xFutureTechx/lost_and_found_2025

Full fine-tune vs stable-diffusion-v1-5/stable-diffusion-v1-5. Fine-tune: 100% of the weights changed, across 12 of 12 layers.

Tensors changed: Embeddings 7/7, Norms 282/282, MLP 48/48, Attention 272/272, other 524/524

On the Hub · Downloads on Model Pulse