search

google / diffseg

DiffSeg is an unsupervised zero-shot segmentation method using attention information from a stable-diffusion model. This repo implements the main DiffSeg algorithm and additionally includes an experimental feature to add semantic labels to the masks based on a generated caption.
https://sites.google.com/corp/view/diffseg
MIT License
257 stars 19 forks source link

Pytorch #14

Open wenfang361 opened 2 months ago

wenfang361 commented 2 months ago

Hi author, do you have the complete code based on Pytorch architecture, can you make it public for learning?

amanaknows commented 1 month ago

Hi author, do you have the complete code based on Pytorch architecture, can you make it public for learning?

No