Question about InputImageEmbedder and EditImageEmbedder in FLUX.2

[AmberC181]

Thanks for the excellent contributions!
While studying the FLUX.2 model, I noticed some differences between the implementation in this repo and the official one.
There are two separate image input embedder classes in the repo: InputImageEmbedder and EditImageEmbedder.
For single-image editing (in examples/flux2/model_inference/FLUX.2-klein-4B.py) uses the edit_image parameter in the pipeline call function. I would like to clarify: under what circumstances is the input_image parameter intended to be used?
Looking for your reply!