WendaShi
WendaShi
U are right, I think some pixels of the background have gray value = 0, so I add a rule (two line code) to filter out small pixel connected components....
Thanks for your prompt response! And I got another question is why the shape of t5_out is different with original diffusers SD3 pipeline? ``` in /path/TensorRT/demo/Diffusion/stable_diffusion_3_pipeline.py t5_out, _ = encode_token_weights('t5xxl',...
+1 NEED!🔥
@Mowenyii Hi, I found this one may be helpful ⬇️ https://github.com/wooyeolbaek/attention-map-diffusers