n8n 自动化：单图生成六格联络表并转电影级视频发布

输入 Google Sheets 图片链接 → NanoBanana Ultra 生成 2×3 联络表 → Kling 逐帧生成三段视频 → FFmpeg 合并 → Blotato 自动发布 YouTube

给谁

已有 n8n、Google Workspace 使用经验的内容创作者、营销人员或自动化搭建者

你会得到

从一张图片自动产出六格联络表、三段 AI 视频片段、一段合并后的最终视频，并自动上传发布到 YouTube

你需要

n8n · google-sheets · google-drive

步骤

1. 准备表格与凭证

   在 Google Sheets 创建或复制模板表格，确保包含列：status、image_nanobanana、image_contactsheet、image_atlas、Final video。在 n8n 中连接 Google Sheets OAuth2、Google Drive OAuth2、Blotato 账户。在 AtlasCloud 获取 API key，在 Fal 获取 API key。

2. 生成 2×3 联络表（NanoBanana Ultra）

   触发工作流（手动或 Schedule Trigger）。n8n 从 Google Sheets 读取 status=nanobanana_done 的行，从 Google Drive 下载图片，上传到 tmpfiles 获取公共 URL（将返回 URL 中的 tmpfiles.org/ 替换为 tmpfiles.org/dl/ 以获得直链）。在 Edit Fields 节点设置 contactSheetPrompt（见下方提示词），调用 AtlasCloud NanoBanana Ultra (google/nano-banana-pro/edit-ultra) 生成 2×3 联络表。等待 4 分钟后轮询预测结果，下载 PNG，上传回 Google Drive，更新表格 status=contact_done 并保存 image_contactsheet 与 image_atlas。

   运行提示词 · 来源原文。Edit Fields : contactSheetPrompt 节点的 value 字段

   复制提示词

   Analyze the input image and silently inventory all fashion-critical details: the subject(s), exact wardrobe pieces, materials, colors, textures, accessories, hair, makeup, body proportions, environment, set geometry, light direction, and shadow quality. All wardrobe, styling, hair, makeup, lighting, environment, and color grade must remain 100% unchanged across all frames. Do not add or remove anything. Do not reinterpret materials or colors. Do not output any reasoning. Perfectly replicate the exact facial features of the model.  Face & Identity Preservation Rule Do NOT modify the face or head of the person in the original image. The subject must remain the exact same person, with no AI alteration to facial features, identity, proportions, or appearance. No face swap, no enhancement, no identity change.  Your visible output must be: One 2×3 contact sheet image (6 frames). Then a keyframe breakdown for each frame.  Each frame must represent a resting point after a dramatic camera move — only describe the final camera position and what the subject is doing, never the motion itself. The six frames must be spatially dynamic, non-linear, and visually distinct.  Required 6-Frame Shot List  High-Fashion Beauty Portrait (Close, Editorial, Intimate) Camera positioned very close to the subject's face, slightly above or slightly below eye level, using an elegant offset angle that enhances bone structure and highlights key wardrobe elements near the neckline. Shallow depth of field, flawless texture rendering, and a sculptural fashion-forward composition.  High-Angle Three-Quarter Frame Camera positioned overhead but off-center, capturing the subject from a diagonal downward angle. This frame should create strong shape abstraction and reveal wardrobe details from above.  Low-Angle Oblique Full-Body Frame Camera positioned low to the ground and angled obliquely toward the subject. This elongates the silhouette, emphasizes footwear, and creates a dramatic perspective distinct from Frames 1 and 2.  Side-On Compression Frame (Long Lens) Camera placed far to one side of the subject, using a tighter focal length to compress space. The subject appears in clean profile or near-profile, showcasing garment structure in a flattened, editorial manner.  Intimate Close Portrait From an Unexpected Height Camera positioned very close to the subject's face (or upper torso) but slightly above or below eye level. The angle should feel fashion-editorial, not conventional — offset, elegant, and expressive.  Extreme Detail Frame From a Non-Intuitive Angle Camera positioned extremely close to a wardrobe detail, accessory, or texture, but from an unusual spatial direction (e.g., from below, from behind, from the side of a neckline). This must be a striking, abstract, editorial detail frame.  Continuity & Technical Requirements  Maintain perfect wardrobe fidelity in every frame: exact garment type, silhouette, material, color, texture, stitching, accessories, closures, jewelry, shoes, hair, and makeup. Environment, textures, and lighting must remain consistent.  Depth of field shifts naturally with focal length (deep for distant shots, shallow for close/detail shots). Photoreal textures and physically plausible light behavior required. Frames must feel like different camera placements within the same scene, not different scenes.  All keyframes must share the exact same dimensions and 3:2 aspect ratio, and exactly 6 keyframes must be produced.  Maintain the exact visual style in all keyframes: shot on Fuji Velvia film with a hard flash, light concentrated on the subject and fading toward the edges. The image is overexposed, shows significant film grain, is oversaturated, with shiny (almost oily) skin and harsh white reflections on glasses frames.  Output Format  A) One mandatory 2×3 contact sheet image (6 frames)

