n8n Automation: Image to Six-Shot Contact Sheet and Cinematic Video Publishing

Input Google Sheets image link → NanoBanana Ultra generates 2×3 contact sheet → Kling frame-to-frame video in 3 clips → FFmpeg merge → Blotato auto-publishes to YouTube

Who

Content creators, marketers, or automation builders already familiar with n8n and Google Workspace

You get

Automatically produce a six-frame contact sheet, three AI video segments, a merged final video, and publish to YouTube from a single image

You need

n8n · google-sheets · google-drive

Steps

1. Prepare spreadsheet and credentials

   Create or copy the Google Sheets template with columns: status, image_nanobanana, image_contactsheet, image_atlas, Final video. In n8n, connect Google Sheets OAuth2, Google Drive OAuth2, and Blotato accounts. Obtain an AtlasCloud API key and a Fal API key.

2. Generate 2×3 contact sheet (NanoBanana Ultra)

   Trigger the workflow manually or via Schedule Trigger. n8n reads a row with status=nanobanana_done from Google Sheets, downloads the image from Google Drive, uploads it to tmpfiles for a public URL (replace tmpfiles.org/ with tmpfiles.org/dl/ in the returned URL for direct access). Sets contactSheetPrompt in the Edit Fields node (see prompt below), then calls AtlasCloud NanoBanana Ultra (google/nano-banana-pro/edit-ultra) to generate a 2×3 contact sheet. Waits 4 minutes, polls the prediction endpoint, downloads the PNG, uploads back to Google Drive, and updates the sheet to status=contact_done with image_contactsheet and image_atlas.

   Execution prompt · Source text。Edit Fields : contactSheetPrompt node value field

   Copy prompt

   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. Crop contact sheet and generate video clips (Kling)

   When status=contact_done, the Schedule Trigger fires phase two. Download the contact sheet, use the Edit Image node to get dimensions, then crop into 4 regions (Top Left, Top Center, Top Right, Bottom Left) each sized width/3 × height/2, corresponding to 4 of the 6 frames (the flow uses 3 adjacent frame pairs). Upload cropped frames to tmpfiles for public URLs. Call AtlasCloud Kling start-end-frame (kwaivgi/kling-v2.1-i2v-pro/start-end-frame) to generate three 5-second cinematic clips, each using adjacent frames as start and end images. Wait 4 minutes after each call before polling for results.

   Execution prompt · Source text。Kling Generation / Kling Generation1 / Kling Generation2 node prompt field (bodyParameters.prompt)

   Copy prompt

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

   Execution prompt · Source text。NanoBanana ULTRA: Contact Sheet node JSON Body

   Copy prompt

   ={
     "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"
   }

   Execution prompt · Source text。Merge 3 Videos node JSON Body (Fal FFmpeg API)

   Copy prompt

   ={
     "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. Merge videos and update status

   Merge the 3 Kling clips via the Fal FFmpeg API (https://fal.run/fal-ai/ffmpeg-api/merge-videos) into a single MP4. Wait 1 minute, then update the Google Sheets row to status=video_done and write the merged video URL to the Final video column.

5. Auto-publish to YouTube (Blotato)

   Pass the final video URL to the Blotato Upload media node, then publish via the Create post node to YouTube. Current template settings: platform=youtube, privacyStatus=private, postContentText=test, postCreateYoutubeOptionTitle=test. The published video will be private; adjust visibility or schedule publication as needed.

6. Customize and schedule runs

   Modify the Kling node prompt to adjust camera movement and mood, change the duration parameter for segment length, add or remove crop + Kling branches to change shot count, replace the Schedule Trigger for automatic execution, or adjust NanoBanana aspect_ratio and crop math for different aspect ratios.

You are reproducing n8n template #12769: image to six-shot contact sheet and cinematic video. Please confirm the following before starting:
1) Google Sheets spreadsheet created with columns: status, image_nanobanana, image_contactsheet, image_atlas, Final video;
2) n8n connected to Google Sheets OAuth2, Google Drive OAuth2, and Blotato accounts;
3) AtlasCloud API key obtained (for NanoBanana + Kling) and Fal API key obtained (for FFmpeg merge);
4) Understand tmpfiles URLs need tmpfiles.org/ replaced with tmpfiles.org/dl/ for direct links;
5) Kling negative_prompt is currently example_value and must be replaced with an actual negative prompt;
6) Blotato publish defaults to YouTube private; adjust postCreateYoutubeOptionPrivacyStatus if public visibility is needed.

After confirmation, follow steps 1-6 to import workflow.json into n8n and configure all placeholders.