My Character LoRA Gallery (1000+ Character LoRAs)

Moss Image:

• Steps: 5460

• Effective BS: 10 (10 batch × 1 grad accum)

• LR: Scaled up for BS 10 (≈ 1e-04 @ BS 1)

• Dataset: Same as Krea 2 (see Krea 2 page for download)

Collected nearly all works of Christie's on DeviantArt, and processed the images through a comprehensive combination of Qwen+Krea2+Klein. The style of the final dataset images falls between 3D CG and real photography. The final dataset consists of 3159 images, and it's available for download —— traindata(1.28G)

The model has plenty of knowledge regarding NSFW, poses, and streethookers, but it is also prone to causing artifacts. The dataset ratio for training faces versus my niche/guilty pleasures was roughly 7:3. Feel free to explore the dataset's potential and try out different concepts.

KREA2 | Moss Image

I personally recommend using lodestones' Kroma v0.3. Due to its training dataset, it does a great job of restoring Christie's features. I also recommend using Realistic Slider - (Krea-2) (Rank1 7mb), which allows you to easily switch between photographic realism and 3DCG styles. Testing shows that this LoRA performs better on Kroma than on other fine-tuned models.