MAGNIFIC SPACES + SEEDANCE 2 IS INSANE?!
Shows how AI‑driven, low‑code pipelines can replace traditional product‑video shoots, giving indie filmmakers rapid, cost‑effective commercial content.
What this lesson covers
Thomas Lundström demonstrates a node‑based workflow in Freepik Spaces that turns a simple product photo into high‑quality images and a 15‑second commercial using Nano Banana Pro and C댄스 2.0. The process automates prompt creation, image generation, and multi‑shot video synthesis without complex manual prompting.
Key takeaways from the creator
AI-extracted notes, not independently verified product claims. Timestamp links let you check each point in the original video.
- 00:35 ↗
Upload a clean product image (white background) and a style reference to seed the workflow.
- 03:00 ↗
The node‑based system separates prompt creation, image generation, and video generation, letting you run each step individually.
- 05:22 ↗
Generate images first at lower resolution for iteration, then upscale to 4K for final assets.
- 07:00 ↗
The multi‑shot prompt node builds a detailed video script that references the generated images for each shot.
- 07:23 ↗
Verify video generation parameters (duration, resolution, aspect ratio, sound) before rendering to avoid costly re‑runs.
Workflow outlined in the video
- Upload the product photo with a white background into the Freepik Spaces workflow.
- Select or upload a style reference image (AI‑generated or stock) to define the visual theme.
- Run the image‑prompt node to automatically craft a tailored prompt from the two assets.
- Execute the image‑generation node, iterating via the prompt editor until the product image meets expectations.
- Run the multi‑shot prompt node to create a comprehensive video prompt that references the hero and auxiliary images.
- Configure the C댄스 2.0 video node: set length (15 s), resolution (720p or 4K), aspect ratio, and enable sound.
- Generate the video, review the output, and repeat prompt or asset tweaks as needed.
Before you use this workflow
These notes describe the source video at its publication date. Model access, pricing, connectors and interfaces may have changed. Check the original source and the provider’s current documentation before installing an add-on, connecting an account or spending credits.
ReelStack has not independently tested this workflow. Preview one representative shot and check motion, continuity and output quality before applying it to a full production. No result, cost saving or model capability is guaranteed.
Explore the tools
How to interpret the numbers
20,194 views captured 24 October 2026. ReelStack recommendation score: 42/100. Formula: radar-v5. This is ReelStack’s calculation, not a YouTube rating or a measure of factual accuracy.
Show the calculation
- 45% performance: 0.88× views vs 6 other channel videos observed at a similar age. View-evidence factor 95% (views / (views + 1,000))
- 25% freshness: 0/100 with a 14-day half-life
- 20% momentum: 11 views/day vs 5 channel baseline (3 comparable uploads), with the same view-evidence factor
- 10% engagement: 92/100; likes + 4× comments, smoothed with a 500-view neutral prior