Loading activity…
@haoailab
Hao AI Lab at UCSD. Our mission is to democratize large machine learning models, algorithms, and their underlying systems.
AI
A user estimates self-hosted fastH3-omni at about $0.14 per 15-second 768p clip, versus about $11.31 for Seedance's 1080p output.
AI
The @haoailab account says a five-second 480p clip with audio takes 15 seconds on one RTX 5090.
AI
Hao AI Lab comments on an independent review of its open-source FastH3 Preview against H3 models.
