[feature request] Automatically print token being modified (and by how much) when generating an image

[lendrick]

I was getting some nonsensical results for a little while until it occurred to me that some words are multiple tokens (and punctuation, etc, are tokens as well).

Here's some code I'm using to do it:

        #Process prompt editing
        if prompt_edit is not None:
            tokens_conditional_edit = clip_tokenizer(prompt_edit, padding="max_length", max_length=clip_tokenizer.model_max_length, truncation=True, return_tensors="pt", return_overflowing_tokens=True)
            embedding_conditional_edit = clip(tokens_conditional_edit.input_ids.to(device)).last_hidden_state
            
            init_attention_edit(tokens_conditional, tokens_conditional_edit)
            
            #My code starts here
            for t in prompt_edit_token_weights:
                token_word = prompt_token(prompt_edit, t[0])
                print(f"{token_word}: {t[1]}")
        else:
            for t in prompt_edit_token_weights:
                token_word = prompt_token(prompt, t[0])
                print(f"{token_word}: {t[1]}")

Probably ought to check and make sure I'm not misunderstanding anything, but it appears to work.

[bloc97]

Yeah, I'll get back to working on it during the week. Adding a more intuitive prompt editing method, such as using brackets (eg. a landscape of (mountains:-10) with (rivers and trees:+3)) would be for me one of the high priority improvements that can be added.