Vorla AIVorla.ai

캐릭터 레퍼런스 시트

캐릭터 레퍼런스 시트는 다양한 각도, 다양한 표정, 상세한 특징 콜아웃을 통해 단일 캐릭터를 보여줍니다. 캐릭터 디자인의 일관성을 유지하기 위한 시각적 가이드 역할을 합니다.

프롬프트

Based on the provided character original image, create a "Character Identity Fixed Reference Chart", landscape 16:10, light grayish-white background, professional visual mood board layout. The primary goal is for all panels to clearly show the exact same character at a glance, not multiple similar figures. Treat the character's identity in the reference image as an unchangeable hard constraint. Strictly lock: - Face width-to-height ratio, cheekbones, cheeks, jaw, and chin - Eye contour, interocular distance, eyelid structure, and gaze temperament - Eyebrow arch, thickness, color, and eyebrow-to-eye distance - Bridge of the nose, nose tip, ala, and profile nose shape - Upper and lower lip thickness, cupid's bow, mouth corners, and natural lip color - Skin tone, pores, complexion, and natural skin contours - Hairline, parting, bangs, side hair, back hair length, and hair flow direction - Age impression, bone structure, shoulder width, limb length, and overall body shape - Original clothing, original art style, light texture, and overall atmosphere In the center of the image, display with larger panels: - Full body, front - Full body, side - Full body, back - Face, front - Profile, left - Profile, right - Diagonal, left - Diagonal, right - Back of head Maintain completely consistent skull structure, relative positions of facial features, hair volume, and body proportions for each angle. Side profiles must accurately continue the nose bridge, lips, chin, and forehead structure of the front view; do not generate side profiles that look like different people. On the right side, arrange a small expression matrix: - Normal - Smiling - Serious - Surprised - Shy - Thinking - Troubled expression - Slightly sad - Calm Maintain the same pupil, basic eye size, nose shape, lip shape, and face shape. Smiles should be natural and restrained, not changing the character's age or temperament. At the bottom, configure detailed identity anchor points: - Left eye - Right eye - Eyebrows - Nose, front - Nose, side - Lips - Ears - Jawline contour - Skin texture - Bangs structure - Side hair structure - Back hair structure - Hair tip flow - Hands On the left side, add 5-7 accurate color swatches: hair color, eye color, skin color, lip color, clothing color, shadow color, base tone. Add minimalist "fixed key points": fixed face shape, fixed eye area, fixed nose shape, fixed lips, fixed bangs, fixed body shape, unified clothing, same character priority. The background should be clean, with soft, even lighting, no cinematic lighting, strong depth of field, or decorative elements. For real-person characters, retain natural pores, fine hairs, and subtle skin tone variations; for non-real-person characters, strictly maintain the original image's lines, color blocks, shadows, and materials, and do not arbitrarily change styles. All labels should only use clear simplified Chinese, with an appropriate font size, not covering the character. If there is insufficient space on the layout, prioritize retaining identity anchor points and main angles, reduce redundant panels, and do not force content by shrinking text or sacrificing character consistency. Negative prompts: different people, similar but not the same face, identity drift, face swapping between panels, face shape drift, changed interocular distance, changed pupils, changed eyebrow shape, changed nose bridge, changed nose tip, changed lip shape, changed chin, changed hairline, changed bangs, changed parting, changed hair color, changed hair length, changed body shape, changed age, changed clothing, excessive beautification, skin smoothing, plastic skin, childlike face, sexualization, underwear, swimwear, magazine photos, movie lighting, exaggerated poses, props, complex background, English text, garbled text, fake Chinese, watermarks, logos, signatures, extra fingers, missing fingers, fused hands, misaligned facial features, collapsed side profile, overlapping faces, distorted body, style transformation, chaotic layout.

프롬프트 사용법

프롬프트 복사

정리된 프롬프트를 원하는 언어로 복사하거나, 한 번의 클릭으로 편집기로 보낼 수 있습니다.

모델 선택

이 결과를 만든 모델이 미리 선택되며, Vorla가 지원하는 다른 모델로 바꿀 수도 있습니다.

생성하고 다듬기

먼저 그대로 실행해 분위기를 재현한 뒤, 문구를 수정해 나만의 결과로 만들어 보세요.

GPT Image 2의 다른 프롬프트

전체 2004개 보기
테라코타 및 초콜릿 란제리 세트
봄나들이 인물 사진
전체 프롬프트 보기
실크 캐미솔 광고
계화꽃떡 제품 광고
테니스 코트에 선 여성
전체 프롬프트 보기
동양적인 종이 오리기 꿈 풍경
전체 프롬프트 보기
80년대 중국풍 증명사진
전체 프롬프트 보기
몰튼 리듬 란제리 세트 디자인
전체 프롬프트 보기

이미지와 영상 중 선택

다음 AI 프롬프트 찾기

한 번의 검색으로 모든 모델과 두 매체를 아우르고, 찾은 것을 복사하는 데 비용은 없습니다.

모든 프롬프트 둘러보기