设置: 食物渴望发布影片

视频内容由提示@ultimaxbt创建。请添加您的详细信息——它们将被添加到提示中。

初始提示 @ultimaxbt

请告诉我您需要什么：我的产品、用户输入的确切请求、用于结果卡片的 6 到 8 张照片、一首 130 BPM左右、带有清晰副歌的免版税歌曲（Mixkit，可免费商用），以及用于结尾卡片的我的品牌标识。如果我省略了任何内容，则使用默认设置：以下点餐故事、来自 Pexels 的食物照片（火鸡面、墨西哥牛肉卷饼、辣鸡、水牛城鸡翅、碎牛肉汉堡、辣拉面），以及 Mixkit 的“Cat Walk”素材。

一段15秒的产品发布短片，1920x1080分辨率，60帧/秒。仅2D，一镜到底。无淡入淡出、模糊或剪辑：每个场景都由前一个场景逐渐展开。文字从遮罩线中升起，按钮扩展成页面，色彩从一个物体涌出，然后逐渐缩小到另一个物体。每个场景仅使用一次平移镜头，切勿连续放大和缩小。

外观：暖白色画布 (#f5f5f2)、黑色 UI (#0e0e10)、浅绿色点缀 (#cdf24f)、橙色 (#ff6a2a) 和蓝色发送按钮 (#2f6bff)。在输入框周围添加类似 Apple Intelligence 的炫彩光晕：模糊的圆锥形渐变，依次呈现粉色、橙色、浅绿色、青色和紫色。深色卡片上使用真实的食物照片，UI 使用Geist，结尾卡片上的产品名称使用衬线字体。

禁止使用：淡入淡出、模糊效果、3D、粒子效果、反向镜头移动、持续时间超过 1 秒、任何感觉像模板的东西。

每分钟 130 BPM，32 拍（14.8 秒）。在歌曲高潮前 12 拍开始播放。

节拍 0-6，请求：缓慢推入发光的作曲器，放大约 3 倍。以自然的击键节奏，在三行固定的行上输入请求：
“我真的很饿，我不知道
我想要的，但有些东西
香辣酥脆，饱腹感强”

按下发送键，即可发送消息。屏幕上会泛起一道青柠色的涟漪，将消息变成聊天气泡。向后拉一下即可显示周围的手机（428x900 屏幕，11px 黑色边框，9:41 状态栏）。

在第 6 到 12 拍，想象一下：发送按钮变成了一个橙色的炒锅，一个带有细长把手的半圆盘。在第 8、9、10 和 11 拍，它会在闪闪发光的文字“正在为你寻找……”下方抛出 6 种色彩缤纷的食材。

第 12 拍，即落差：一个青柠色的圆圈从炒锅中扩展，约 0.35 秒后充满整个画面。深色的食物卡片（330x440，半径 28，顶部有照片，下方有名称、一行描述、价格和评分）从中心弹出。滑动条穿过三张卡片，最终停在“火鸡面”上，卡片上会弹出一个“最佳匹配”药丸。

第 16-21 拍，聊天：青柠缩回用户的气泡中，带着文字，同时选中的卡片飞入对应的位置。“找到了。Wok & Fire 的火鸡面，烟熏味浓郁，辣味十足，而且分量超足。” 出现，接着是“要我帮你点吗？” 然后显示两个提示框：“立即订购”（黑色）和“更多选项”（带边框）。光标点击“立即订购”→ 旋转图标 → “✓ 已订购”。

第21-32拍，结尾：黑色按钮向页面扩展，保持药丸形状直至边缘，同时镜头推近。按钮上的标签放大至标题大小，然后滑落。逐字显示“你渴望面条。”和“现在它正在路上。”（92像素，黑底白字）。一个快递点沿着路线指向一个图钉。图钉变成品牌标识，其后的文字标识消失，上方显示“采用……制成”，下方显示产品名称。

1. 一个HTML文件，1920x1080。从 seek(t) 内部的时间开始计算每个样式：没有CSS过渡、计时器或在帧之间传递状态。
2. 对容器使用一个相机变换，以 [时间、缩放、x、y] 为键，并进行缓动分段，缩放在对数空间中进行插值。
3. 对每个弹跳和回弹都使用封闭式阶跃响应弹簧。
4. 让每一次交接都成为一个共享元素：石灰水流携带气泡文字的副本，按钮将其标签带入页面。
5. 音效：为每个事件使用下载的 Mixkit 音效——打字声、发送提示音、每次投掷音、掉落冲击声、卡片嗖嗖声、点击声、成功提示音、页面填充嗖嗖声和标记闪烁声。根据测量的峰值音量放置每个音效，并将响度标准化为 -14 LUFS。
6. 使用Playwright以 60fps 的帧率渲染，每帧使用 8 个子帧，并使用ffmpeg tmix进行混合。逐帧检查每个快速移动的瞬间，并扫描整个视频以查找单帧抖动。

