Empire State Proposal Video

Flow·2 steps

Upload two photos and live an unforgettable proposal at the top of the world. Dressed in black with faces hidden behind masks, one of you kneels and offers a ring high above the city — then the masks come off, revealing who you really are, and you hold each other tight in pure joy.

Steps
2
Inputs
2
Runs
8
Template · pipeline2 steps
  1. 1
    bytedance-seedance-2-0-reference-to-videoid · step1 · model
    aspect_ratio
    "16:9"
    duration
    "15"
    enable_safety_checker
    true
    generate_audio
    false
    image_urls
    [3 items]
    +2 more params
  2. 2
    ffmpeg-api-merge-audio-videoid · step2 · model
    audio_url
    "https://cdn-us.eachlabs.ai/uploads/ec912a22-35c4-418e-b807-3…"
    start_offset
    0
    video_url
    "$.step1.primary"
How to use this template
trigger.sh
sh
# 1. Trigger the workflow
EXEC=$(curl -s -X POST https://workflows.eachlabs.run/api/v1/d1812224-73e8-424e-b022-c0d747551cb1/trigger \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
      "version_id": "v1",
      "inputs": {
        "person1": "https://cdn-us.eachlabs.ai/uploads/ac33b333-0b8a-4743-a04e-d2e97a6477be.jpg",
        "person2": "https://cdn-us.eachlabs.ai/uploads/397af8a5-9d95-4190-b93f-4c319aa49038.jpg"
      }
    }' | 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 change2 inputs

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.

  • person1
    default · ac33b333-0b8a-4743-a04e-d2e97a6477be.jpg
    image URL
  • person2
    default · 397af8a5-9d95-4190-b93f-4c319aa49038.jpg
    image URL
Ideas for your remix
  • · Swap the input media to retell the story with different subjects.
  • · Edit the prompt inside bytedance-seedance-2-0-reference-to-video 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