I took the GPT-4 captioned dataset found here: <a target="_blank" rel="ugc" href="https://civarchive.com/models/281464?modelVersionId=322747">https://civarchive.com/models/281464?modelVersionId=322747, made by</a> <a target="_blank" rel="ugc" href="https://civarchive.com/user/steffangund">steffangund</a>, and then duplicated the entire zip file. I then re-tagged every photo in the set using WD14 tagging conventions, and then trained the LORA using both sets - thus training with short, one &amp; two word descriptors along with more verbose phrases to describe the same images.(I also added a number of screen grabs from the movies Teen Spirit and Neon Demon) The result, hopefully, is a more responsive model that will listen better to your img-to-txt input, no matter how you input it (so long as it's in English).

Files with SHA256: 9c43b1d15079cb59f0996adc6153eb16d5d75ce1aff8e9cf42d8eb1eadf4513c