haooxia

How to set the base_learning_rate in finetune autoencoderKL?

2

How to set the base_learning_rate in finetune autoencoder? Should I modify the default `base_learning_rate: 1.6e-7` It can be seen that the learning rate changes with num_gpus, batchsize and base_learning_rate: 

question about few-shot generation

1

May I ask if your current code is unable to achieve few-shot font style transfer? Because in the `validation.py`, I only see that it references the style of a single...

Something wrong with the demo on huggingface

1

something wrong with the demo on [huggingface](https://huggingface.co/spaces/lnyan/stablediffusion-infinity)

two questions about the detect result

2

Hi, I have two questions: **First**, may I ask why Figure 1 (inscription rubbing) is basically unrecognizable, but after binarization (Figure 2) the effect is very good? I guess it...

Can 'easyOCR' output multiple prediction results and probabilities of one character?

2

Can 'easyOCR' output multiple prediction results and probabilities of one character? (only one character in the picture) For example, output the 3 prediction results with the highest probability.

I want to know if I need to rebuild the data set when finetune? I use 20 fonts in pretraining, and use 1 font in finetuning, but it report an...