Communitygithub.com

Raibit-AI/food-shot-director

指导AI将菜品照片转化为视频广告中的美食镜头(如筷子夹起面条、勺子舀取、酱汁浇淋、食物特写)。提供提示词公式、动画效果评估清单及保留/拒绝检查表,确保成品与真实菜品一致。兼容Kling、Veo、Seedance、LTX、Runway等图像转视频模型。

food-shot-director 是什么?

Food Shot Director是一款专为餐厅广告设计的AI技能,用于将菜品照片转化为引人注目的视频片段,避免使用简单慢速缩放等乏味开场。该技能的核心是通过

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/Raibit-AI/food-ad-kit/tree/HEAD/plugins/food-ad-kit/skills/food-shot-director

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

美食镜头导演

成功的餐厅广告在 首秒引入动态画面(79%) 和 手入镜(79%)。静态菜品配慢速缩放是最弱的开场。解决方案是“手入镜动作镜头”,从真实的菜品照片生成。

1. 从真实菜品的实拍照片开始

使用餐厅自己的照片,最好放置在他们真实餐桌或空间的背景中。这关乎三点:

  • 模型会复现输入的内容,因此他们的摆盘和份量保持真实。
  • 每道菜品使用一个干净的镜头。 如果照片带有模糊填充或边框,模型大约在第3秒会偏离并生成新场景。
  • 先清除杂物。 一次图像编辑移除背景中多余的盘子,可避免多次重做。

2. 提示词公式

[餐具] 从画面顶部进入,[一个动作],然后缓缓将**[食物]** 举向镜头,[一个细节:蒸汽、滴落、光泽]。只有**[餐具]** 移动;[碗/盘] 保持不动。 然后加上风格尾部:特写诱人美食广告,夜晚温馨餐厅氛围,浅景深,写实,稳定镜头。背景无人物。音效:柔和氛围,无音乐,无对话。

已验证示例:

  • 筷子从碗中夹起油亮面条,辣椒油滴落。
  • 白瓷勺舀起红油中的豆腐块,蒸汽升腾。
  • 手持小勺将辣椒油浇在饺子上。
  • 筷子夹起一块裹满辣椒片的酥脆金黄炸鸡。必须准确描述纹理和颜色,否则模型会生成模糊的块状物。

3. 动画效果好 vs 容易变形的食物

效果好的效果差的
面条、酱汁、汤汁、浇淋、蒸汽、滴落单独夹起的固体食物(饺子融化,鸡块变成面糊)
一个餐具、一个动作提示词中出现两个动作
俯拍或45度角宽场景拍摄:路人走入画面
5秒片段;使用其中最好的1.5-2.5秒使用整个片段:动作常会反向或出现第二个勺子

预计每2次拍摄约有1次可保留。每次拍摄生成2个随机种子。

4. 保留/拒绝检查表(以0.5秒为步长检查帧)

出现以下任一情况则拒绝该镜头:

  • 食物不再像真实菜品(形状、颜色或份量错误)。
  • 夹起的食物在途中变形。
  • 出现第二个餐具、手或盘子。
  • 有行人从背景中穿过。
  • 餐具过大、塑料质感或融化。
  • 动作出现反向。

然后修剪至最干净的1.5-2.5秒。

5. 两个陷阱

  • 剥离片段音频。 大多数视频模型会加入自带音乐,每次裁剪都会切换歌曲。单独构建音轨;social-ad-builder技能可完成此操作。
  • 真实性。 镜头必须展示顾客实际拿到的东西。绝不添加真实菜品上没有的食物、装饰或份量,也绝不在真实餐厅广告中生成虚构的顾客或人群。

Individual skills in this repo

This repo contains 4 individual skills — each has its own dedicated page.

Raibit-AI/ad-teardown

Breaks a video ad down the way a creative director would. It measures length, cut speed and first cut; pulls frame strips of the first 3 seconds and of the whole ad; transcribes the speech; tags the hook, format, people, text, offer and ending; and scores it against benchmarks from winning food ads. Use when the user asks to analyze, break down, tear down, critique or compare a video ad, Reel or TikTok, especially for a restaurant or food brand.

Raibit-AI/blind-ad-review

Improves a video ad through repeated blind A/B reviews. Two versions are shown as contact sheets to a fresh reviewer who doesn't know which is newer, and both are scored against benchmarks from winning food ads. The next version changes only what reviewers agree on, and the loop continues until the gains stop. Use when the user wants to improve, iterate, critique or A/B test an ad or Reel before spending money, or asks "which version is better".

Raibit-AI/social-ad-builder

Assembles finished vertical social video ads from clips plus a simple JSON shot list. It outputs a 9:16 master for Reels, Stories and TikTok plus a 4:5 feed cut, with brand-color dish labels, the brand on frame 0, hard cuts, a matched color grade, clean designed sound, safe loudness and an end card. It uses free ffmpeg only. Use when the user wants to edit, cut, assemble or render a short ad, Reel or TikTok from food or product clips, or make several ad variations to A/B test.

Raibit-AI/winning-ad-finder

Finds video ads that are probably working for restaurants and food brands, using the free Meta Ad Library, and builds a short "swipe file" of likely winners to study. Use when the user asks to find winning ads, research competitors' Facebook or Instagram ads, see what ads restaurants are running, or build ad inspiration for a food business.

相关技能