yumianhuli

Results 28 issues of yumianhuli

Hello!Dear @Sanster The mask image generated by the app works better than the mask image generated by my code:mask = cv2.circle(mask, (int(x), int(y)), int(radius), (255, 255, 255), -1) **Did you...

How can I Determine similar the text I entered is to the text in the training set thanks?

Does inference currently only support torch_dtype=torch.float16?int8_float16、int8 will be supported?

Does ControlNet support face restoration now? OR Adetailer only can be used?

I tried to clean the faster whisper model from the VRAM for use by other module. I del the fasterWhisper_Transcriber object and torch.cuda.empty_cache(), but there was always 200-300M of memory...

Hello!@LinB203 I used the ‘Inference for video’ code from readme,but got Loading checkpoint shards: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:06

What are the minimum requirements for gpu memory,thanks!

OS:win11 python3.8.10 run auto-py-to-exe Error: tkinter not found For linux, you can install tkinter by executing: "sudo apt-get install python3-tk" plz take a look ,thanks!

question

说话人识别CAM++模型对比pyannote.audio的模型效果如何?谢谢!

question