Back to Details

rembrandt-portrait-lighting

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Format-Adaptive Rembrandt Portrait Lighting

适配格式的伦勃朗肖像布光

Turn a supplied photo into a complete, credible Rembrandt-lit studio hero portrait at a proportion suited to the source and intended use. Rembrandt chiaroscuro is the defining style; the studio conversion, framing, subject separation, and final grade exist to make that light hit with premium editorial authority.
将提供的照片转换为符合源图比例与预期用途的完整、可信的伦勃朗布光工作室主肖像。伦勃朗明暗对比（chiaroscuro）是核心风格；工作室场景转换、构图、主体分离及最终调色均为强化该布光的专业编辑质感服务。

Scope and subject fidelity

适用范围与主体保真度

  • Use the built-in image-generation editing workflow. If the source is a local file, inspect it with 
    view_image
    first. Never overwrite the original.
  • The subject can be one or more people, pets, or a mixed group. If no photo is supplied, ask the user to attach one; if they want only a prompt, provide it without generating an unrelated subject.
  • Preserve the original subject, count, identity, expression, clothing, accessories, and visible anatomy. Preserve pose and viewpoint by default, but permit the controlled composition and posture refinements below when they make a static source feel like a credible new studio sitting. Do not mirror or radically re-pose merely to accommodate a lighting diagram.
  • For people, preserve identity, apparent age, ethnicity, skin tone, facial proportions, hairstyle, hands, tattoos, jewelry, glasses, and wardrobe.
  • For pets, preserve species, breed traits, coat color and markings, muzzle, eye color and shape, ear position, whiskers, collar, limbs, and tail. Do not humanize animal eyes, add makeup, alter paws, or invent a different animal.
  • 使用内置的图像生成编辑工作流。若源图为本地文件，先使用
    view_image
    查看。切勿覆盖原图。
  • 主体可为单人、单宠物或混合群体。若未提供照片，请用户上传；若用户仅需提示词，则提供提示词但不生成无关主体。
  • 保留原主体的数量、身份、表情、服饰及可见身体特征。默认保留姿势与视角，但当静态源图可通过可控的构图与姿态调整变为可信的新工作室拍摄效果时，允许进行以下微调。切勿仅为适配布光示意图而翻转或大幅改变姿势。
  • 针对人物：保留身份、表观年龄、种族、肤色、面部比例、发型、手部、纹身、首饰、眼镜及衣着。
  • 针对宠物：保留物种、品种特征、毛色及斑纹、口鼻部、眼睛颜色与形状、耳朵位置、胡须、项圈、四肢及尾巴。切勿拟人化动物眼睛、添加妆容、修改爪子或替换为其他动物。

