Empire State Banner Video

Flow·3 steps

Type your message and drop it over the New York skyline. High atop the Empire State Building, two masked figures in black unfurl a giant banner with your words in bold letters — a dramatic, cinematic announcement that turns anything you write into a citywide statement.

Steps
3
Inputs
1
Runs
14
Template · pipeline3 steps
  1. 1
    nano-banana-pro-editid · step1 · model
    aspect_ratio
    "9:16"
    image_urls
    [1 item]
    num_images
    1
    output_format
    "png"
    prompt
    "Keep everything in this image exactly the same—same people, …"
    +1 more param
  2. 2
    google-gemini-omni-flash-image-to-videoid · step2 · model
    aspect_ratio
    "9:16"
    duration
    "10s"
    image_url
    "$.step1.primary"
    prompt
    "[00:00 - 00:02] Ultra-photorealistic, raw drone footage, doc…"
  3. 3
    ffmpeg-api-merge-audio-videoid · step3 · model
    audio_url
    "https://cdn-us.eachlabs.ai/uploads/b254bc69-5ce5-4ae9-b39a-4…"
    start_offset
    0
    video_url
    "$.step2.primary"
How to use this template
trigger.sh
sh
# 1. Trigger the workflow
EXEC=$(curl -s -X POST https://workflows.eachlabs.run/api/v1/0056b767-5fdb-4162-8589-47bb3ed281b8/trigger \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
      "version_id": "v1",
      "inputs": {
        "text": "WHERE AI HAPPENS"
      }
    }' | jq -r .execution_id)

# 2. Poll the execution until it's done
curl -s https://workflows.eachlabs.run/api/v1/executions/$EXEC \
  -H "X-API-Key: $EACHLABS_API_KEY"

Trigger returns an execution_id · poll the executions endpoint for the final output

Playground · what you can change1 input

Clone this template into your workspace, then tweak any of the inputs below, or rewrite the step prompts, to spin up your own variation. The pipeline stays the same; the creative output is yours.

  • text
    default · WHERE AI HAPPENS
    text
Ideas for your remix
  • · Swap the input media to retell the story with different subjects.
  • · Edit the prompt inside nano-banana-pro-edit to change tone, scene, or pacing.
  • · Replace any model step with a faster or pricier alternative for a different vibe.
  • · Chain extra steps (upscale, audio, captions) to extend the pipeline.

More flows like this