All ideasMore in Hobbies
Hobbies

Musician made a whole music video from one image running models locally

The musician creator recorded a 90 second experimental techno track and generated every shot of its music video locally on MiniMax H3 from a single year old Midjourney image. An Augmentor agent over MCP controlled ComfyUI for the generation, because the creator did not fully know ComfyUI, and the creator edited the result in DaVinci Resolve, building the story around an unexpected second character the AI produced.

How it works

  1. Creator recorded a 90 second experimental techno track
  2. Creator took one year old Midjourney image as the source
  3. Augmentor agent over MCP controlled ComfyUI to generate every shot locally on MiniMax H3
  4. Creator kept the lo-fi look and built the story around the unexpected second character
  5. Creator edited the video in DaVinci Resolve, cutting in time with the music

Why it’s worth knowing

Every shot of the video came from a single year old image generated locally on the creator's own GPU, with an agent driving ComfyUI because the creator did not fully know ComfyUI

Where it’s from

Summarized from a public post on youtube.com. See the original ↗

Upgraded prompt

A ready-to-use prompt for this idea, built from research on what makes AI agents do the job right: who the AI should be, the exact steps, and a check to make sure it was done the way you wanted.

1Who the AI should be
2The prompt, with the steps
3The check when it’s done
Upgraded prompts are coming soon.

Try next

HobbiesFill and submit UK master’s applications from one master fileHobbiesLaid off on Tuesday. The AI shipped my game by breakfast on Wednesday.HobbiesAudit my whole drive every week, flag 380GB to delete — and delete nothingHobbiesAn AI assistant traced my family tree past 1,200 people and 13 generations

Every idea is a real post from someone who tried it, summarized in our words, with a link to the original. App names are swapped for plain words.