超广角视角与动态姿态的混搭编辑

完整提示词
Applicable to real photos. Thanks for sharing. English version of the prompt: Remix Edit: Extreme Wide-Angle Perspective & Dynamic Poses This is an edit based on the original image, not a brand-new character. Please use the original image as a strict reference for: The character's identity, hairstyle, and overall clothing style. The general type of background and scene (the same street, the same room, the same beach, the same architectural environment, etc.). You can completely change the camera position, angle, and pose, but you must maintain: The scene remains in the same location. The character and clothing design remain consistent. Camera & Perspective: Use an ultra-wide-angle or fisheye-like lens (giving the feel of a 12–18mm full-frame equivalent). The camera angle must be significantly different from the original. Exaggerated camera positions to use include: An upward-looking, low-angle shot from directly below. A downward-looking, high-angle shot from directly above. An ultra-low angle, close to the ground. A high-angle shot from above. A tilted "Dutch angle" composition. Always create a strong foreshortening effect: the body part closest to the lens appears enormous, while the rest of the body extends into the distance in perspective. The final result must look like a bold fashion or street-style photograph, completely photorealistic, not an illustration or anime style. Background Consistency: Maintain the same location as the original image: the same street, the same bridge, the same room, the same photo studio, the same beach, with similar or identical structures and materials. Do not replace the background with a completely different scene. Due to the change in camera angle, different areas of the environment are allowed and expected to appear. When new areas appear, they must logically and naturally extend the original environment (same architecture, fences, road markings, walls, colors, materials, lighting style, etc.), as if the camera were moved within the same location. Body Parts Close to the Lens (1–2, sometimes 3): In each edited image, select one or two primary body parts to be extremely close to the lens (in more complex poses, it can sometimes be three). Vary these parts between different images; don't always have the same part close to the lens. Body parts that can be brought close to the lens include: One or both hands/fingers extending toward the lens. One or both feet/shoes/boots close to the lens. Knees or thighs. The face, very close to the lens. Shoulders or chest in a leaning-forward pose. The selected body parts should be extremely close to the lens, almost touching it, with clearly visible skin texture, fabric texture, and realistic wide-angle distortion. Pose & Overall Body (Complex & Varied): Create strong, cool, and dynamic poses that match the extreme perspective. Randomly use different types of poses, including: Standing poses with one leg or hand extended towards the lens. Squatting or a low semi-squat. Sitting on the ground or on an object. Lying flat on the ground with legs or feet towards the lens. The body leaning significantly forward towards the lens. Twisting the torso, crossing legs, or arching the back to create more dynamic body lines. Complex poses are allowed, for example: Both hands close to the lens, making gestures (a peace sign, a triangle, framing with fingers, pointing at the viewer, etc.). Both feet pointing towards the lens. One hand and one foot simultaneously acting as large foreground elements. The face close to the lens, while a hand or foot also appears in the perspective. Maintain a plausible and believable human anatomy, even with extreme foreshortening. Camera Position & Attitude (Randomized): Randomly change the camera angle and direction (upward, downward, sideways, tilted composition) while keeping the composition visually balanced and impactful. The attitude should remain cool, composed, and confident, leaning towards a high-fashion or street-style vibe, depending on the original outfit's feel. Facial expressions can vary (serious, playful, confident, mysterious, etc.), but it must always look like the same person. Lighting & Rendering: Maintain a similar time of day and lighting atmosphere as the original image (day/night, indoor/outdoor, soft/hard light), but you can enhance contrast and color to make the image more impactful and dramatic. Maintain realistic shadows and contact with the ground/floor. High resolution and sharp details, showing skin texture, fabric texture, and material highlights. Variation & Randomness: Each edit should be distinctly different from the original and other edited versions. Maintain diversity in the following aspects: Camera angle. Pose type. Which body parts are closest to the lens. Compositional orientation (straight, tilted, top-down, bottom-up, etc.). Avoid repeatedly using the exact same "one foot close to the lens" composition; aim for a rich variety of dynamic poses and camera position changes. Strict Rules: Do not change the person into someone else. Do not change the type of clothing; only alter its appearance through posing, perspective, and the natural movement of the fabric. Do not move the scene to a completely different location; always stay within a reasonable extension of the original place. Do not add text, logos, watermarks, or graphic design elements. Do not change the style to an oil painting, illustration, or anime; a photorealistic effect must be maintained. Overall Goal: Transform the original photograph into a dramatic, photorealistic, ultra-wide-angle shot. The camera position is extreme (including from directly below or above), with one or more body parts pressed against the lens, appearing enormous, while the rest of the body recedes into the distance. The same character appears in a complex, powerful, and fashionable pose within a scene that is consistent with and a natural extension of the original environment.
来源: underwood
怎么用这条提示词
- 1. 复制上面的完整提示词。
- 2. 打开免费生成器,粘贴到提示词输入框。
- 3. 如果提示词需要参考图,先上传参考图,然后生成。
这条提示词是为 Nano Banana Pro 写的,在其他 Nano Banana 模型上同样可用,风格和细节会略有差异。
更多其他提示词
查看全部 →
《泰坦尼克号》模仿
将附图中的人物转换成可爱Q版3D造型 场景:在豪华游轮最顶尖的船头,船头是尖的。 男士带着女士站在泰坦尼克号船头,男士双手搂着女士的腰,女士双臂伸展穿着连衣裙,迎着风,脸上洋溢着自由与畅快。 此时天色呈现出黄昏的暖色调,大海在船下延展。 除了人物用Q版3D造型以外,其他环境都是实物。

