Walk through creating a complete video from idea to export using GEN's Vidsheet workspace.
π Getting Started Guide Β· Step 4 of 6
Most brands take hours to create one video. You're about to create your first professional video in under 15 minutes β no filming, no editing experience required.
This is where GEN stops feeling like software and starts feeling like magic.
π‘ Did you know?
One DTC skincare brand went from 4 posts/week to 52 β and hit 2.4M views in their first month using this exact workflow.
Understanding the Vidsheet Layout
Your Vidsheet is split into two powerful sections that work together seamlessly:
Left Side (Content Cells): Your creative laboratory where you generate all video assets β images, video clips, voiceovers, and text overlays. Each cell is a content creation node.
Right Side (Video Editor): Your assembly timeline where generated content automatically appears and gets combined into your final video. Think of it as a timeline editor, but infinitely simpler.
Each row = one complete video. You'll create everything for Video #1 in row 1, Video #2 in row 2, and so on.
Step 1: Set Up Your Content Structure
First, let's organize what you want to create. Start with a simple but powerful structure:
Click on Column A header and rename it to "Video Idea" (Text type)
Rename Column B to "Script" (AI Text type)
Rename Column C to "Background Image" (Media type)
Rename Column D to "Voiceover" (Media type)
β‘ Pro Move: Use variables to connect your columns. Type #########{{Video Idea}} in your Script column prompt, and GEN will automatically reference your idea when generating the script.
Step 2: Add Your First Idea and Generate Script
Now let's bring your video to life:
Click cell A1 and type your video concept
Example: "Why our vitamin C serum works better than expensive brands"
Click cell B1 β the Creation Card panel opens automatically
Select "AI Text" from the creation card options
Write a prompt like: "Create a 30-second engaging script about #########{{Video Idea}} that feels conversational and authentic"
Click the generate button and watch the AI create your script in real-time
The script appears in cell B1 and automatically flows to your video timeline on the right.
Step 3: Generate Your Background Visual
Time to create stunning visuals without filming anything:
Click cell C1 β the Creation Card opens
Select "Image from Text" from the creation card types
Choose your model based on your needs:
Midjourney: Highest quality, takes 30-60 seconds
Nano Banana: Great quality, generates in 10-20 seconds
Write your prompt: "Professional skincare lab background, clean and modern, soft lighting"
Set aspect ratio to 9:16 (perfect for TikTok, Reels, and Shorts)
Click generate and watch your custom background appear
[Screenshot: Image from Text creation card showing model selection dropdown and aspect ratio setting]
π How a supplement brand uses this
One founder created 31 videos in 21 days using this exact image generation workflow. Result: 1.1M total views and 18% increase in TikTok Shop revenue.
Step 4: Add Professional Voiceover
Now let's bring your script to life with AI voice:
Click cell D1 for your voiceover
Select "Speech from Text" from creation cards
Choose a voice that matches your brand:
Browse available voices in the dropdown
Click play icons to preview different options
Pick one that sounds natural and on-brand
Reference your script by typing: #########{{Script}}
Click generate
The AI creates professional voiceover audio using your generated script. No recording studio needed.
"I've never shown my face on camera. My audience has no idea every video is made with AI."
ββ Creator, Faceless YouTube Channel
Step 5: Watch Your Video Assemble Automatically
Here's where the magic happens on the right side:
As each asset generates, it automatically appears in your video timeline:
Your background image appears as the base visual layer
Your voiceover appears as the audio track
Timeline layers show exactly how everything combines
You can fine-tune the timing by:
Dragging layer edges to trim duration
Moving layers left/right to change start times
Adding text overlays by clicking the + button
Adjusting layer order by dragging up/down
π‘ Did you know?
71% of GEN users reduced manual editing time by 80% or more using this assembly workflow instead of traditional video editors.
