Viewing profile — arkadiuss
arkadiuss
HN member- Joined
- Thu, Mar 26, 2026, 4:56 PM UTC
- HN karma
- 69
- Public activity
- 13 items
- HN profile
- View on Hacker News ↗
About arkadiuss
No profile information was provided.
Recent public activity
-
comment
Comment #47920450
Privacy is close to my heart too. It's just a balance between privacy as a need vs operation speed and intellectual property. To be decided. Inference can be totally done client-si…
-
comment
Comment #47920384
Great to hear that :D
-
comment
Comment #47920379
Yes, sex is one of the inputs. But regional fat distribution isn't something we model or evaluate yet. But going to work on it.
-
comment
Comment #47920280
Thanks, this matches what we're seeing. Trying to establish relationship with some brands, this is the problem we hit. The clothing batches can be very different from each other - …
-
comment
Comment #47919493
The previous response was exactly right. The estimated features are impacting height, so the height can't be set then do the rest. It also cannot be tuned afterwards because it wou…
-
comment
Comment #47919384
Not yet, but it's the first thing to add this week.
-
comment
Comment #47919367
Yeah, the demo wasn't prepared for such peak. Normally it's <2s after warm-up. Like the precomputation idea, but for now it changes too dynamically to precompute each time.
-
comment
Comment #47919297
Exactly, thanks! I'm not English-native, and while most was wrote by hand, some AI assistance makes it more understandable/better readable.
- story
-
comment
Comment #47584811
Actually not this time. Wrote it by myself, but I'm not native speaker and engineer not writer so then used for review and reframing couple sentences.
-
comment
Comment #47584728
Really glad it helped! Thanks! I do believe that thanks to Anny and Sam3D it will get better, cheaper and more accessible than in tools like CLO3D. Extrapolating body from a few in…
- story
- story