Testing my diffusers text2image lora model and kohya dreambooth lora model.
fine tune on stingermix v3.0 checkpoint model, meaning it doesn't have many compatibility because not trained on base model.
i will research what other model that can be used for this lora.
this is link of my dataset, you can preprocessing it for better result :
https://huggingface.co/datasets/faizalnf1800/sibear-lora-dataset
you can't make it as commercial use since i am collecting image on pinterest and doesn't have permission from artist that making image dataset.
this is my lora project experimenting and studying stable diffusion. not serious project and far from perfect outcome, may generate inaccurate or nonsensical image result from user prompt
use kohya dreambooth lora training on epoch 6 at 4,200 steps, pick lora file near standard training 2x 3 epoch on small dataset. more epoch training visit my huggingface account
1. The rights to reposted models belong to original creators.
2. Original creators should contact SeaArt.AI staff through official channels to claim their models. We are committed to protecting every creator's rights. Click to Claim
