JoyCaption is amazing to caption training data. Advanced Gradio APP with batch processing and 1-click install
Downlad latest Joy Caption from here : https://www.patreon.com/posts/118827960
It supports
Joy Caption Pre Alpha
Joy Caption Alpha One
Joy Caption Alpha Two
Joy Caption Beta One - Newest and Best
Beta One is extremely fast, advanced, and supports full batch processing
When doing multi-GPU batch captioning displayed statistics could be wrong
Downlad latest Joy Caption from here : https://www.patreon.com/posts/118827960
Here a Hugging Face space that you can test it yourself : https://huggingface.co/spaces/fancyfeast/joy-caption-pre-alpha - still working
I have been requested to make a Gradio app for this so i made an advanced app and 1-click installers
It uses a clip siglip-so400m-patch14-384 and Meta-Llama-3.1-8B-Instruct as model and a fine tuned checkpoint for better captioning
My app who wants to checkout : https://www.patreon.com/posts/110613301
It has batch folder captioning feature as well and auto save all captioned images and captions into outputs folder
Also I have a very lightweight, super fast Gradio caption editor. Since I don't like other existing apps, i self developed this one from scratch : https://www.patreon.com/posts/108992085
Comments (4)
Is it possible to get this level of precision into a WD14 style of caption list for training SDXL? This is far more superior than WD14 in it's description.
WD14 is very specific and works only on specific fine tuned sdxl sd 1.5 models. it is pretty worthless for flux
Would love for you to embed this into SUPIR!
this alone uses some real vram :D but would be good addition like auto load and deload
