Skip to content
かみもと · 本地AI视频工作流·· 2026-10-12AI score58

Hands-On Test: Training a Qwen Image 2.1 Character LoRA on Google Colab A100 80GB

【Qwen Image 2.1】VRAM 12GBに入らないモデルを使ってGoogle ColabのA100 80GBでLoRA学習してみた

AI briefing

The author trained a Qwen Image 2.1 character LoRA with ai-toolkit 0.13.19 on Google Colab's A100 80GB; 1,000 steps took about 21 minutes this run, whereas the same number of steps on a local RTX 4070 12GB takes about 2 hours.

Open original note.com