[Question] Should we just use "INSTANCE_NAME" in the prompt when generating new concept?

[rexroth0619]

Might seem like a dumb question, but what prompt format should be used when we generate images for a newly trained concept? e.g. In the original dreambooth implementation we use "sks person" or "identifier+person". Say using this colab, should we combine subject_type and instance_name(uniqueIdentifier + person) , or just use instance_name (uniqueIdentifier) alone?

[TheLastBen]

If your using the new method, use the same name as the images filenames. For the old method you can use INSTANCE_NAME without subject_type.