Cinel AI
灵感库
全部灵感浏览全部作品人像写真产品与电商海报与平面设计信息图与 UI3D 角色与手办美食饮品插画与动漫创意场景
AI 图片
免费 AI 图片生成器从文字提示词创作图片文生图生成器从文字提示词创作图片AI 图生图生成器根据参考图生成图片AI 图片编辑器用文字编辑已有图片背景移除即时移除图片背景图片放大图片放大 2 倍或 4 倍AI 扩图扩展图片原有边界
AI 视频
AI 视频生成器打开视频生成工作台文生视频生成器从文字提示词创作视频图生视频让参考图片动起来
AI 模型

图片模型

FLUX.2 Klein 4BFLUX.2 Klein 极速生图,支持提示词与参考图。KolorsKolors 免费生图,支持提示词与参考图。Seedream 4.0低成本 1K、2K、4K 生成,支持多参考图编辑。Seedream 4.54K 生成、文字渲染与参考图编辑。Seedream 5.0 Lite电影感 3K 写实,支持多参考图创意控制。Seedream 5 Pro提供 1K 快速、1.5K 轻量和 2K 专业视觉,支持文字与多参考图控制。GPT Image 2精准理解提示词,文字清晰,适合产品视觉。GPT Image 2.5更快的 GPT 图像生成,编辑更准,主体更稳定。Nano Banana 2 Lite快速 1K 生成与编辑,适合高频迭代。Nano Banana 2多参考图编辑与快速风格控制。Nano Banana Pro4K 渲染与高级图像编辑。Nano Banana轻量 Gemini 编辑,适合快速修改。Nano Banana 2.1最新一代 Nano Banana 生成与多参考图编辑。

视频模型

Seedance 1.0 Turbo快速视频生成,动作流畅,最高 1080p。Seedance 2.54–30 秒视频,支持同步音频、480p 或 720p。Seedance 2.0 Mini低成本 4–15 秒视频,支持同步音频、480p 或 720p。Seedance 2.04–15 秒视频,支持 Fast/Standard,最高 1080p。MiniMax H3高质量 4–15 秒视频,支持首帧和多图参考。Kling 3.0强动态、运镜与可选声音,最高 4K。Kling 3.0 Turbo更快的 3–15 秒视频,支持 720p、1080p 和首帧输入。Kling O1Kling O1 图片转视频,支持首帧和可选尾帧。Kling O3Kling O3 文生视频与首尾帧生成,最高支持 4K。Grok Imagine Video 1.06–30 秒测试版视频,支持 Fun、Normal 和 Spicy 风格模式。Grok Imagine Video 1.51–15 秒视频,支持原生音频和最多 7 张参考图。Wan 2.55–10 秒文生或单图生视频,支持原生音频。Wan 2.62–15 秒多镜头视频,支持原生音频和 720p、1080p。Wan 2.72–15 秒视频,支持文字、首尾帧和最多三张参考图。Veo 3.1 Fast稳定版 Veo 3.1 Fast,支持 4–8 秒视频、音频和首尾帧输入。Veo 3.1 Pro稳定版 Veo 3.1 Pro,支持 4–8 秒视频、音频和首尾帧输入。Veo 3.1 Fast BetaFast Beta 固定 8 秒视频,支持首尾帧或三张参考图。Veo 3.1 Pro BetaPro Beta 固定 8 秒视频,支持首尾帧输入。
价格
  1. 灵感库
  2. 创意场景
  3. 废弃教室对决余波关键帧

废弃教室对决余波关键帧

Cinematic 30-second 16:9 live-action fight scene, 24fps, realistic gritty Korean-thriller look. Setting: . Teal-green chalkboard, worn grey concrete floor, wooden desks and chairs, a brown leather sofa, wooden cabinets, cold flickering fluorescent tube lights, dusty air, desaturated green-teal color grade, handheld camera with fast whip-pans, heavy impacts, natural film grain.

