cagliostrolab/animagine-xl-3.1
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
8 derivatives checked
- bean980310/tomboy-xl-animagine: Adapter
- Raelina/Rae-Diffusion-XL-V2: Full fine-tune
- Raelina/RaemuXL: Full fine-tune
- bean980310/minami-asuka-xl-animagine: Adapter
- yodayo-ai/kivotos-xl-2.0: Full fine-tune
- yodayo-ai/holodayo-xl-2.1: Full fine-tune
- kayfahaarukku/UrangDiffusion-2.0: Full fine-tune
- Raelina/Raena-XL: Partial fine-tune
15 other repos hold byte-for-byte identical weight files.