mflux-community/z-image-turbo-mflux-bf16

Same weights, converted vs Tongyi-MAI/Z-Image-Turbo. Same weights stored in another dtype (F32 → BF16), plus 6 new tensors.

Tensors changed: other 0/68, Embeddings 0/5, Norms 0/204, Attention 0/136, MLP 0/102

On the Hub · Downloads on Model Pulse