Default: full low-key studio conversion

默认设置：完整低调工作室转换

Unless the user explicitly asks to retain the scene, treat the request as a full Rembrandt studio conversion: replace the casual environment with a clean deep-charcoal-to-ink studio field and relight the subject around one dominant high-side key. It must feel like one exposure made in one studio, never a cut-out pasted onto black. A background swap without new subject lighting is a failure.
Build clear figure-ground separation:
  • Make the subject’s key-side planes the highest-value area. Render empty background as a smooth, noise-free deep charcoal that falls toward ink black across the frame. Use one extremely broad, low-contrast, asymmetric tonal transition aligned with the key so the set has depth without becoming visible scenery; never use a centered head halo, spotlight disc, gray haze, or uniformly clipped black canvas. The subject must read instantly even as a thumbnail.
  • Treat the background as a clean low-ISO commercial digital capture: silky continuous-tone gradient, visually noise-free at 100% zoom, with no film emulation. Gradient is allowed and desirable; grain, texture, and random luminance variation are not.
  • Use one dominant, image-coordinate key (
    key from image-left
    or 
    key from image-right
    ), 40–60° off camera and 30–45° above the primary face/eyes. Never use an unqualified “left” or “right”.
  • Describe a large, close, feathered, gridded soft source: directional enough for visible highlight-to-shadow modeling, but broad enough for a natural penumbra, gentle highlight roll-off, and believable light wrap at hair, fur, ears, and shoulders.
  • Default to a 4:1–6:1 key-to-fill ratio (about two to two-and-a-half stops) with restrained black-flag negative fill on the shadow side. Reserve 8:1 for an explicitly severe theatrical result. Keep both eyes alive and preserve texture in the shadows; do not make the shadow side a dead black cutout.
  • Add a restrained, physically plausible kicker only when the subject merges into the backdrop. It should define fur, hair, shoulders, or ears at lower intensity than the key—never a neon rim halo. Preserve irregular fine edge hairs and slight optical softness so the silhouette does not resemble a segmentation mask.
  • Hold focus on the nearer eye(s) and facial/muzzle plane, then let sharpness fall naturally across ears, shoulders, and clothing as an 85 mm-equivalent studio portrait would. Preserve real skin, fur, whiskers, and fabric without amplifying pores, wrinkles, weave, or edge contrast. Ban clarity/texture boosting, crunchy microcontrast, plastic smoothing, and synthetic bokeh.
Use rich neutral blacks, neutral-to-gently-warm highlights, controlled specular roll-off, and restrained saturation. Preserve the source skin or coat albedo; do not lay an amber, copper, orange, or brown wash over the subject. Keep natural microtexture without exaggerating it. Avoid flat front light, beauty-light wash, HDR halos, orange-and-teal grading, painterly texture, and global film-grain overlays.
除非用户明确要求保留原场景，否则将请求视为完整伦勃朗工作室转换：将日常环境替换为干净的深炭黑至纯黑工作室背景，并使用单侧主光重新为主体布光。成品需呈现为同一场工作室拍摄的单张曝光效果，绝不能是主体抠图粘贴到黑色背景上。仅替换背景而不为主体重新布光即为失败。
打造清晰的主体-背景分离：
  • 使主体受光面成为画面中亮度最高的区域。将空白背景渲染为平滑无噪点的深炭黑色，并沿主光方向形成渐变过渡至纯黑，为场景增加深度但不呈现可见景物；切勿使用居中头部光晕、聚光圆盘、灰色雾效或完全死黑的画布。主体在缩略图尺寸下也需清晰可辨。
  • 背景需呈现低ISO商业数码拍摄质感：丝滑连续色调渐变，100%放大下无视觉噪点，无胶片模拟效果。渐变是允许且推荐的；颗粒、纹理及随机亮度变化均不允许。
  • 使用单侧固定主光（
    key from image-left
    或
    key from image-right
    ），与镜头夹角40–60°，高于主体面部/眼睛30–45°。切勿使用无明确指向的“左侧”或“右侧”。
  • 描述一个大型、近距离、柔化、带格栅的光源：方向感足够形成清晰的明暗塑造，但范围足够宽以产生自然半影、柔和高光过渡，以及在毛发、皮毛、耳朵和肩部位置可信的光包裹效果。
  • 默认使用4:1–6:1的主辅光比（约2至2.5档），阴影侧使用克制的黑旗负补光。仅当用户明确要求戏剧化效果时才使用8:1的光比。确保双眼均有光泽，保留阴影处的纹理；切勿将阴影侧处理为死黑的抠图效果。
  • 仅当主体与背景融合时，添加克制、符合物理逻辑的轮廓光（kicker）。其亮度需低于主光，用于勾勒毛发、皮毛、肩部或耳朵轮廓——绝不能是霓虹式边缘光晕。保留不规则的细碎边缘毛发和轻微光学柔化效果，避免轮廓像分割蒙版般生硬。
  • 聚焦于离镜头较近的眼睛及面部/口鼻区域，然后让清晰度自然衰减，如同85mm等效焦距的工作室肖像照片。保留真实皮肤、皮毛、胡须及织物质感，不放大毛孔、皱纹、纹理或边缘对比度。禁止提升清晰度/纹理、强化微对比度、塑料磨皮及合成虚化效果。
使用浓郁的中性黑色、中性至微暖高光、可控的高光过渡及克制的饱和度。保留源图皮肤或皮毛的反射率；切勿为主体添加琥珀色、铜色、橙色或棕色色调。保留自然微纹理但不过度夸张。避免平面前光、美妆光效、HDR光晕、橙青色调分级、绘画质感及全局胶片颗粒叠加。

