Hacker News new | past | comments | ask | show | jobs | submit
vblanco | on: MiniMax H3 Day-0 Support in ComfyUI: Open Weights, Native Audio, and 2K Video
Im running this on my 4070ti super (16 gb vram), and it takes 10 minutes for a 10-seconds 480p video. but the results are spectacular.
Maxious | parent | next
FWIW on a 5080 16GB it takes 3 minutes for 10 seconds 480p video (the mouse video workflow with length changed from 5 seconds to 10 seconds)
loading story #49161013
loading story #49156459
ddevnyc | parent | next
I am particularly curious how multimodal models will work with types of knowledge that are inherently non-text. For example, SOTA LLMs really suck at electronics, especially analog electronics.

Is MiniMax H3 capable of logical / technical reasoning, or is it purely art oriented?

loading story #49156717
loading story #49156580
loading story #49156674
loading story #49156598
mwigdahl | parent | next
If you wouldn't mind sharing, what's your Comfy workflow for this? I have the same video card setup and would like to give it a shot.
vblanco | root | parent
just the default one in the link for image-to-video
robbru | parent | next
1 minute for a second of footage, that is awesome! Thanks for sharing.
chrsw | parent | next
Huh, interesting. I tried to generate a 10 second 1080p clip on a bigger machine and the results were quite poor. Unusable for anything, in fact.
384028345 | parent
How much RAM does your machine have?