HackerTrans
TopNewTrendsCommentsPastAskShowJobs

dnnssl2

no profile record

Submissions

MirageLSD: The First Live-Stream Video Diffusion Model (∞-Generation, 0-Latency)

mirage.decart.ai
9 points·by dnnssl2·12 bulan yang lalu·9 comments

Oasis: A Universe in a Transformer (Playable Demo)

oasis.decart.ai
8 points·by dnnssl2·2 tahun yang lalu·1 comments

Anyscale Appoints Keerti Melkote as CEO

anyscale.com
2 points·by dnnssl2·2 tahun yang lalu·0 comments

comments

dnnssl2
·2 bulan yang lalu·discuss
70% at launch seems pretty saturated, why ship a benchmark frontier models are about to top out on?
dnnssl2
·12 bulan yang lalu·discuss
MirageLSD: The First Live-Stream Diffusion (LSD) Model - A Vid2Vid running in real time, infinite generation, zero latency. Available now in a live-hosted unlimited demo at https://mirage.decart.ai!

Please check out our Wired article on this model: https://www.wired.com/story/decart-artificial-intelligence-m...
dnnssl2
·tahun lalu·discuss
What can this handle? Code? Browser? Computer Use?
dnnssl2
·2 tahun yang lalu·discuss
Oasis is playable so therefore:

1. Non-cherrypicked in its consistency (if you look at the demonstrations in the Oasis blog post you can find specific cases of consistency which is an anomaly rather than the norm)

2. Is live-inferenced at 20fps. If you use Runway v3 which is a comparably larger and higher quality model (resolution and consistency) it might take a minute or two generate 10 seconds of video.

3. Is served (relatively) reliably at consumer scale (with queues of 5-10k concurrent players) which means that in order to save on GPU cost, you increase batch size and decrease model size to “fit” more players in 1 GPU.
dnnssl2
·2 tahun yang lalu·discuss
Blog Post: https://oasis-model.github.io/

Model Weights: https://huggingface.co/Etched/oasis-500m
dnnssl2
·2 tahun yang lalu·discuss
What is the upper bound on the level of improvement (high performance networking, memory and compute) you can achieve with ternary weights?