The new version, trained for SDXL is up.
For this version, I recommend to use weight between 0.6 and 1.2.
A style LoRA to reproduce John Singer Sargent's oil painting and watercolor.
It's a merge of multiples LoRA trained with the same dataset on SD 1.5 but with different training parameters.
Use a weight of 1.
Description
FAQ
Comments (1)
I just tried to import your LoRA to mage.space. Got an error. Same happens with your other painter LoRAs. Any idea?
--------------
Error message: Error(s) in loading state_dict for CLIPTextModel: size mismatch for text_model.encoder.layers.0.self_attn.k_proj.lora_linear_layer.down.weight: copying a param with shape torch.Size([112, 768]) from checkpoint...