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 месяцев назад·9 comments

Oasis: A Universe in a Transformer (Playable Demo)

oasis.decart.ai
8 points·by dnnssl2·2 года назад·1 comments

comments

dnnssl2
·2 месяца назад·discuss
70% at launch seems pretty saturated, why ship a benchmark frontier models are about to top out on?
dnnssl2
·12 месяцев назад·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
·в прошлом году·discuss
What can this handle? Code? Browser? Computer Use?
dnnssl2
·2 года назад·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 года назад·discuss
Blog Post: https://oasis-model.github.io/

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