Cinel AI
靈感庫
全部靈感瀏覽全部作品人像寫真產品與電商海報與平面設計資訊圖與 UI3D 角色與公仔美食飲品插畫與動漫創意場景
AI 圖片
免費 AI 圖片生成器從文字提示詞創作圖片文生圖生成器從文字提示詞創作圖片AI 圖生圖生成器根據參考圖生成圖片AI 圖片編輯器用文字編輯已有圖片背景移除即時移除圖片背景圖片放大圖片放大 2 倍或 4 倍AI 擴圖擴充套件圖片原有邊界
AI 影片
AI 影片生成器開啟影片生成工作臺文生影片生成器從文字提示詞創作影片圖生影片讓參考圖片動起來
AI 模型

圖片模型

FLUX.2 Klein 4BFLUX.2 Klein 極速生圖,支援提示詞與參考圖。KolorsKolors 免費生圖,支援提示詞與參考圖。Seedream 4.0低成本 1K、2K、4K 生成,支援多參考圖編輯。Seedream 4.54K 生成、文字渲染與參考圖編輯。Seedream 5.0 Lite電影感 3K 寫實,支援多參考圖創意控制。Seedream 5 Pro提供 1K 快速、1.5K 輕量和 2K 專業視覺,支援文字與多參考圖控制。GPT Image 2精準理解提示詞,文字清晰,適合產品視覺。GPT Image 2.5更快的 GPT 影象生成,編輯更準,主體更穩定。Nano Banana 2 Lite快速 1K 生成與編輯,適合高頻迭代。Nano Banana 2多參考圖編輯與快速風格控制。Nano Banana Pro4K 渲染與高階影象編輯。Nano Banana輕量 Gemini 編輯,適合快速修改。Nano Banana 2.1最新一代 Nano Banana 生成與多參考圖編輯。

影片模型

Seedance 1.0 Turbo快速影片生成,動作流暢,最高 1080p。Seedance 2.54–30 秒影片,支援同步音訊、480p 或 720p。Seedance 2.0 Mini低成本 4–15 秒影片,支援同步音訊、480p 或 720p。Seedance 2.04–15 秒影片,支援 Fast/Standard,最高 1080p。MiniMax H3高質量 4–15 秒影片,支援首幀和多圖參考。Kling 3.0強動態、運鏡與可選聲音,最高 4K。Kling 3.0 Turbo更快的 3–15 秒影片,支援 720p、1080p 和首幀輸入。Kling O1Kling O1 圖片轉影片,支援首幀和可選尾幀。Kling O3Kling O3 文生影片與首尾幀生成,最高支援 4K。Grok Imagine Video 1.06–30 秒測試版影片,支援 Fun、Normal 和 Spicy 風格模式。Grok Imagine Video 1.51–15 秒影片,支援原生音訊和最多 7 張參考圖。Wan 2.55–10 秒文生或單圖生影片,支援原生音訊。Wan 2.62–15 秒多鏡頭影片,支援原生音訊和 720p、1080p。Wan 2.72–15 秒影片,支援文字、首尾幀和最多三張參考圖。Veo 3.1 Fast穩定版 Veo 3.1 Fast,支援 4–8 秒影片、音訊和首尾幀輸入。Veo 3.1 Pro穩定版 Veo 3.1 Pro,支援 4–8 秒影片、音訊和首尾幀輸入。Veo 3.1 Fast BetaFast Beta 固定 8 秒影片,支援首尾幀或三張參考圖。Veo 3.1 Pro BetaPro Beta 固定 8 秒影片,支援首尾幀輸入。
價格
  1. 靈感庫
  2. 創意場景
  3. 廢棄教室對決餘波關鍵幀

廢棄教室對決餘波關鍵幀

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 為生成示例圖做了以上替換。

會員 1K 2 積分,每日積分 4。 比例 16:9。

ratio 16x9text only電影感寫實復古video sourced

引數

分類創意場景
畫面比例16:9
輸入純文字
示例圖模型GPT Image 2.5
推薦模型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

這條提示詞為什麼有效

根據 @Alina_with_Ai 於 2026-10-18 的影片帖改寫(記錄時 237 贊)。我們改成一張乾淨的16:9寬屏關鍵幀,去掉品牌和Logo,也不需要你的照片。一次只改一個變數。

如何改寫

變數作用示例
an old, run-down school classroom at night場景地點雨夜廢棄停車場, 打烊後空無一人的霓虹遊戲廳

使用提示

  • 從影片提示詞中挑一個高光瞬間,定格為單幀。
  • 一次只改一個變數,畫面才易讀。
  • 保留原影片的16:9寬屏畫幅,並要求畫面無文字。

相關推薦

發光蝸牛日落水面桌布1:1發光蝸牛日落水面桌布@churvikv
2003年DV攝像機商場冰淇淋約會關鍵幀16:92003年DV攝像機商場冰淇淋約會關鍵幀@AIwithkhan
不等電梯的不可能樓梯關鍵幀16:9不等電梯的不可能樓梯關鍵幀@umesh_ai
萬聖節攝像機骷髏鬥舞關鍵幀9:16萬聖節攝像機骷髏鬥舞關鍵幀@Just_sharon7
敞開窗外海岸風景畫1:1敞開窗外海岸風景畫@AllaAisling
擰不開果醬蓋的酥皮世界關鍵幀16:9擰不開果醬蓋的酥皮世界關鍵幀@umesh_ai
動漫雨夜陽臺咖啡關鍵幀9:16動漫雨夜陽臺咖啡關鍵幀@JohnSmith5912
行李箱變形飛行摩托關鍵幀16:9行李箱變形飛行摩托關鍵幀@Aiminithoughts
膨脹果汁瓶立體字產品海報1:1膨脹果汁瓶立體字產品海報@ou_zhen599
小烏龜樹葉滑翔山谷關鍵幀16:9小烏龜樹葉滑翔山谷關鍵幀@AIwithWania
條紋光影油畫人像1:1條紋光影油畫人像@AllaAisling
雨夜咖啡館熔岩巧克力蛋糕1:1雨夜咖啡館熔岩巧克力蛋糕@Nokiardnv
← 上一條萬聖節攝像機骷髏鬥舞關鍵幀下一條 →發光蝸牛日落水面桌布
1× · 1K
Cinel AI

Cinel 是免費的無限 AI 文生圖生成器,提供提示詞圖片編輯和 AI 圖生影片工具。無需註冊即可創作圖片,使用 GPT Image 2、Seedream 5 Pro 和 Nano Banana 2 編輯,再使用 Seedance 2.5、Veo 3.1 和 Kling 3.0 將靜態畫面變成影片。

產品免費 AI 圖片生成器AI 影片生成器圖片模板工作臺文生圖生成器圖生圖文生影片生成器圖生影片AI 圖片編輯背景移除
靈感庫全部靈感人像寫真產品與電商海報與平面設計資訊圖與 UI3D 角色與公仔美食飲品插畫與動漫創意場景GPT Image 2.5 提示詞Nano Banana 2.1 提示詞來源與下架

AI 圖片模型

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 影片模型

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
公司價格關於我們聯絡我們support@cinel.ai隱私條款可接受使用政策
© 2026 Cinel AI。保留所有權利。