lopho/Wan2.2-T2V-A14B-Diffusers_nf4
Quantization vs Wan-AI/Wan2.2-T2V-A14B-Diffusers. lopho/Wan2.2-T2V-A14B-Diffusers_nf4 is a quantized version of the other (U8/F32). Pipeline repo, only part read: lopho/Wan2.2-T2V-A14B-Diffusers_nf4: only transformer/diffusion_pytorch_model.safetensors was read.