how to use flux full-finetune safetensors in diffusers?

essentially the title. i've tried the following:
```
transformer = diffusers.Flux2DTransformer.from_single_file(path_to_kohya_safetensors, torch.dtype=torch.bfloat16)
pipeline = diffusers.FluxPipeline.from_pretrained(..., transformer=transformer, torch.dtype=torch.bfloat16)
```

however all generated images have weird artifacts, regardless of checkpoint number
i've tried with both lr 1e-5 and 1e-4

Start with the shown Flux2DTransformer.from_single_file and FluxPipeline.from_pretrained calls, using the Kohya safetensors checkpoint and the reported dtype settings. Compare the loading path and checkpoint expectations with the generated outputs. Done means identifying a supported usage path or a reproducible cause for the artifacts.

Written by the indexing model from the issue text.