Skip to main content
Video Studio is the long-form generation counterpart to Image Studio. It lets users generate AI videos with several model families while keeping a clean gallery workflow for history, previewing, and downloads.

​
What Users Can Do

Users can:
  • generate videos from text prompts
  • use image-to-video when the selected model supports it
  • switch between multiple video providers
  • choose settings like ratio, duration, and resolution where supported
  • browse their generated videos in a gallery
  • preview completed videos
  • download or delete older generations
This makes it a strong base for creative tools, marketing tools, and short-form video products.

​
Current Model Surface

  • openai/sora-2
  • openai/sora-2-pro
  • google/veo-3-fast
  • google/veo-3
  • kwaivgi/kling-v2.6-pro-t2v
  • kwaivgi/kling-v2.6-pro-i2v
  • wan-video/wan-2.6-t2v
  • wan-video/wan-2.6-i2v
Some models are text-to-video only. Others support image input.

​
What You Need

Supabase

Needed for auth and generation history.

Storage

Needed for generated videos and source assets.

Replicate

Needed for Kling and WAN models.
You also need the provider keys for the models you actually enable, such as OpenAI for Sora and Google for Veo.

​
How The App Works

The user flow is:
  1. choose a video model
  2. write a prompt and optionally upload a source image
  3. submit the generation
  4. let the queue and polling flow track progress
  5. save the final output into storage
  6. show it in the video gallery for later playback or download
This is important because video generation is usually slower and more fragile than image generation. The app already handles that reality much better than a single request/response demo would.

​
Why This App Is Useful As A Template

This app is a good starting point for:
  • ad video generators
  • social content tools
  • product promo generators
  • AI storyboarding tools
  • creator workflows with reusable visual styles
It saves you from building the whole async video-generation workflow from scratch.

​
Good First Customizations

Most teams customize:
  • which video models are shown
  • which settings are exposed to users
  • credit pricing per model
  • output layout and gallery presentation
  • whether image-to-video should be prominent or optional

​
Verification

Your setup is correct if:
  • the page loads
  • at least one configured model is available
  • a generation completes and saves successfully