MAIN CHARACTER: a young woman in a black baseball cap pulled low over her eyes, long black ponytail, fitted black long-sleeve top, black pants, dark glossy sleeves/arm wraps. Cold, emotionless face, calm and silent the whole time. Her face, cap, hairstyle and outfit stay identical in every shot (character lock).

0-4s: Medium two-shot. She stands with head down, cap hiding her eyes. A huge, bald, shirtless bodybuilder with a gold chain walks up grinning arrogantly. Behind them, a crowd of students and men watches from the classroom. He reaches out and pushes her shoulder mockingly. She does not react. The camera pushes slowly toward her face.

5-7s: High-angle shot. The bald giant has been smashed onto the teacher's desk, then crashes onto the floor next to a fallen green chalkboard, arms spread, motionless. Papers, books and a bottle scatter across the floor.

8-9s: A second shirtless man in grey sweatpants charges at her. She spins into a high roundhouse kick to his face. A chair flies through the air. He slams into the wall and slides down it, dazed.

10-12s: A bearded man in a dark jacket rushes her. She catches his arm, drops her hips and flips him over her back in a fast motion-blurred throw. He crashes onto the desks. Papers explode into the air.

13-15s: Near the brown leather sofa, another dark-jacketed man grabs her. A bottle shatters over his head in a burst of water and glass in slow-motion. He collapses onto the sofa, unconscious.

16-17s: Slow-motion shot. She turns sharply, her ponytail whips through the frame. She walks forward calmly through the wrecked room, toppled chairs around her.

18-24s: The last and strongest enemy, a tall man in an olive-khaki jacket, charges in with a roar. He lands one hit that splits his own lip, with blood on his mouth. She absorbs it, then fights back with a quick close-range combination: elbow, knee to the ribs, grab and throw. She pins his arm, drives him down onto a desk, and he falls hard onto the floor. Fast cuts, heavy impacts, chairs and papers flying, debris and dust in the air.

25-30s: Slow wide shot of the aftermath. Defeated men lie scattered across the floor among overturned chairs and papers. Thin dust and smoke hang under the flickering lights. She stands in the middle, adjusts her cap and wipes her sleeve. She lifts her head and stares at the camera with a cold, expressionless face. Hold on her face. End.

Audio: heavy punches, kicks and body impacts, breaking wood and glass, a deep low cinematic drone, almost no dialogue, final silence with faint buzzing of the lights.

Keep it fully photorealistic. No text, no subtitles, no watermark, no cartoon or anime look, no face change, no outfit change. (prompt shared in the reply to the video post)
Cinematic live-action thriller video keyframe, widescreen 16:9, realistic gritty Korean-thriller look: an old, run-down school classroom at night with a teal-green chalkboard, worn grey concrete floor, overturned wooden desks and chairs, a brown leather sofa and wooden cabinets, loose papers frozen mid-air and thin dust hanging under cold flickering fluorescent tubes. In the middle stands a fictional young woman in a black baseball cap pulled low over her eyes, her long black ponytail whipping mid-turn, fitted black long-sleeve top, black pants and dark glossy arm wraps, cold emotionless face, calm after the fight. Desaturated green-teal colour grade, slow-motion feel, natural film grain, handheld camera at waist height. No other people, no blood, no weapons, no text, no subtitles, no logo. Widescreen 16:9 composition.
  • Rewrote the Seedance 2.5 video prompt as one widescreen 16:9 key-frame still (kept the video's aspect); removed brands, logos, violence/IP elements and any reference-image dependency

cinel 为生成示例图做了以上替换。

会员 1K 2 积分,每日积分 4。 比例 16:9。

ratio 16x9text only电影感写实复古video sourced

参数

分类创意场景
画面比例16:9
输入纯文本
示例图模型GPT Image 2.5
推荐模型GPT Image 2, Nano Banana 2, Seedream 5 Pro
原作者@Alina_with_Ai · X 原帖
原帖模型seedance-2.5

