Job
시각적 컨셉·무드·레퍼런스를 구조화된 이미지 생성 프롬프트로 옮깁니다. 피사체·환경·조명·카메라·스타일을 층으로 나누고, 모호한 형용사 대신 정확한 사진 용어를 씁니다. 인물·제품·풍경·패션·에디토리얼·일러스트를 Midjourney, DALL-E, Stable Diffusion, Flux 등 여러 도구에 맞춰 다룹니다.
← Marketplace01 02 03
Image Prompt Engineer
by Agentlas
Agent explainer
What this agent actually does
Tool use
If a run needs a plugin or external API, it asks for access first and uses it only within the approved scope.
Result
It produces a result you can review before you apply it.
Best for
What it's good for
골든아워 인물 사진 느낌으로 미드저니 프롬프트 만들어줘. 85mm, 얕은 심도.
제품 화보용 스튜디오 조명 프롬프트 짜줘. 소프트박스랑 리플렉터 위치까지.
이 패션 화보 레퍼런스를 Flux용 상세 프롬프트랑 네거티브 프롬프트로 바꿔줘.
What's inside
What's in this agent
1 skill1 agent1 command
Prerequisites
Before you start
the visual concept, mood, or references to render
the target AI image platform (Midjourney, DALL-E, Stable Diffusion, Flux, etc.)
the intended use and aspect ratio (portrait, product hero, landscape, editorial, etc.)
Safety
What it can touch
Access
Files: scoped
Network: none
External API: yes
ONTOLOGY CHIPS
Operational experience and taste compatible with this agent
Hiring the agent and selecting an experience chip are separate decisions. Only verified exact-release matches appear, and none is purchased or attached automatically.
The chip registry could not be loaded. The base agent remains available.
Safety
Inspect everything before it runs
A security scan runs before publish or install, and Agentlas never hosts or proxies models — it runs on your own account and keys.