an additional target image is not required?

#1
by suruchiarora - opened

Hi @prithivMLmods

This object-editing pipeline does not take an additional target image as an input alongside the original image to perform the replacement?Right?

@suruchiarora

You're right. The adapter is trained on both the original and target designs, specified as text (e.g., “Add a Batman design here” or “Make her wear tinted goggles”). A reference image is optional.

If you need an object to be added with high confidence that the output will match the reference image, you can use multi-image editing within the same pipeline, if needed.

prithivMLmods changed discussion status to closed

Sign up or log in to comment