Camera, pose, and living presence

机位、姿势与鲜活感

When the source is stiff, passport-like, or memorial-looking, make the smallest safe adjustment that creates editorial life while retaining identity:
  • Prefer a subtle three-quarter relationship: turn the virtual camera or the head/torso only a few degrees, keep both eyes plausible, and preserve facial geometry. Never reveal a substantially unseen side of the face or body.
  • For people, allow a slight head turn or tilt, relaxed shoulder drop, asymmetric shoulder line, mild torso rotation, or natural weight shift. Keep the original expression unless the user requests another; do not manufacture a grin, change hand gestures, or invent hidden limbs.
  • For pets, allow a small head/gaze turn, more attentive but anatomically natural ear posture, or a slight seated/standing weight adjustment. Preserve breed structure, ear shape, paws, tail, coat markings, and the original emotional character.
  • Use an eye-level or subtly elevated portrait camera by default. A small camera-height or yaw refinement is acceptable; dramatic low angles, overhead views, wide-angle distortion, or major perspective changes require an explicit request.
  • Build asymmetry with gaze room, shoulder direction, light direction, and negative space—not dutch angles or theatrical action. The result should feel alert, present, and recently photographed, not frozen or ceremonial.
当源图姿势僵硬、类似证件照或纪念照时，进行最小幅度的安全调整，在保留身份的同时赋予编辑感活力：
  • 优先采用微妙的四分之三视角：将虚拟机位或头部/躯干转动几度，确保双眼姿态自然，保留面部几何结构。切勿展示面部或身体未被拍摄过的大幅侧面。
  • 针对人物：允许轻微转头或歪头、放松单侧肩膀、不对称肩线、轻微躯干转动或自然重心转移。除非用户要求，否则保留原表情；切勿强行添加笑容、改变手势或虚构隐藏肢体。
  • 针对宠物：允许轻微转头/转视线、更专注但符合解剖学的耳朵姿态，或轻微坐姿/站姿重心调整。保留品种结构、耳朵形状、爪子、尾巴、毛色斑纹及原有的情绪特征。
  • 默认使用平视或略微抬高的肖像机位。小幅调整机位高度或偏角是可接受的；戏剧性低角度、俯视视角、广角畸变或大幅透视变化需用户明确请求。
  • 通过视线空间、肩部方向、布光方向及负空间打造不对称感——而非倾斜角度或戏剧化动作。成品需呈现警觉、鲜活、近期拍摄的状态，而非僵硬或仪式感的定格。

