LyliaEngine/hassakuXLIllustrious_v22

Full fine-tune vs OnomaAIResearch/Illustrious-xl-early-release-v0. Fine-tune: 98% of the weights changed, across 12 of 12 layers.

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

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

On the Hub · Downloads on Model Pulse