Loading video...

Video Failed to Load

Go Home

拡散Transformerを稠密予測へ転用「Marigold V2」 🔹Qwen-Image-Edit-2509を4-bit量子化+Rank-128 QLoRAで微調整 🔹深度・法線・アルベドなどを1ステップで推定 🔹単一GPUで数日の学習を実現 STeRとの動画への応用可能性も示唆。 情報元はリプ欄。

61,045 views • 20 days ago •via X (Twitter)

5 Comments

Sadao Tokuyama's profile picture
Sadao Tokuyama20 days ago

情報元ページ

SirBadfish's profile picture
SirBadfish19 days ago

Tested this earlier today on HuggingFace in the Space. By far the best in class. It works really, really well.

Fajar M Reza's profile picture
Fajar M Reza19 days ago

Quantized QLoRA could make dense prediction research far more reproducible on modest hardware.

Leo Phiêu Diêu's profile picture
Leo Phiêu Diêu19 days ago

@tokufxug Hi, can it create grey-scale depth ?

Seltop's profile picture
Seltop19 days ago

holy cook

Related Videos