图像 · 21:9
适用于 ChatGPT, Nano Banana, Qwen-Image, Midjourney, Flux

电影感人像

一张像电影画面的人像:宽银幕变形镜头构图,背景里有实景灯光,青橙色调调色。

即拿即用。

同一套设置,按每个模型最擅长理解的方式写好。

ChatGPT / GPT Image

124 个词
在 Higgsfield 上试用 GPT Image 2 推广链接
Generate one photorealistic horizontal cinematic film still. Cinematic film still, photorealistic. Waist-up medium shot, horizontal 21:9 frame. The subject is an original fictional adult woman, 30s in appearance, pose: seated or reclined, gaze looking away from camera, expression: pensive. Shoulder-length copper red hair. Wearing a cream trench coat. Set in a cafe, night, rainy, wet reflections, background blurred bokeh city lights, mood melancholic, dramatic. Neon colored lighting, color temperature mixed warm and cool, reflections on surfaces. Shot on a cinema camera (ARRI Alexa), anamorphic 50mm lens, shallow depth of field, creamy bokeh. Teal and orange cinematic grade. Avoid: CGI, 3D render, illustration, anime, plastic skin, over-smoothed face, text, captions, watermarks, logos, UI overlays, extra fingers, deformed hands, distorted anatomy, heavy studio lighting, large smile.
非常擅长处理长篇结构化 JSON。 更多 ChatGPT 技巧
请我喝杯咖啡