Makernice
← 产品与美食视频提示词

在家自拍做拿铁的早晨 vlog

产品与美食 · Seedance 2.5 · @Strength04_X ·

这是一条 30 秒文生视频提示词,生成一位年轻男子在家自拍做拿铁的随手 vlog:磨粉、压粉、萃取两股浓缩咖啡、打奶、拉花,最后喝一口、用手盖住镜头,接一小段黑屏。逐个镜头对应博主发布的成片。

原作成片:@Strength04_X · 原帖 ↗

在 Makernice 上的费用

$7.776

Seedance 2.5 · 文生视频 · 720p · 30 秒 × $0.2592/秒

  • 480p$3.45888
  • 720p$7.776
  • 1080p$19.2456
  • 4k$58.65
  • 失败、超时、排队中取消:冻结金额全额释放。 了解规则
  • 先报价:报价免费,锁定 12 分钟,按报价扣费。 接口文档
  • 成片被输出审核拦截照常扣费,可申请人工复核。

价格截至 2026 年 11 月 3 日(价表 v12)。

提示词

自己拍的早晨咖啡 vlog,30 秒,16:9,九个镜头,最后接一小段黑屏,明亮柔和的日光透过白色窗帘。 角色:一位二十五岁左右的年轻男子,原创虚构人物,浅棕色头发乱蓬蓬的,没有胡子,穿一件纯黑色圆领 T 恤;沉稳专注,对着镜头时带点俏皮。 场景:一间白色小厨房,白色橱柜,浅色带斑点的台面,窗户挂着白色薄纱窗帘。台面上有:一台拉丝不锈钢意式咖啡机,自带磨豆器,顶上是黑色豆仓;两个不锈钢奶缸;一块黑色压粉垫;一只外面红棕色釉、里面白色的杯子。 画面质感:一台小型广角相机,有时他把它架在台面上,有时自己拿在手里;轻微桶形畸变,贴着台面的低机位,轻微晃动,偶尔有运动模糊,色彩柔和自然,像个人 vlog 而不是广告。 0-3 秒:相机低低地架在台面上:他伸手去弄咖啡机,然后凑近镜头,轻声说:「早晨的咖啡,就得这么做。」 3-6 秒:从磨豆器出粉口下方往上拍的低机位特写:新磨的咖啡粉落进手柄粉碗,慢慢堆起来。 6-9.5 秒:隔着压粉垫的低机位特写:他用压粉锤用力压实粉碗里的咖啡粉,专注的脸就在手后面,背景里一个不锈钢奶缸是虚的。 9.5-12 秒:侧面中景:他把手柄拧进冲煮头,然后转向镜头:「开始了。」 12-15 秒:贴着滴水盘的低机位细节镜头:两股细细的浓缩咖啡从出液口流进杯子,油脂慢慢积起来。 15-18 秒:顺着台面拍的中景:他站在咖啡机旁,看了一眼镜头,说「该打奶了」,把牛奶从一个不锈钢奶缸倒进另一个。 18-21 秒:往奶缸里看的微距镜头:蒸汽棒的喷头把牛奶搅成一个泛着光泽、带细密奶泡的漩涡。 21-24 秒:贴着台面的镜头:一道细细的牛奶落进杯中,在油脂上拉出一个层层叠叠、像郁金香的图案。 24-28.5 秒:手持近景:他双手捧着杯子,闭着眼慢慢喝了一口,放低杯子,笑着说:「这正是我需要的。」然后仍拿着杯子,说「回头见」,伸手朝镜头够过来,直到手掌把镜头盖住。 28.5-30 秒:黑屏,几乎没有声音。 声音:磨豆器的嗡嗡声、压粉时闷闷的一声、手柄扣紧的咔哒声、浓缩咖啡滴落、倒牛奶、蒸汽棒的嘶嘶声和杯子轻碰的叮一声;他说话的声音轻松随意,音量不大。画面上不要渲染任何文字、字幕或水印。