3. 裁剪联络表并生成视频片段（Kling）

   当 status=contact_done 时，Schedule Trigger 触发第二阶段。下载联络表图片，使用 Edit Image 节点获取尺寸信息后，裁剪为 4 个区域（Top Left、Top Center、Top Right、Bottom Left），每个区域尺寸为 width/3 × height/2，对应 6 格中的 4 格（实际流程使用其中 3 组相邻帧对）。将裁剪后的帧上传到 tmpfiles 获取公共 URL。使用 AtlasCloud Kling start-end-frame (kwaivgi/kling-v2.1-i2v-pro/start-end-frame) 生成 3 段 5 秒视频，每段使用相邻两帧作为起止画面。每段调用后等待 4 分钟再轮询结果。

   运行提示词 · 来源原文。Kling Generation / Kling Generation1 / Kling Generation2 节点的 prompt 字段（bodyParameters.prompt）

   复制提示词

   =The camera very slowly and smoothly lowers on a boom. The subject barely moves, and is extremely deliberate and thoughtful in movement

   运行提示词 · 来源原文。NanoBanana ULTRA: Contact Sheet 节点的 JSON Body

   复制提示词

   ={
     "model": "google/nano-banana-pro/edit-ultra",
     "aspect_ratio": "3:2",
     "enable_base64_output": false,
     "enable_sync_mode": false,
     "images": ["{{ $('Build Public Image URL nano').item.json.data.url.replace(/tmpfiles\.org\//, 'tmpfiles.org/dl/') }}"],
     "output_format": "png",
     "prompt": "{{ $json.contactSheetPrompt }}",
     "resolution": "4k"
   }

   运行提示词 · 来源原文。Merge 3 Videos 节点的 JSON Body（Fal FFmpeg API）

   复制提示词

   ={
     "video_urls": [
       "{{ $('download video kling').item.json.data.outputs[0] }}",
       "{{ $('download video kling1').item.json.data.outputs[0] }}",
       "{{ $('download video kling2').item.json.data.outputs[0] }}"
     ],
     "output": {
       "format": "mp4"
     }
   }

4. 合并视频并更新状态

   将 3 段 Kling 视频通过 Fal FFmpeg API（https://fal.run/fal-ai/ffmpeg-api/merge-videos）合并为一段 MP4。等待 1 分钟后，更新 Google Sheets 行 status=video_done，并将合并后的视频 URL 写入 Final video 列。

5. 自动发布到 YouTube（Blotato）

   将最终视频 URL 传入 Blotato Upload media 节点，随后通过 Create post 节点发布到 YouTube。当前模板配置为：platform=youtube，privacyStatus=private，postContentText=test，postCreateYoutubeOptionTitle=test。发布成功后视频为私有状态，需手动调整为公开或按计划公开。

6. 自定义与排期运行

   可通过修改 Kling 节点的 prompt 调整镜头运动与情绪，修改 duration 参数调整单段时长，增减 crop + Kling 分支调整镜头数量，替换 Schedule Trigger 实现自动触发，或调整 NanoBanana 的 aspect_ratio 与裁剪数学公式适配不同画幅。

你正在复现 n8n 模板 #12769：单图生成六格联络表并转电影级视频。请先确认以下事项再开始：
1) Google Sheets 表格已创建且含列：status、image_nanobanana、image_contactsheet、image_atlas、Final video；
2) n8n 已连接 Google Sheets OAuth2、Google Drive OAuth2、Blotato 账户；
3) 已获取 AtlasCloud API key（用于 NanoBanana + Kling）与 Fal API key（用于 FFmpeg 合并）；
4) 理解 tmpfiles URL 需将 tmpfiles.org/ 替换为 tmpfiles.org/dl/ 以获得直链；
5) Kling negative_prompt 当前为 example_value，需替换为实际负面提示词；
6) Blotato 发布默认设为 YouTube private，如需公开请调整 postCreateYoutubeOptionPrivacyStatus。

确认后，按步骤 1-6 在 n8n 中导入 workflow.json 并配置占位符。