diffusers inference

I'm having trouble inference with diffusers.

When I convert fine-tuned ckpt to diffusers and then inference, I'm getting a completely different image than ckpt.
The inference code is taken from diffusers.

Do you have any inference code that you use after converting to diffusers?
The convert code I referenced is below.
https://note.com/kohya_ss/n/n374f316fe4ad

Start by reviewing the conversion procedure linked in the issue and the inference code taken from diffusers. Compare the converted model's inference inputs and outputs with those used for the original fine-tuned checkpoint. Done means identifying why the generated images differ or documenting the correct inference procedure.

Written by the indexing model from the issue text.