1950年代复古风女神
Gemini Nano Banana 3.0 { "prompt_structure": { "subject": { "archetype": "Glamorous woman", "facial_reference": "Use uploaded image features", "pose": "Three-quarter profile, body angled toward camera, arm lifted elegantly near face", "action": "Holding a cigarette between fingers, holding a small metallic lighter in the other hand", "expression_and_mood": "Sultry, confident, seductive, intimate" }, "styling": { "hair": "Voluminous golden-blonde retro waves, sculpted 1950s pin-up bangs, soft curls framing face", "wardrobe": "Black satin backless dress, ultra-thin side straps, dramatic open silhouette revealing waist and hips", "accessories": "Large stacked silver rhinestone bracelets, small metallic lighter", "texture_notes": "Silky satin texture, sparkling rhinestones, glossy lips" }, "composition": { "setting": "Old Hollywood nightlife, smoky vintage-noir atmosphere", "lighting": "Warm, dramatic, low-key, deep shadows, golden highlights on cheekbones", "framing": "Tight portrait framing" }, "technical_specs": { "resolution": "8k ultra-high-resolution", "visual_style": "Hyper-realistic, cinematic, polished", "camera_effects": "Shallow depth of field, soft film-grain texture" } }, "final_prompt_string": "Hyper-realistic 8k portrait of a glamorous woman with [uploaded facial features], vintage-noir style. She stands in three-quarter profile, sultry and confident, wearing a black satin backless dress with ultra-thin side straps revealing her waist. Hair styled in voluminous golden-blonde 1950s retro waves and pin-up bangs. She holds a cigarette elegantly near her face, wearing stacked silver rhinestone bracelets. Warm, dramatic low-key lighting with deep shadows and golden highlights. Smoky, intimate old Hollywood nightlife atmosphere. Shot on ultra-high-resolution camera, shallow depth of field, soft film-grain texture." }

1964与2018:同一房间的对比
> a photo of a bedroom, split down the middle, the left side is 2018, the right side is 1964, it's the same room

3个图像生成的技巧
補足3 画像生成のコツ 「文字数少なめ」で指示すること。 ※nanobananaは文字を詰め込む癖があるため 今回使ったプロンプトと画像↓ Nanobanana-proで5枚作成 アスペクト比16:9 #シーン 広告ポスターを作成 ワイモバイルらしい赤を基調 #内容 新トクするサポート 2年レンタル 支払総額 24円

