Buckets:
Source:
https://huggingface.co/alibaba-pai/Wan2.2-Fun-Reward-LoRAs
Rank reduced from 128 using "LoraReduceRank" -node in KJNodes, which is basically kohya's script: https://github.com/kohya-ss/sd-scripts/blob/main/networks/resize_lora.py
Quick comparison (note that this isn't accurate test of the reward lora itself, just to compare the effect of reducing the rank)
Xet Storage Details
- Size:
- 525 Bytes
- Xet hash:
- d5e08d7ece6d26babf1b63193e8652f765e98b0eedf8373e1b10b9303d00fd6c
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.