AUTOMATIC1111
PLMS crashing at the end
Arguments: ('artificial intelligence taking over the planet movie poster', '', 'None', 'None', 100, 12, False, False, 1, 1, 7, -1.0, -1.0, 0, 0, 0, False, 768, 512, True, 0.7, 0, 0, 0, False, False, None, '', False, 4.0, '', 10.0, True, False, True, 30.0, False, True, 10.0, True, 30.0, True, 1, '', 0, '', True, False, False) {} Traceback (most recent call last): File "X:\AI\SUPER SD 2.0 Dependencies\stable-diffusion-webui\modules\ui.py", line 212, in f res = list(func(*args, **kwargs)) File "X:\AI\SUPER SD 2.0 Dependencies\stable-diffusion-webui\webui.py", line 64, in f res = func(*args, **kwargs) File "X:\AI\SUPER SD 2.0 Dependencies\stable-diffusion-webui\modules\txt2img.py", line 44, in txt2img processed = process_images(p) File "X:\AI\SUPER SD 2.0 Dependencies\stable-diffusion-webui\modules\processing.py", line 403, in process_images samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength) File "X:\AI\SUPER SD 2.0 Dependencies\stable-diffusion-webui\modules\processing.py", line 588, in sample samples = self.sampler.sample_img2img(self, samples, noise, conditioning, unconditional_conditioning, steps=self.steps) File "X:\AI\SUPER SD 2.0 Dependencies\stable-diffusion-webui\modules\sd_samplers.py", line 190, in sample_img2img x1 = self.sampler.stochastic_encode(x, torch.tensor([t_enc] * int(x.shape[0])).to(shared.device), noise=noise) AttributeError: 'PLMSSampler' object has no attribute 'stochastic_encode'
To Reproduce Use PLMS sampler and show pictures every generation setting to n=1
Desktop (please complete the following information):
- Windows
- edge
- fc220a51cf5bb5bfca83322c16e907a18ec59f6b
img2img / highres-fix?
PLMS doesn't work for img2img which is used by Highres. fix behind the scenes.
https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/2521#issuecomment-1278039887
https://github.com/AUTOMATIC1111/stable-diffusion-webui/commit/b186d44dcd0df9d127a663b297334a5bd8258b58
