Show HN: Instantly create video clips from LLM prompts

Re:Show HN: Instantly create video clips from LLM prompts by mdrzn on Friday February 23, 2024 @06:30AM (#39479348)

"Use any LLM of your choice like OpenAI, Claude or Gemeni Pro" will local LLMs like LLaMa/LLaVa be added in the future?

edit: nevermind, I thought it was fully open source, instead you will still have to pay for "videodb" on top of your AI tokens.

[ Parent | on HN ]

Re:Show HN: Instantly create video clips from LLM prompts by ashu_trv on Friday February 23, 2024 @09:48AM (#39481183)

Yeah, VideoDB is the next-gen infrastructure for videos and actually less costly than current video infrastructure.

But you can use any LLM for analysing the transcript.

[ Parent | on HN ]

Re:Show HN: Instantly create video clips from LLM prompts by mdrzn on Friday February 23, 2024 @10:02AM (#39481356)

So it's still just analysing the transcript, not using GPT4-V or OCR in any way?

Can you confirm if I could skip using VideoDB by using Whisper to transcribe the video, and then use that transcript with LLaMa to extract the important parts?

[ Parent | on HN ]

Re:Show HN: Instantly create video clips from LLM prompts by ashu_trv on Friday February 23, 2024 @10:21AM (#39481643)

It analyse the transcript, but there is no way to get back the video clip without building your own video infra. We at Videodb are solving the exact problem.

[ Parent | on HN ]