FastVideo/FastVideo-FastH3-Trim-8-Step

Full fine-tune vs FastVideo/FastVideo-FastH3-8-Step-V2. Fine-tune: 100% of the weights changed, across 0 of 0 layers.

Tensors changed: Attention 222/222, Embeddings 6/6, Norms 148/179, other 134/134

On the Hub · Downloads on Model Pulse