ostris/Z-Image-De-Turbo

Full fine-tune vs Tongyi-MAI/Z-Image-Turbo. Fine-tune: 100% of the weights changed, across 30 of 30 layers.

Tensors changed: Embeddings 7/7, other 66/66, Norms 136/136, MLP 102/102

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse