20s with short hair"

This causes the model to generate a new face.

Identity must come from the reference image only.

---

Recommended Models

Best results with:

  • nano-banana-edit

---

Result

This system produces:

  • consistent identity
  • photorealistic images
  • multi-style photo packs
  • professional outputs

Related skills

FAQ

How many images does muapi-photo-pack-generator create by default?

muapi-photo-pack-generator defaults to NUM_IMAGES=5 outputs per run, using the nano-banana-edit model from a single --image file or --image-url reference, saved to the media_outputs directory.

Which platforms does muapi-photo-pack-generator support?

muapi-photo-pack-generator includes a LinkedIn category preset and supports Twitter and product asset categories via the --category flag, producing consistent branded image packs for each platform.

Is Muapi Photo Pack Generator safe to install?

skills.sh reports 2 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.

Generative Mediaautomationagents

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.