Mischief 1: a video model born from lab-grown brain cells, from 0.5¢ per second
azed_ai · x · 2026-10-30
A startup has launched Mischief 1, a video generation model it says is derived from four years of growing real neurons on electrodes to study how they compute. Image-to-video costs from 0.5¢ per second, claimed to be at least 5x faster than its base model and the cheapest image-to-video option on fal and OpenRouter, with an AWS Marketplace listing coming. The team calls it proof that biocompute is "real and commercial." A user demo shows it takes several prompt retries to nail multi-step motion like hugging a toy rabbit.
Related event: Startup launches mischief 1, a video model inspired by cultured neurons(5 posts)→
More from Multimodal
- 60+ community-made ChatGPT slash-style words turn one word into a full visual style — heyshrutimishra · 2026-10-31
- Cartesia's cascaded voice agents top the Speech Agent Arena, beating native speech-to-speech — rohanpaul_ai · 2026-10-31
- Hyperflow H3 hits #5 on I2V and #3 on video editing at under half Seedance 2.5's price — ArtificialAnlys · 2026-10-31
- Krea plugin brings image and video generation, sketch-to-animation into Grok — angrypenguinPNG · 2026-10-31
- Open-source Stem Studio separates AI video audio into editable stems via ComfyUI — eraiozei · 2026-10-31
- When an AI video defames someone, who gets sued: prompter, provider, or platform? — New_Pension_4485 · 2026-10-31