fluently/Fluently-XL-v4
Full fine-tune vs stabilityai/stable-diffusion-xl-base-1.0. Fine-tune: 99% of the weights changed, across 12 of 12 layers.
Tensors changed: Embeddings 591/591, other 606/662, Attention 707/716, Norms 502/546
1 derivatives checked
- sd-community/sdxl-flash-lora: Adapter