[transformers] `CLIPImageProcessor` requires torchvision (not installed); falling back to `CLIPImageProcessorPil` for backward compatibility. Install torchvision to use the default backend, or import `CLIPImageProcessorPil` directly to silence this warning.
[transformers] `SiglipImageProcessor` requires torchvision (not installed); falling back to `SiglipImageProcessorPil` for backward compatibility. Install torchvision to use the default backend, or import `SiglipImageProcessorPil` directly to silence this warning.
[conv] loading ckpt
[conv] ckpt keys=1131 dtype=torch.int64 (0s)
[conv] unet
  unet missing=0 unexpected=0
[conv] text_encoder
  text_encoder missing=0 unexpected=1
[conv] vae
  vae missing=0 unexpected=0
[conv] tokenizer + scheduler
[conv] assemble + save

Writing model shards:   0%|          | 0/1 [00:00<?, ?it/s]
Writing model shards: 100%|██████████| 1/1 [00:00<00:00,  1.83it/s]
Writing model shards: 100%|██████████| 1/1 [00:00<00:00,  1.82it/s]
[conv] DONE -> /data/onlyfake/v3/rv6_diffusers (64s)