CabalResearch/Mugen

Partial fine-tune vs CabalResearch/NoobAI-Flux2VAE-RectifiedFlow-0.3. Partial change: 74% of the weights changed (attention, embeddings, norms, other), in 0 of 12 layers.

Tensors changed: Embeddings 4/590, other 534/665, Attention 700/716, Norms 442/546

2 derivatives checked