hadwin
hadwin
谢谢大佬，我试试
请问大佬能给个联系方式吗？请教一下。
请教一下，如果要增加一个元素，应该如何操作呢？工作量大吗？ 
同样有需求 😂
用上了，感觉不错，比默认的简洁不少。
I have implemented loading my own dataset and tried some optimization methods, but there is no improvement in classification accuracy. For example: https://github.com/chaofengc/TexForce Currently the only way to improve the...
Refer to this program: https://webcache.googleusercontent.com/search?q=cache:https://ngwaifoong92.medium.com/how-to-fine-tune-stable-diffusion-using-lora-85690292c6a8 Use this dataset: https://www.heywhale.com/mw/dataset/5e732227c59d610036227d89 train： ```python accelerate launch train_text_to_image_lora.py \ --pretrained_model_name_or_path=runwayml/stable-diffusion-v2-0 \ --train_data_dir="weather" \ --resolution=512 --center_crop --random_flip \ --train_batch_size=1 \ --num_train_epochs=100 \ --learning_rate=1e-04 --lr_scheduler="constant" --lr_warmup_steps=0...
May I ask how the DiT model was trained in the paper? If I want to train with my own dataset how do I do it? Refer to Training DiT...
My own dataset is weather with 6 classes and using the default SD2.0 Mean per class acc is about 43%, SD1.5 is about 67% and SD2.1 is about 71%. After...