Comment on Carbon Flame Saber
DasKapitalist@lemmy.ml 5 months ago
What model do you use to generate the descriptions?
The descriptions are heavily edited JoyCaption Alpha Two descriptions.
Thank you
It gets a lot of things wrong, so you have to do a lot of corrections. It’s impressive how well VLM captioned models work if they’re trained on raw generated captions.
Even_Adder@lemmy.dbzer0.com 5 months ago
The descriptions are heavily edited JoyCaption Alpha Two descriptions.
DasKapitalist@lemmy.ml 5 months ago
Thank you
Even_Adder@lemmy.dbzer0.com 5 months ago
It gets a lot of things wrong, so you have to do a lot of corrections. It’s impressive how well VLM captioned models work if they’re trained on raw generated captions.