xinsir

/

controlnet-union-sdxl-1.0

like 980

initializing the controlnet model in diffusers through the following call

controlnet = diffusers.ControlNetModel.from_pretrained(
    "xinsir/controlnet-union-sdxl-1.0", # regular
    torch_dtype=torch.float16,
    use_safetensors = True
)

results in the following warning:

Some weights of the model checkpoint were not used when initializing ControlNetModel: 
 ['control_add_embedding.linear_1.bias, control_add_embedding.linear_1.weight, control_add_embedding.linear_2.bias, control_add_embedding.linear_2.weight, spatial_ch_projs.bias, spatial_ch_projs.weight, task_embedding, transformer_layes.0.attn.in_proj_bias, transformer_layes.0.attn.in_proj_weight, transformer_layes.0.attn.out_proj.bias, transformer_layes.0.attn.out_proj.weight, transformer_layes.0.ln_1.bias, transformer_layes.0.ln_1.weight, transformer_layes.0.ln_2.bias, transformer_layes.0.ln_2.weight, transformer_layes.0.mlp.c_fc.bias, transformer_layes.0.mlp.c_fc.weight, transformer_layes.0.mlp.c_proj.bias, transformer_layes.0.mlp.c_proj.weight']

wondering if this impacts performance, or can be safely ignored.