中文由 Makernice 翻译,英文提示词附在下方。

英文提示词
Self-filmed morning coffee vlog, 30 seconds, 16:9, nine shots followed by a short black screen, bright soft daylight through white curtains. Character: a young man in his mid-twenties, an original fictional character, with tousled light brown hair, clean-shaven, wearing a plain black crew-neck T-shirt; calm and focused, a little playful with the camera. Setting: a small white kitchen with white cabinets, a pale speckled countertop and a window behind sheer white curtains. On the counter: a brushed stainless-steel espresso machine with a built-in grinder and a black bean hopper on top, two steel milk pitchers, a black tamping mat and a cup glazed reddish-brown outside and white inside. Camera look: a small wide-angle camera that he either props on the counter or holds himself; slight barrel distortion, low counter-level angles, gentle wobble, occasional motion blur and soft natural colour, like a personal vlog rather than an advert. 0-3s: camera propped low on the counter: he reaches over to the machine, then leans close to the lens and says quietly, "Morning coffee, the proper way." 3-6s: low close-up looking up beneath the grinder spout: fresh grounds pour down into the portafilter and heap up. 6-9.5s: low close-up across the mat: he presses the tamper firmly into the portafilter, his concentrating face just behind his hand, a steel jug blurred in the background. 9.5-12s: side medium shot: he twists the portafilter into the group head, then turns to the camera: "Here we go." 12-15s: low detail shot at drip-tray level: two thin streams of espresso run from the spouts into the cup as the crema builds. 15-18s: medium shot from along the counter: standing by the machine, he glances at the camera, says "Time for the milk," and pours milk from one steel jug into the other. 18-21s: macro looking down into the pitcher: the steam wand tip spins the milk into a glossy whirlpool of fine foam. 21-24s: counter-level shot: a thin ribbon of milk falls into the cup and draws a layered tulip-like pattern on the crema. 24-28.5s: close handheld shot: holding the cup in both hands, he takes a slow sip with his eyes closed, lowers it, smiles and says, "That's exactly what I needed." Still holding the cup, he says "See you later" and reaches toward the lens until his palm covers it. 28.5-30s: black screen, almost silent. Sound: grinder whirr, the dull knock of tamping, the click of the portafilter locking in, espresso trickling, milk pouring, the hiss of the steam wand and a soft cup clink; his voice is quiet and casual. Do not render any text, subtitles or watermark on screen.

让 AI 智能体来跑

  1. 创建一个单独设了花费上限的 API Key。
  2. 复制智能体说明,粘贴到 Claude Code、Codex 等编程智能体里。
  3. 智能体先报价、等你确认,再带幂等键创建并轮询,直到视频生成完成。

为什么这样改

博主的分镜和发布的成片是同一套做咖啡流程,但有几处细节不同。原文写的是主角自己拍摄(用了指女性的「herself」),描述的却是一位年轻男子;成片里是年轻男子。原文要求柔和、带颗粒的迷你 DV 磁带画质,成片看起来是干净的广角相机画面,只有轻微晃动。原文排了十个均匀的 3 秒节拍;成片是九个长短不一的镜头,他用手盖住镜头后还有约 1.5 秒黑屏。磨粉镜头是从出粉口下方往上拍,不是俯拍;不是把冷牛奶倒进奶缸,而是把牛奶从一个不锈钢奶缸倒进另一个;喝咖啡和道别合在最后一个镜头里。台词从画面上无法确认,所以四句话都保留在他明显在说话的位置。本站适配版按成片写,并保留结尾的黑屏。发布文件为 1280×720、约 30 秒,正好对应一次 30 秒、16:9、720p 的 Seedance 2.5 文生视频。

原提示词

@Strength04_X · 2,234 字符
CAMERA / LOOK: Handheld mini DV camcorder footage filmed by the subject herself. Slight hand shake, occasional focus hunting, imperfect framing, natural zoom adjustments, soft tape-like image quality, subtle grain, realistic auto-exposure shifts from bright kitchen morning light. Natural skin tones, mild motion blur, authentic consumer camcorder aesthetic. STYLE: Cozy coffee-prep vlog with gentle ASMR elements. Relaxed pacing, minimal dialogue, candid moments. Focus on satisfying sounds: bean grinder whirring, portafilter tamping, steam wand hissing, cup clinking, milk frothing. SUBJECT: Young man in his mid-20s, plain t-shirt, hair slightly tousled, minimal accessories. Calm, focused energy while making his morning coffee. SETTING: Small kitchen counter with an espresso machine on a bright morning. Natural daylight, coffee beans and a mug nearby, quiet atmosphere. STORYBOARD: → (3s, propped medium shot) Places camera on the counter, switches on the machine. "Morning coffee, the proper way." → (3s, overhead shot) Grinds fresh coffee beans, fine grounds falling into the portafilter. → (3s, close-up) Tamps the grounds down firmly and evenly. → (3s, handheld shot) Locks the portafilter into the machine. "Here we go." → (3s, detail shot) Espresso streams slowly into a small cup. No dialogue. → (3s, medium shot) Pours cold milk into a small steel pitcher. "Time for the milk." → (3s, macro shot) Steam wand hissing as it froths the milk. → (3s, propped shot) Pours frothed milk carefully over the espresso, forming light layers. → (3s, warm ending shot) Holds the finished cup, takes a small sip, satisfied smile. "That's exactly what I needed." → (3s, final shot) Reaches toward camera, still holding the cup. "See you later." Hand covers lens as recording ends. AUDIO NOTES: Natural kitchen ambience — grinder whirring, tamping, steam hissing, milk pouring should be clearly audible. Dialogue quiet and casual. REALISM NOTES: Authentic body language, natural blinking, genuine focused smiles, occasional careful pauses while pouring, imperfect framing, focus breathing, bright morning light shifts. Should resemble a genuine personal coffee vlog on a consumer camcorder, not a commercial or AI-generated production.