快速移动时，四个子帧会留下残影，因此渲染 8 个子帧并减慢移动速度。洪水必须到达最远的角落，耗时约 0.35 秒，否则看起来像闪光。为每个图层设置 z-index，以防止卡片漂浮在洪水之上。将文本请求保持在固定行上，这样摄像机就不必跟随循环光标。在第一次调用 seek() 之前声明所有变量。

先征求我的意见，然后给我看节奏图和 4 张剧照（提问、高潮、聊天、结尾），之后再写完整的影片。

Ask me for: my product, the exact request a user types into it, 6 to 8 photos for the result cards, a royalty-free song around 130 BPM with a clear drop (Mixkit, free for commercial use), and my brand mark for the end card. If I skip anything, use the defaults: the food-ordering story below, food photos from Pexels (fire noodles, birria tacos, hot chicken, buffalo wings, smash burger, spicy ramen), and Mixkit "Cat Walk".

A 15-second product launch film, 1920x1080 at 60fps. 2D only, one continuous take. No fades, blurs or cuts: each scene grows from the last. Text rises from a mask line, buttons expand into pages, and color floods from one object before shrinking into another. Give the camera one eased move per scene, and never zoom in and out consecutively.

Look: warm white canvas (#f5f5f2), black UI (#0e0e10), lime accent (#cdf24f), orange (#ff6a2a), and a blue send button (#2f6bff). Add an Apple Intelligence-style iridescent glow around the input: a blurred conic gradient rotating through pink, orange, lime, cyan and violet. Use real food photography on dark cards, Geist for UI and a serif for the product name on the end card.

Banned: crossfades, blur-ins, 3D, particles, camera moves that reverse direction, holds longer than 1s, anything that feels like a template.

130 BPM, 32 beats (14.8s). Start the song 12 beats before its drop.

Beats 0-6, ask: push slowly into the glowing composer, about 3x zoom. Type the request over three fixed lines with a natural keystroke rhythm:
"I'm really hungry, I don't know
what I want but something
spicy, crispy and filling"

Beat 6, send: press the send button. A lime ripple spreads from it and transforms the message into a chat bubble. Pull back once to reveal the phone around it (428x900 screen, 11px black bezel, 9:41 status bar).

Beats 6-12, think: the send button grows into an orange wok, a half-disc with a thin handle. It tosses 6 colorful ingredients on beats 8, 9, 10 and 11 beneath the shimmering text "Finding something for you…".

Beat 12, the drop: a lime circle expands from the wok to fill the frame in about 0.35s. Dark food cards (330x440, radius 28, photo on top, name, one-line description, price and rating) burst in from the center. Slide the strip across three cards and land on "Fire Noodles", which lifts with a "Best match" pill.

Beats 16-21, chat: the lime contracts back into the user's bubble, carrying its words as the chosen card flies into its slot. "Found it. Fire Noodles from Wok & Fire, smoky, spicy and seriously filling." rises in, followed by "Want me to order it for you?" Then show two pills: "Order now" in black and "More options" outlined. The cursor clicks Order now → spinner → "✓ Ordered".

Beats 21-32, outro: the black button expands into the page, staying pill-shaped as it reaches the edges while the camera pushes into it. Its label grows to headline size, then slides away. Bring in "You were craving noodles." and "Now it's on the way." word by word (92px, white on black). A courier dot follows a route to a pin. The pin becomes the brand mark, and the wordmark wipes out from behind it, with "made with" above and the product name below.

1. One HTML file, 1920x1080. Compute every style from time inside seek(t): no CSS transitions, timers or state carried between frames.
2. Use one camera transform on a container, keyed by [time, zoom, x, y] with eased segments and zoom interpolated in log space.
3. Use closed-form step-response springs for every pop and settle.
4. Make every handoff a shared element: the lime flood carries a copy of the bubble's words, and the button carries its label into the page.
5. Sound: use a downloaded Mixkit SFX for each event - typing, send pop, each toss, drop impact, card swoosh, click, success tone, page-fill whoosh and mark sparkle. Place each by its measured peak and loudnorm to -14 LUFS.
6. Render with Playwright at 60fps using 8 subframes per frame, blended with ffmpeg tmix. Review every fast moment frame by frame and scan the full video for single-frame pops.

Four subframes leave ghost copies on fast moves, so render 8 and slow the move down. The flood must reach the farthest corner and take about 0.35s, or it looks like a flash. Set z-index on every layer so the cards don't float above the flood. Keep the typed request on fixed lines so the camera never has to follow a wrapping cursor. Declare every variable before the first seek() call.

Ask me for the inputs, then show me the beat map and 4 stills (ask, drop, chat, outro) before writing the full film.

提示取自邮政 @ultimaxbt.