Show HN: We compressed a 31B video+audio diffusion model to 14B, 6 steps, INT8

ricardobeat 4 minutes ago | parent | next [-]

Their product page has sample videos: https://www.videorebirth.com/lp/hyperflow-flash

swiftcoder an hour ago | parent | prev | next [-]

This is very cool, I wish they would make quality+time comparisons between the various quantisations though

	▲	Reubend 37 minutes ago \| parent [-]
		Seconded, I'd like to see a head to head comparison to see how the quant loks vs the original

▲

xrd an hour ago | parent | prev [-]

I see references to comfyui in the readme. Is that the easiest way to run it? I've always found it a bit cumbersome to use and wish I had something like a simple CLI tool to use it like llama.cpp. Perhaps that's not possible with a video diffusion model?

	▲	syntaxing 18 minutes ago \| parent \| next [-]
		I use stable diffusion cpp with a LLM driving it using CLI. It’s been the quickest way for me to run new diffusion models and require near zero skills but the results come out great.
	▲	swiftcoder an hour ago \| parent \| prev [-]
		They also have references to stable-diffusion.cpp, which is probably the closest analogue to llama.cpp in this space