LazyChild
LazyChild
请问我需要怎么做才能够复现一遍AnyText的训练过程?能否提供文档或者指南之类的东西?
Branch: main Bug description: In lines 674-676 of train_sketch.py, when calculating the timesteps variable, it may generate an illegal timesteps = 1000, causing an assertion error when running the training...
Excellent work! I would like to consult about the approximate value of loss during the whole training process. I am using about 20k 512*512 images to train T2I-Adapter-sketch, and the...
When I attempt to train the Adapter (main branch) using the following terminal command, executed in the background: `nohup accelerate launch train_sketch.py --pretrained_model_name_or_path stabilityai/stable-diffusion-xl-base-1.0 --output_dir experiments/adapter_sketch_xl --config configs/train/Adapter-XL-sketch.yaml --mixed_precision="fp16" --resolution=1024...