A test version of latex kigurumi Lora, trained on a 3090Ti with about 18k pics scraped from Twitter, then tagged with Mistral's Pixtral-Large-2411Current Lora config: 128 Rank Linear + 32 Rank Conv for SDXL versionTrained at 1024px, 64 batch effective (8 batch x 8 accumulation), Prodigy with cosine annealing.Upcoming version:LyCORIS GLoRA + DoRA, 1024px + 1536px multires

Files with SHA256: cba75fed5a681566a47be398fe30ffacc30769c6b33391a839df5d6931b5ebff