cagliostrolab/animagine-xl-3.0
Full fine-tune vs Linaqruf/animagine-xl-2.0. Fine-tune: 94% of the weights changed, across 11 of 12 layers.
Tensors changed: Embeddings 569/591, other 534/662, Attention 700/716, Norms 442/546
5 derivatives checked
- cagliostrolab/animagine-xl-3.1: Full fine-tune
- votepurchase/animagine-xl-3.1: Full fine-tune
- Asahina2K/Animagine-xl-3.1-diffuser-variant-fp16: Full fine-tune
- prithivMLmods/Montuno-Omega-Anime-LoRA: Adapter
- MomlessTomato/ruby-kurosawa: Adapter
6 other repos hold byte-for-byte identical weight files.