alibaba-pai/Wan2.2-Fun-5B-Control

Full fine-tune vs Wan-AI/Wan2.2-TI2V-5B. Fine-tune: 100% of the weights changed, across 30 of 30 layers.

Tensors changed: Attention 480/480, Norms 180/180, MLP 120/120, other 35/35, Embeddings 9/9

1 derivatives checked

• QuantStack/Wan2.2-Fun-5B-Control-GGUF: Quantization

On the Hub · Downloads on Model Pulse