GPT影像2街道摄影

Experimental street photography output using GPT Image 2, although the prompt is target-specific for another tool.

提示：

{ "generation_request": { "meta_data": { "tool": "NanoBanana Pro", "task_type": "photoreal_artistic_street_photography", "version": "v1.0_STREET_ART_REALISM_SER_EN", "priority": "highest" }, "output_settings": { "aspect_ratio": "4:5", "orientation": "portrait", "resolution_target": "ultra_high_res", "render_style": "ultra_photoreal_candid_film_still", "sharpness": "crisp_but_natural", "film_grain": "subtle_35mm", "color_grade": "restrained_cinematic_realism", "dynamic_range": "natural_not_hdr", "skin_rendering": "real_texture_no_retouch" }, "creative_prompt": { "scene_summary": "纪录片风格的 Candid 街头摄影，在 [城市/邻区] 实地拍摄。一个未经脚本、未经摆拍的时刻，感觉情感真诚且视觉真实。", "subject": "一个 [年龄] [性别] 穿着 [服装]，在动作中捕捉：[微动作]。完全自然的面部表情，轻微不对称保持完整。", "camera": "35mm 镜头等效，水平视角，近距离但尊重距离，故意不完美的构图如同真实街头摄影师，眼睛锐利聚焦，浅到中等景深。", "lighting": "有机动机的自然光，来源于 [来源：商店窗户 / 街灯 / 日落 / 霓虹灯]，深度阴影仍保持细节，零摄影棚灯光。", "environment_details": "真实城市纹理：剥落海报、刮伤凹陷金属、雨点路面、微妙玻璃反射、真实城市杂乱无清理背景。", "authenticity_markers": "仅背景元素轻微运动模糊，明亮高光柔和晕影，轻微电影门摆动，全片逼真颗粒，完全无美颜修图。", "mood": "[情绪：忧郁 / 充满希望 / 紧张 / 安静喜悦]，电影感但完全可信。" }, "negative_prompt": [ "摄影棚灯光", "美颜修图", "塑料皮肤", "过度锐化", "HDR", "AI 发光", "完美对称", "过度干净背景", "假散景形状", "文本", "标志", "水印", "画风", "卡通" ] } }

机器翻译 — 实际生成作品的是原文提示词。

✨ 生成 收藏 复制提示词 分享 原始帖子 在 Hitboard 打开