Step 6: Preview and Perfect Your Video
Before exporting, make sure everything looks perfect:
Look at the preview in your Final Video section (right side)
Click to play and watch with audio
Make adjustments if needed:
Regenerate any asset by selecting it and clicking generate again
Adjust layer timing by dragging in the timeline
Add text overlays for captions or titles using the + button
If something isn't quite right, just select the asset and regenerate. Each generation is saved in your history β you can always go back.
Adding Text Overlays and Captions
Want to add titles or captions? Here's how:
Click the + button in your video timeline
Select "Text Overlay" from creation cards
Type your text and adjust positioning
Choose font, size, and background style
Step 7: Export Your Professional Video
When you're happy with the preview:
Click "Generate" in the Final Video section
Wait for processing β this combines all layers into one file (usually takes 30-90 seconds)
Download your video when "Ready" appears in green
Your professional video is now ready to post anywhere!
[Screenshot: Final video section showing "Ready" status and download button]
β‘ Pro Move: Duplicate your row to create variations. Change one element (like the background image prompt) and you'll have a completely new video in under 2 minutes.
What You Just Accomplished
You've created a complete video workflow that most brands pay thousands for:
β Generated a professional script from a simple idea
β Created custom visuals without stock footage
β Added professional voiceover without recording
β Assembled everything into a publish-ready video
β Exported a final video in under 15 minutes
π‘ Did you know?
82% of GEN users said their audience couldn't tell the content was AI-generated when following this creation process.
Beyond the Basics: More Creation Card Types
Once you master the basics, explore these powerful options:
Video from Text: Generate video clips directly from prompts using models like Kling, Veo3, and Seedance
Video from Image: Animate your still images into moving video
Talking Avatar: Create AI presenters that speak your script with perfect lip-sync
Video from Ingredients: Combine multiple images into cohesive video sequences
Each creation card works the same way β select it, configure your inputs, and generate. The power is in combining them creatively.
What Brands Like Yours Are Doing
π Beauty brands β Product showcase videos with custom backgrounds and talking avatar testimonials
ποΈ E-commerce brands β Educational content about product benefits using animated product shots
ποΈ Fitness brands β Motivational content with talking avatars and trending audio
π¬ Faceless YouTube creators β AI visuals + voice clone + auto-captions for Shorts and long-form
Your Next Video Will Be Even Faster
Now that you understand the workflow, your next video will take under 10 minutes. You'll intuitively know:
Which creation cards to use for different content types
How to structure your columns for maximum efficiency
How variables make content creation scalable
How the timeline assembly works
The hardest part is behind you. From here, it's just creative experimentation.
β¬ οΈ Previous: Build Your First Project in 60 Seconds Β· Next: Connect Social Accounts and Start Posting β
Creation Card Types
Each cell in your Vidsheet uses a creation card to generate content. Here are all the types available β click any to learn more:
Text β Direct text input that syncs with the cell
Media β Upload files or select from your asset library
Text Overlay β Add styled text overlays to your video
Image from Text β Generate images from prompts (Nanobanana, Midjourney)
Video from Text β Generate videos from descriptions (Veo3, Kling, Wan 2.2)
Video from Image β Animate still images (Kling, Veo3, Seedance, Sora 2)
Video from Ingredients β Combine multiple images into video (Pika, Kling)
Video from Talking Avatar β Lip-synced avatar videos
Image from Avatar β Generate images with your trained avatar
Speech from Text β Text-to-speech in 23 languages (ElevenLabs)
Captions β Auto-generated synchronized captions
Lipsync β Sync lip movements to any audio track
For the full reference with inputs, models, and tips for each card, see All Creation Cards: Your Complete Guide.
Keep Learning
Now that you've created your first video, dive deeper:
Image Generation Guide β master prompts, models, and styles
Generate AI Videos β Veo3 vs Kling vs Seedance deep dive
Create Talking Avatar Videos β lip-synced characters speaking your scripts
Advanced Features β variables, duplication, and AI text to scale to 30+ videos
All Creation Cards β every content type explained
Something not working? β troubleshooting common issues
Ready to start creating?
Browse our library of ready-made templates and launch your first video in minutes.