35mm 胶片风格飞岛
35 毫米胶片风格的照片:莫斯科漂浮在天空中的飞行岛屿上。

3D Q版中式婚礼图
将照片里的两个人转换成Q版 3D人物,中式古装婚礼,大红颜色,背景“囍”字剪纸风格图案。 服饰要求:写实,男士身着长袍马褂,主体为红色,上面以金色绣龙纹图案,彰显尊贵大气 ,胸前系着大红花,寓意喜庆吉祥。女士所穿是秀禾服,同样以红色为基调,饰有精美的金色花纹与凤凰刺绣,展现出典雅华丽之感 ,头上搭配花朵发饰,增添柔美温婉气质。二者皆为中式婚礼中经典着装,蕴含着对新人婚姻美满的祝福。 头饰要求: 男士:中式状元帽,主体红色,饰有金色纹样,帽顶有精致金饰,尽显传统儒雅庄重。 女士:凤冠造型,以红色花朵为中心,搭配金色立体装饰与垂坠流苏,华丽富贵,古典韵味十足。

Q版求婚场景
将照片里的两个人转换成Q版 3D人物,场景换成求婚,背景换成淡雅五彩花瓣做的拱门,背景换成浪漫颜色,地上散落着玫瑰花瓣。除了人物采用Q版 3D人物风格,其他环境采用真实写实风格。

3D Q版大学拟人化形象
给 {西北工业大学} 画一个拟人化的3D Q版美少女形象,体现学校 {航空航天航海三航} 特色

3D 情侣珠宝盒摆件
根据照片上的内容打造一款细致精美、萌趣可爱的3D渲染收藏摆件,装置在柔和粉彩色调、温馨浪漫的展示盒中。展示盒为浅奶油色搭配柔和的金色装饰,形似精致的便携珠宝盒。打开盒盖,呈现出一幕温暖浪漫的场景:两位Q版角色正甜蜜相望。盒顶雕刻着“FOREVER TOGETHER”(永远在一起)的字样,周围点缀着小巧精致的星星与爱心图案。 盒内站着照片上的女性,手中捧着一束小巧的白色花束。她的身旁是她的伴侣,照片上的男性。两人都拥有大而闪亮、充满表现力的眼睛,以及柔和、温暖的微笑,传递出浓浓的爱意和迷人的气质。 他们身后有一扇圆形窗户,透过窗户能看到阳光明媚的中国古典小镇天际线和轻柔飘浮的云朵。盒内以温暖的柔和光线进行照明,背景中漂浮着花瓣点缀气氛。整个展示盒和角色的色调优雅和谐,营造出一个奢华而梦幻的迷你纪念品场景。 尺寸:9:16

折叠式纸雕立体绘本
多层折叠式纸雕立体绘本,放在一张书桌上,背景纯净突出主题,绘本呈现出立体翻页书般的风格,比例为3:2横版。翻开的书页呈现【魔童版哪吒大战敖丙】的场景,所有元素皆可精细折叠组合,呈现出逼真细腻的纸张折叠质感;构图统一采用正面视角,整体视觉风格梦幻唯美,色彩缤纷绚丽,充满奇幻而生动的故事氛围。

3D Q版人物立体相框
将场景中的角色转化为3D Q版风格,放在一张拍立得照片上,相纸被一只手拿着,照片中的角色正从拍立得照片中走出,呈现出突破二维相片边框、进入二维现实空间的视觉效果。

3D Q版情侣水晶球
将附图中的人物转换成水晶球场景。 整体环境:水晶球放在窗户旁桌面上,背景模糊,暖色调。阳光透过球体,洒下点点金光,照亮了周围的黑暗。 水晶球内部:人物是可爱Q版3D造型,相互之间满眼的爱意。