原帖 ↗

分镜拆解

主体
一位二十五岁左右、浅棕色头发乱蓬蓬、穿纯黑 T 恤的原创年轻男子,以及他的器具:自带磨豆器的不锈钢意式咖啡机、两个不锈钢奶缸、黑色压粉垫,和一只外面红棕色、里面白色的杯子。
动作
按顺序完整做一杯拿铁:对镜头打招呼,咖啡粉落进手柄,用力压粉,扣上手柄,萃取浓缩,在两个奶缸之间倒牛奶,打奶,拉花,最后喝一口,用手掌盖住镜头收尾。
镜头
九个长短不一的镜头,大约在第 3、6、9.5、12、15、18、21、24 秒切换,最后是 1.5 秒黑屏。多数机位贴着台面、用广角拍;蒸汽棒的微距和喝咖啡的近景把镜头直接凑到动作跟前。
风格
自制、不加修饰的 vlog 画面,场景是明亮的白色厨房:窗帘透进柔和的光,轻微广角畸变,手持晃动,色彩自然,刻意不拍成广告的样子。
声音
咖啡吧 ASMR:磨豆器的嗡嗡声、压粉的闷响、手柄的咔哒声、浓缩咖啡滴落、倒牛奶、蒸汽棒的嘶嘶声和杯子轻碰声,外加四句简短、轻声的话。

推荐参数

模型
Seedance 2.5
时长
30 秒
画幅
16:9
分辨率
720p

改成你自己的

  • 每句台词都用引号写在他说话的那个镜头里;如果声音跑到了别的镜头上,只保留开头和结尾两句,中间几个镜头只留机器声。
  • 想做馥芮白或卡布奇诺,只改「21-24 秒」的拉花和杯子描述;磨粉、压粉、打奶这几拍对任何奶咖都一样。
  • 如果想停在笑容上而不是黑屏,删掉「28.5-30 秒」那一行,把喝咖啡的镜头拉长到第 30 秒,并去掉盖住镜头的动作。

常见问题

这段拿铁 vlog 最长只能 30 秒吗?

单次请求是的:Seedance 2.5 每次生成 4 到 30 秒,这条提示词已经用满 30 秒。想加内容,比如清洁咖啡机或再做一杯,就另外生成一段,重复同样的角色和场景两行。想接得顺,可以截取上一段结尾的一张静帧,作为 i2v 模式的起始图。

咖啡的特写镜头能用 4K 生成吗?

可以。Seedance 2.5 提供 480p、720p、1080p 和 4K,本页用的是默认的 720p。油脂和奶泡的微距镜头在 1080p 或 4K 下提升最明显,不过画面越清晰,离提示词想要的自制 vlog 感就越远。

能把我自己的脸和厨房放进这段 vlog 吗?

纯文生视频的话,就在角色和场景两行里用文字描述。如果你有照片,Seedance 2.5 还有最多接受 16 张图的 r2v 模式,以及从单张静图起步的 i2v 模式;两者支持的画幅和文生视频相同。

来源与版权

本页视频与原提示词来自 X 上 @Strength04_X 的公开帖子,版权归原作者所有,仅作学习参考。 在 X 上查看

如涉及版权问题,请联系 support@makernice.com,我们会尽快处理。

更多产品与美食提示词