这条提示词为什么有效

根据 @Alina_with_Ai 于 2026-10-18 的视频帖改写(记录时 237 赞)。我们改成一张干净的16:9宽屏关键帧,去掉品牌和Logo,也不需要你的照片。一次只改一个变量。

如何改写

变量作用示例
an old, run-down school classroom at night场景地点雨夜废弃停车场, 打烊后空无一人的霓虹游戏厅

使用提示

  • 从视频提示词中挑一个高光瞬间,定格为单帧。
  • 一次只改一个变量,画面才易读。
  • 保留原视频的16:9宽屏画幅,并要求画面无文字。

相关推荐

发光蜗牛日落水面壁纸1:1发光蜗牛日落水面壁纸@churvikv
2003年DV摄像机商场冰淇淋约会关键帧16:92003年DV摄像机商场冰淇淋约会关键帧@AIwithkhan
不等电梯的不可能楼梯关键帧16:9不等电梯的不可能楼梯关键帧@umesh_ai
万圣节摄像机骷髅斗舞关键帧9:16万圣节摄像机骷髅斗舞关键帧@Just_sharon7
敞开窗外海岸风景画1:1敞开窗外海岸风景画@AllaAisling
拧不开果酱盖的酥皮世界关键帧16:9拧不开果酱盖的酥皮世界关键帧@umesh_ai
动漫雨夜阳台咖啡关键帧9:16动漫雨夜阳台咖啡关键帧@JohnSmith5912
行李箱变形飞行摩托关键帧16:9行李箱变形飞行摩托关键帧@Aiminithoughts
膨胀果汁瓶立体字产品海报1:1膨胀果汁瓶立体字产品海报@ou_zhen599
小乌龟树叶滑翔山谷关键帧16:9小乌龟树叶滑翔山谷关键帧@AIwithWania
条纹光影油画人像1:1条纹光影油画人像@AllaAisling
雨夜咖啡馆熔岩巧克力蛋糕1:1雨夜咖啡馆熔岩巧克力蛋糕@Nokiardnv
← 上一条万圣节摄像机骷髅斗舞关键帧下一条 →发光蜗牛日落水面壁纸
1× · 1K
Cinel AI

Cinel 是免费的无限 AI 文生图生成器,提供提示词图片编辑和 AI 图生视频工具。无需注册即可创作图片,使用 GPT Image 2、Seedream 5 Pro 和 Nano Banana 2 编辑,再使用 Seedance 2.5、Veo 3.1 和 Kling 3.0 将静态画面变成视频。

产品免费 AI 图片生成器AI 视频生成器图片模板工作台文生图生成器图生图文生视频生成器图生视频AI 图片编辑背景移除
灵感库全部灵感人像写真产品与电商海报与平面设计信息图与 UI3D 角色与手办美食饮品插画与动漫创意场景GPT Image 2.5 提示词Nano Banana 2.1 提示词来源与下架

AI 图片模型

FLUX.2 Klein 4BKolorsSeedream 4.0Seedream 4.5Seedream 5.0 LiteSeedream 5 ProGPT Image 2GPT Image 2.5Nano Banana 2 LiteNano Banana 2Nano Banana ProNano BananaNano Banana 2.1

AI 视频模型

Seedance 1.0 TurboSeedance 2.5Seedance 2.0 MiniSeedance 2.0MiniMax H3Kling 3.0Kling 3.0 TurboKling O1Kling O3Grok Imagine Video 1.0Grok Imagine Video 1.5Wan 2.5Wan 2.6Wan 2.7Veo 3.1 FastVeo 3.1 ProVeo 3.1 Fast BetaVeo 3.1 Pro BetaSora 2
公司价格关于我们联系我们support@cinel.ai隐私条款可接受使用政策
© 2026 Cinel AI。保留所有权利。