yuxincui

Hi! After I added "fp16 = dict(loss_scale=512.)" in config file and added attribute "fp16_enabled" in occnet and bevdepth, the time and memory used when training were same as before. How...

I want to train a text-to-video model, where is ’stable_diffusion_image_key_temporal_attention_x1.json‘ in 't2v_train.yaml'?

2

Hi! Where is 'sd_keys_path': 'models/stable_diffusion_image_key_temporal_attention_x1.json', in config file? Could you give me a link please?