zilue

That’s a fair concern DougN7. Generative image/video models are probabilistic, so they can easily cause mistakes like the arrow example you mentioned.

Film Studio works differently for many edits: It is not a generative image/video model. Instead, the prompt will be translated into deterministic code/parameters, which are then rendered with Remotion. So “move this 20px left” or “start this animation at frame 60” becomes an exact operation, rather than a suggestion to a generative model.

It’s more like an AI-powered version of Adobe After Effects + Premiere

Hi rkeswick, thanks for your interest! If u have any issues or problems when using our app, please feel free to submit your issues on GitHub, we will address it as soon as possible.

Our product uses different popular models including the one from Google but provide so much more functionalities～

Hi andrew, MCPs are required here because the only way that our app can communicate with the agents like Claude Code and Codex is through MCP protocol. Skills and prompt are also the key part in our app to provide the best in class experience for different agents

Thanks for your feedback!

Streaming agent's workflow is a good suggestion! We actually already have this feature - if you click the chat bubble button at the top-right corner, just below “Preview,” you’ll be able to see it. That said, the UI definitely needs to improve. We will try to make the AI agent's workflow more visible in our next update.

I’m currently looking into the issue that’s causing it to get stuck. It should work if you would like to try another way: connect the film studio MCP to your codex and let codex call the film studio mcp to create a video for your product.

I like the idea. One of my friends loves watching Dota 2 matches live, and figuring out when tickets go on sale is always a pain. He has to check the website every day, and even then, it’s still easy to miss the release. By the time he notices, the tickets may already be sold out.

So I can definitely see this being useful for non-tech people trying to get tickets to esports matches, popular concerts, or any event where tickets sold out quickly.

Just one thing I am curious: I use GPT’s Scheduled Tasks quite a lot to monitor news and updates from banking.senate.gov around the news I focus on, and it has worked pretty well for me. How does your app differ from GPT with the Scheduled Tasks？

I understand WHY as a personal AI that builds a time-aware understanding of its users. I am wondering what are the most concrete tasks it can perform today?

This is an interesting idea. I was wondering if the app contain following features could make it better, loved to discuss them:

1. There will be a weekly weekly leaderboard on the app for different walls and routes. Climbers need upload and share videos of their attemptes to qualify for the leaderboard. Since the app could resolve the input video into 3D/4Dspace, it could automatically determine and calculate the time that each climber takes to finish the route. The leaderboard resets every week, based on the gym's route-setting schedule.

2. For beginners, it can be difficult for them to identify the correct sequence of moves. If you could partnered with the gyms to place a QR code on each wall, climbers could scan it to view the recommended beta or move sequence on the app when they are stuck. That would be really helpful.