FLUX.1-schnell with the transformer in bitsandbytes NF4 and T5 in 4-bit (fp16 compute), saved with diffusers save_pretrained. Load with FluxPipeline.from_pretrained directly.

Downloads last month: 63

Safetensors

Model size

6B params

Tensor type

F32

F16

Model tree for vftfnn/flux1-schnell-nf4

Base model

black-forest-labs/FLUX.1-schnell

Finetuned

(74)

this model