Asahina2K/Animagine-xl-3.1-diffuser-variant-fp16

Full fine-tune vs cagliostrolab/animagine-xl-3.0. Fine-tune: 98% of the weights changed, across 12 of 12 layers.

Tensors changed: Embeddings 589/590, other 534/662, Attention 700/716, Norms 442/546

15 other repos hold byte-for-byte identical weight files.