christian-byrne/img2txt-comfyui-nodes
Implements popular img2txt captioning models into ComfyUI nodes
Python
Issues
- 0
- 0
img2txt BLIP/Llava Multimodel Tagger | index is out of bounds for dimension with size 0
#9 opened by dxdpxl - 1
你好,这个插件非常好用,有个问题请教,如何一个文件夹的图片打标
#8 opened by plhys - 3
It doesn't work
#7 opened by flybirdxx - 1
typo in requirements.txt
#6 opened by yurayko - 3
- 7
May I ask where the llava model needs to be placed if downloaded manually?
#2 opened by KennyChan3389 - 1
example - workflow.json ?
#1 opened by Fox-pix