disco-diffusion
disco-diffusion copied to clipboard
alembics
————————————————————————— ModuleNotFoundError Traceback (most recent call last) c:\Users\Administrator\Desktop\AIhuitu–Disco Diffusion\disco-diffusion-main\disco-diffusion-main\Disco_Diffusion.ipynb Cell 15 in () 143 try: –> 144 from AdaBins.infer import InferenceHelper 145 except: 这个已经尝试在infer前面加了AdaBins.还是报错 File c:\Users\Administrator\Desktop\AIhuitu–Disco Diffusion\disco-diffusion-main\disco-diffusion-main\AdaBins\infer.py:11, in 9 from...
i just want to type a description and see what it becomes...why are there so many extra steps?
for example, I want the files to have date and time in their filenames it would be nice if I can just change some variables to do that
when using _diffusion_sampling_mode = 'plms'_ everything works when using _diffusion_sampling_mode = 'ddim'_ i get error below : TypeError Traceback (most recent call last) Input In [27], in () 216 torch.cuda.empty_cache()...
"raise RuntimeError('The weights must not sum to 0.')" Shouldn't this say "The sum of the weights must be above 0", since negative weights will also trigger this error yet are...
Added Sampling with Splitting Numerical Methods From the space-nuko repository: https://github.com/space-nuko/guided-diffusion/tree/f91a8708b7b05b48ad01b56bbf5ba375fc66818a The sampler speeds up the sampling process by reducing the step count (50 to 150 seems to work fin)...
 The code is to huge for me to fix, but it is likely the root cause is identified in https://stackoverflow.com/questions/73530569/pytorch-matmul-runtimeerror-addmm-impl-cpu-not-implemented-for-half
