Open capesidereal opened 2 years ago
when using _diffusion_samplingmode = 'plms' everything works when using _diffusion_samplingmode = 'ddim' i get error below :
TypeError Traceback (most recent call last) Input In [27], in <cell line: 217>() 216 torch.cuda.empty_cache() 217 try: --> 218 do_run() 219 except KeyboardInterrupt: 220 pass
Input In [5], in do_run() 648 init = regen_perlin() 650 if args.diffusion_sampling_mode == 'ddim': --> 651 samples = sample_fn( 652 model, 653 (batch_size, 3, args.side_y, args.side_x), 654 clip_denoised=clip_denoised, 655 model_kwargs={}, 656 cond_fn=cond_fn, 657 progress=True, 658 skip_timesteps=skip_steps, 659 init_image=init, 660 randomize_class=randomize_class, 661 eta=eta, 662 transformation_fn=symmetry_transformation_fn, 663 transformation_percent=args.transformation_percent 664 ) 665 else: 666 samples = sample_fn( 667 model, 668 (batch_size, 3, args.side_y, args.side_x), (...) 676 order=2, 677 )
TypeError: ddim_sample_loop_progressive() got an unexpected keyword argument 'transformation_fn'
when using _diffusion_samplingmode = 'plms' everything works when using _diffusion_samplingmode = 'ddim' i get error below :
TypeError Traceback (most recent call last) Input In [27], in <cell line: 217>() 216 torch.cuda.empty_cache() 217 try: --> 218 do_run() 219 except KeyboardInterrupt: 220 pass
Input In [5], in do_run() 648 init = regen_perlin() 650 if args.diffusion_sampling_mode == 'ddim': --> 651 samples = sample_fn( 652 model, 653 (batch_size, 3, args.side_y, args.side_x), 654 clip_denoised=clip_denoised, 655 model_kwargs={}, 656 cond_fn=cond_fn, 657 progress=True, 658 skip_timesteps=skip_steps, 659 init_image=init, 660 randomize_class=randomize_class, 661 eta=eta, 662 transformation_fn=symmetry_transformation_fn, 663 transformation_percent=args.transformation_percent 664 ) 665 else: 666 samples = sample_fn( 667 model, 668 (batch_size, 3, args.side_y, args.side_x), (...) 676 order=2, 677 )
TypeError: ddim_sample_loop_progressive() got an unexpected keyword argument 'transformation_fn'