Format and framing

格式与构图

Default to the source image's aspect ratio and orientation. Do not force a square, portrait, or landscape conversion when the user has not requested one.
  • If the user specifies an aspect ratio or exact dimensions, obey them. If they specify only a use, choose a conventional ratio: 
    1:1
    for avatars, 
    4:5
    for social portrait posts, 
    3:4
    for classic portrait/editorial, 
    2:3
    for full-length portrait/print, 
    3:2
    for photographic landscape/editorial, 
    4:3
    for general landscape, or 
    16:9
    for banners and cinematic covers.
  • Preserve orientation unless the requested use clearly requires another orientation. Treat aspect ratio and pixel dimensions separately; never promise dimensions the generator cannot actually deliver.
  • Reframe with the least destructive method. First remove expendable background. If cropping would clip hair, ears, chin, whiskers, hands, paws, tail, meaningful clothing, or the spatial relationship between multiple subjects, extend the studio field instead of cutting the subject.
  • When extending, synthesize only plausible continuation of the dark studio set, existing clothing/body edges, and necessary contact shadows. Do not invent new anatomy, accessories, furniture, scenery, or a substantially wider camera viewpoint. Extension must match the key direction, lens perspective, depth of field, tonal falloff, and background cleanliness.
  • Keep the face or pet head dominant without imposing a fixed head size on every source. Tight portraits may use head-and-shoulders framing; wider source photographs may retain upper body, full body, or group context when that better preserves the original photograph.
  • Place the eye line and negative space according to the selected orientation and gaze direction. Do not center mechanically; leave breathing room toward the subject's gaze while keeping the subject visually dominant.
  • Keep the eye(s) and face/muzzle as the first visual fixation through focus, local contrast, and controlled dodge-and-burn—not artificial glow or changed eye color.
  • Use simple negative space and a clean silhouette. Do not add typography, badges, ornamental frames, fake lens flares, or props.
  • Use the highest available native image quality. Do not claim “8K” unless the actual delivered dimensions are 8K; fake resolution language and oversharpening are not quality.
For 
1:1
avatar output, use a tight head-and-shoulders crop, keep complete hair/ears/chin/whiskers inside the central 80% circular safe area, and verify readability at 64×64 px. For multiple subjects, preserve the group rather than deleting or merging anyone; use extension or a wider standard ratio when a square would damage the composition.
默认保留源图的宽高比与方向。用户未要求时，切勿强行转换为方形、竖版或横版。
  • 若用户指定宽高比或精确尺寸，严格遵循。若仅指定用途，选择常规比例：
    1:1
    用于头像，
    4:5
    用于社交平台肖像帖，
    3:4
    用于经典肖像/编辑图，
    2:3
    用于全身肖像/印刷品，
    3:2
    用于摄影风景/编辑图，
    4:3
    用于通用风景图，
    16:9
    用于横幅及电影封面。
  • 保留原方向，除非指定用途明确要求更改。将宽高比与像素尺寸分开处理；切勿承诺生成器无法实现的尺寸。
  • 使用破坏性最小的方式重新构图。首先移除可舍弃的背景。若裁剪会裁切头发、耳朵、下巴、胡须、手部、爪子、尾巴、有意义的服饰或多主体间的空间关系，则扩展工作室背景而非裁切主体。
  • 扩展背景时，仅合成可信的深色工作室场景延伸、现有服饰/身体边缘的延续及必要的接触阴影。切勿虚构新的身体部位、配饰、家具、景物或大幅拓宽的机位视角。扩展部分需与主光方向、镜头透视、景深、色调过渡及背景纯净度匹配。
  • 突出面部或宠物头部，但不为所有源图强加固定的头部大小。特写肖像可采用头肩构图；宽幅源图在能更好保留原照片信息时，可保留上半身、全身或群体场景。
  • 根据所选方向与视线方向安排眼位与负空间。切勿机械居中；在保持主体视觉主导的同时，为主体视线方向预留呼吸空间。
  • 通过对焦、局部对比度及可控的提亮/压暗，使眼睛及面部/口鼻成为第一视觉焦点——而非人工光晕或改变眼睛颜色。
  • 使用简洁的负空间与清晰的轮廓。切勿添加文字、徽章、装饰边框、虚假镜头光晕或道具。
  • 使用最高可用的原生图像质量。除非实际输出尺寸为8K，否则切勿声称“8K”；虚假分辨率描述及过度锐化均不属于高质量。
对于
1:1
头像输出，采用紧凑的头肩裁剪，确保头发/耳朵/下巴/胡须完全位于中央80%的圆形安全区内，并验证64×64 px尺寸下的可读性。多主体场景需保留群体，而非删除或合并主体；若方形构图会破坏画面，则扩展背景或采用更宽的标准比例。

Subject-specific light pattern

主体专属布光模式

For people with a three-quarter face and both eyes visible, make the strong default short-light Rembrandt: the nasal shadow joins the cheek shadow as a closed loop and leaves a small natural Rembrandt patch below the far eye. It is a lighting diagnostic, not a painted-on triangle.
For frontal or profile people, use Rembrandt-inspired low-key facial-plane modeling instead; do not distort a nose shadow just to force a patch.
For pets, translate Rembrandt chiaroscuro into an elevated three-quarter side key with sculptural low-key modeling. Prioritize species-appropriate catchlights, muzzle form, eyes, ears, and coat/fur texture. Do not force human cheek-triangle geometry onto animals.
Read subject diagnostics before choosing the light pattern.
对于四分之三面部且双眼可见的人物，默认采用经典的短光伦勃朗布光：鼻影与脸颊阴影形成闭合环，在远侧眼睛下方留下一小块自然的伦勃朗光斑。这是布光诊断特征，而非绘制的三角形。
对于正面或侧面人物，采用伦勃朗风格的低调面部塑造布光；切勿为强行制造光斑而扭曲鼻影。
对于宠物，将伦勃朗明暗对比转换为高位四分之三侧主光的雕塑感低调塑造布光。优先考虑符合物种特征的眼神光、口鼻形态、眼睛、耳朵及皮毛纹理。切勿将人类面部三角几何结构强加于动物。
选择布光模式前，请阅读主体诊断指南。

