AIPython★ 154⑂ 11 forksMIT
AcademiaSD/AcademiaSD_LoRAlab-Krea2
Low-VRAM Krea-2 LoRA Training
The project enables efficient Krea-2 fine-tuning via LoRA even on GPUs with limited VRAM, using mixed-precision and gradient checkpointing techniques.
// KEY FEATURES
- LoRA training on Krea-2 at VRAM ≤ 8 GB without quality loss
- Support for mixed-precision (FP16/BF16) and gradient checkpointing for acceleration
- Simple CLI and configs for quick start with custom data
New repositories every 30 minutes
REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.
Join on Telegram