BestWishYsh/Helios-Base

Full fine-tune vs Wan-AI/Wan2.1-T2V-14B-Diffusers. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: Norms 0/240, Attention 320/640, MLP 80/160, other 1/42, Embeddings 6/12

On the Hub · Downloads on Model Pulse