Background and set continuity

背景与场景连续性

  • Preserve the source aspect ratio by default. Choose or change to a standard ratio only from an explicit dimension, aspect ratio, or use-case request, following the format rules above.
  • Default to a clean, smooth, textureless deep-neutral-charcoal-to-ink studio field—not a uniformly clipped digital 
    #000000
    canvas, charcoal cloth, painted wall, paper, visible cyclorama texture, or fog. Maintain a subtle broad asymmetric tonal falloff aligned with the key; it should create spatial depth with visually continuous, band-free tone. Background cleanliness is non-negotiable: no luminance noise, chroma noise, film grain, sensor grain, dither pattern, mottling, speckle, paper/fabric texture, smoke, dust, banding, JPEG blocks, or AI texture synthesis. Use absolute pure black only when explicitly requested.
  • Background separation must come primarily from the directional key, natural light wrap, tonal depth, and only if essential a restrained edge kicker. Never place a gray glow, radial hotspot, obvious vignette, halo, or light pool behind the head to fake separation.
  • The background’s direction, falloff, contact shadow, and color temperature must agree with the key. A bright source from the wrong side behind the subject is a defect.
  • Respect difficult contours: hair, fur, whiskers, ears, transparent eyeglass frames, translucent fabric, and paws. Preserve natural contact and floor shadows when visible.
  • Do not add speed trails, motion blur, wind, action effects, extra subjects, or duplicate limbs unless explicitly asked.
  • 默认保留源图宽高比。仅在用户明确指定尺寸、宽高比或用途时，才选择或更改为标准比例，遵循上述格式规则。
  • 默认使用干净、平滑、无纹理的深中性炭黑至纯黑工作室背景——而非完全死黑的数字
    #000000
    画布、炭布、涂漆墙面、纸张、可见的环幕纹理或雾气。保持与主光方向一致的微妙宽幅不对称色调过渡；需通过视觉连续、无条带的色调营造空间深度。背景纯净度是硬性要求：无亮度噪点、色度噪点、胶片颗粒、传感器颗粒、抖动图案、斑点、纹理、烟雾、灰尘、条带、JPEG块或AI纹理合成。仅当用户明确要求时才使用纯黑背景。
  • 主体分离需主要通过定向主光、自然光包裹、色调深度实现，仅在必要时辅以克制的轮廓光。切勿在头部后方添加灰色光晕、径向热点、明显暗角、光环或光池来伪造分离效果。
  • 背景的方向、过渡、接触阴影及色温必须与主光一致。主体后方出现来自错误方向的亮光源属于缺陷。
  • 处理复杂轮廓：头发、皮毛、胡须、耳朵、透明眼镜框、半透明织物及爪子。保留可见的自然接触阴影与地面阴影。
  • 除非用户明确要求，否则切勿添加运动轨迹、动态模糊、风效、动作特效、额外主体或重复肢体。

Avoid memorial-portrait cues

避免纪念肖像特征

The default result must read as contemporary editorial portraiture, not a memorial, funeral, obituary, or posthumous portrait. Avoid the combined pattern of dead-center frontal symmetry, rigid square shoulders, blank forward stare, uniformly pure-black background, sepia/monochrome skin, heavy vignette, oval framing, faded edges, floating bust crop, solemn ceremonial styling, flowers, candles, wreaths, religious symbols, or inscription space. Dark clothing must retain separation from the set. A calm older subject may remain calm and dignified; create living presence through directional gaze, asymmetric posture, dimensional color, catchlights, and breathable composition rather than forcing a smile.
默认成品需呈现为当代编辑肖像，而非纪念照、葬礼照、讣告照或遗像。避免以下组合特征：居中正面对称、僵硬方肩、空洞直视、纯黑背景、棕褐色/单色皮肤、重度暗角、椭圆形边框、褪色边缘、悬浮半身裁剪、庄严仪式风格、花卉、蜡烛、花圈、宗教符号或铭文空间。深色服饰需与背景保持分离。年长的平静主体可保持沉稳庄重；通过定向视线、不对称姿势、立体色彩、眼神光及透气构图营造鲜活感，而非强行添加笑容。

