RuntimeError: Error(s) in loading state_dict for ControlNet:
#7
by
Nafnlaus
- opened
RuntimeError: Error(s) in loading state_dict for ControlNet:
Missing key(s) in state_dict: "time_embed.0.weight", "time_embed.0.bias", "time_embed.2.weight", "time_embed.2.bias", "input_blocks.0.0.weight", "input_blocks.0.0.bias", "input_blocks.1.0.in_layers.0.weight", "input_blocks.1.0.in_layers.0.bias", "input_blocks.1.0.in_layers.2.weight", "input_blocks.1.0.in_layers.2.bias", "input_blocks.1.0.emb_layers.1.weight", "input_blocks.1.0.emb_layers.1.bias", "input_blocks.1.0.out_layers.0.weight", "input_blocks.1.0.out_layers.0.bias", "input_blocks.1.0.out_layers.3.weight", "input_blocks.1.0.out_layers.3.bias"
.... and so forth. I have diffusion_pytorch_model.fp16.safetensors in my ControlNet directory (which Automatic1111 sees) as "control_depth_sdxl_10.safetensors" , as well as config.json as "control_depth_sdxl_10.json". My model is sd_xl_base_1.0.safetensors.
hey @Nafnlaus could you open an issue on github with a reproducible code snippet?
Which github page?
The steps to recreate it are listed above. Download the safetensors and config.json into your AUTOMATIC1111 ControlNet directory , and give them the same base name. Open AUTOMATIC1111. The new models show up under ControlNet. But when you try to use them, the above error occurs.