註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

Tanishq Mathew Abraham, Ph.D.
@iScienceLuvr
CEO @SophontAI | Founder @MedARC_AI | PhD at 19 (2023) | ex Research Director Stability AI | Biomed. engineer @ 14 | TEDx talk➡
加入 December 2011
1.6K 正在關注    91.2K 粉絲
Abra: Scaling Diffusion Image Training A comprehensive scaling laws study of text-to-image diffusion models from Luma AI: "We present a systematic scaling law study for text-to-image diffusion models using Abra, a controlled family of flow-matching transformers trained across three orders of magnitude worth of compute (1019 to 1022 FLOPs), reaching significantly larger compute budgets than previous works. We demonstrate that diffusion models scale just as predictably as language models but require far more data to train optimally: compute optimality occurs at approximately 200 image tokens per parameter, ten times the Chinchilla compute-optimal prescription for LLMs." paper link:
顯示更多
0
6
84
12
轉發到社區