Prompt construction and iteration

提示词构建与迭代

Before editing, read the studio production prompt. Inspect the source, fill the template with only observed facts and user directions, then make one focused edit request. Re-state every source invariant on each retry.
Classify the normal edit as 
identity-preserve
plus 
lighting-weather
; treat the studio backdrop as part of the integrated relight, not an unrelated replacement. Do not introduce props, text, logos, watermarks, costume changes, glamour makeup, or an oil-painting style.
Make one targeted retry only for an observable defect: noisy background, memorial/funeral resemblance, stiff frontal symmetry, cut-out/segmented appearance, visible background halo, insufficient subject separation, weak or frontal key, incorrect key direction, flat shadows, bronze/orange skin, exaggerated wrinkles or fabric, lost identity/coat markings, unsafe pose change, broken anatomy, artificial animal eyes, haloed fur/hair, or contradictory background light. If the image is otherwise successful but the backdrop contains noise, do not regenerate the portrait: request a background-only cleanup, locking the subject, crop, lighting, identity, skin/fur, clothing, silhouette edges, and existing broad gradient exactly. Remove only grain, speckle, noise, mottling, banding, and compression artifacts; return a silky continuous deep-charcoal-to-ink gradient with subtle optical integration at the silhouette.
编辑前，请阅读工作室生产提示词。查看源图，仅填入观察到的事实与用户指令，然后提交一个聚焦的编辑请求。每次重试时需重申所有源图不变特征。
将常规编辑分类为
identity-preserve
+
lighting-weather
；将工作室背景视为整合布光的一部分，而非无关的替换。切勿引入道具、文字、标志、水印、服装变更、美妆或油画风格。
仅针对可观察到的缺陷进行一次定向重试：背景噪点、类似纪念/葬礼风格、僵硬正面对称、抠图/分割感、可见背景光晕、主体分离不足、主光薄弱或正面、主光方向错误、平阴影、古铜色/橙色皮肤、过度夸张的皱纹或织物、身份/毛色斑纹丢失、不安全的姿势变更、解剖结构错误、人工动物眼睛、毛发/皮毛光晕、背景光矛盾。若图像其他部分成功但背景存在噪点，请勿重新生成肖像：请求仅清理背景，锁定主体、裁剪、布光、身份、皮肤/皮毛、服饰、轮廓边缘及现有宽幅渐变。仅移除颗粒、斑点、噪点、斑点、条带及压缩伪影；返回丝滑连续的深炭黑至纯黑渐变，与轮廓边缘实现微妙光学融合。

Final check

最终检查

Before delivery, inspect every empty background quadrant at 100% zoom: the gradient must be smooth, continuous, neutral, and visually noise-free, with no grain, random texture, color speckle, banding, or compression blocks. Tonal depth must be broad and never form a head halo. Any visible background noise is a failed deliverable even when the subject is otherwise excellent; run the locked background-only cleanup once. Confirm there is no segmentation edge, crunchy microcontrast, copper skin cast, or crushed shadow anatomy. Also confirm that this is visibly one coherent new studio exposure—not the original subject pasted onto a different background; the subject is recognizably identical; one side is clearly key-lit while the other falls into deep legible shadow; and all silhouettes, whiskers, hands, paws, and catchlights remain plausible. Verify that cropping, extension, camera refinement, and posture refinement preserved anatomy, identity, lens plausibility, key direction, and meaningful context. Reject any result whose centered symmetry, black field, expression, or styling gives it an unintended memorial/funeral reading. For avatar output only, also inspect a 64×64 circular-crop preview. Report the actual dimensions, aspect ratio, and whether framing used preservation, cropping, extension, or controlled pose/viewpoint refinement.
交付前，以100%放大倍率查看所有空白背景区域：渐变需平滑、连续、中性、无视觉噪点，无颗粒、随机纹理、彩色斑点、条带或压缩块。色调深度需宽广，且绝不形成头部光晕。即使主体部分完美，背景存在可见噪点也属于不合格交付品；需执行一次锁定主体的背景清理。确认无分割边缘、生硬微对比度、铜色肤色或阴影处解剖结构丢失。同时确认成品明显是一张连贯的新工作室曝光照片——而非原主体粘贴到不同背景上；主体可识别为同一对象；单侧明显受主光照射，另一侧落入清晰可辨的深阴影；所有轮廓、胡须、手部、爪子及眼神光均合理可信。验证裁剪、扩展、机位调整及姿态调整是否保留了解剖结构、身份、镜头合理性、主光方向及重要上下文。拒绝任何因居中对称、黑背景、表情或风格而意外呈现纪念/葬礼感的结果。仅针对头像输出，还需检查64×64圆形裁剪预览。报告实际尺寸、宽高比，以及构图采用了保留、裁剪、扩展还是可控的姿势/视角调整。