Closed XeonG closed 1 year ago
About the title - what is broken?
the with the latest commits from https://github.com/AUTOMATIC1111/stable-diffusion-webui .. its got some errors come this addon.. sorry haven't got the errors on hand right now.. I rolled back to an older commit from 2days ago and its working again.
There were no less than 15 commits on the webui today, all connected to the samplers. Since this extension relies on k_diffusion, that has broken it for now. I'll see, if I can fix it.
oh right good luck.. would hate to lose it
Well, luckily the fix was a lot easier than I expected. I was even able to make it backward compatible...
File "C:\Projects\Stable_Diffusion\stable-diffusion-webui\modules\call_queue.py", line 56, in f res = list(func(*args, **kwargs)) File "C:\Projects\Stable_Diffusion\stable-diffusion-webui\modules\call_queue.py", line 37, in f res = func(*args, **kwargs) File "C:\Projects\Stable_Diffusion\stable-diffusion-webui\modules\txt2img.py", line 52, in txt2img processed = process_images(p) File "C:\Projects\Stable_Diffusion\stable-diffusion-webui\modules\processing.py", line 487, in process_images res = process_images_inner(p) File "C:\Projects\Stable_Diffusion\stable-diffusion-webui\modules\processing.py", line 629, in process_images_inner samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, prompts=prompts) File "C:\Projects\Stable_Diffusion\stable-diffusion-webui\modules\processing.py", line 829, in sample samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x)) File "C:\Projects\Stable_Diffusion\stable-diffusion-webui\modules\sd_samplers.py", line 544, in sample samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={ File "C:\Projects\Stable_Diffusion\stable-diffusion-webui\modules\sd_samplers.py", line 447, in launch_sampling return func() File "C:\Projects\Stable_Diffusion\stable-diffusion-webui\modules\sd_samplers.py", line 544, in <lambda> samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={ File "C:\Projects\Stable_Diffusion\stable-diffusion-webui\venv\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context return func(*args, **kwargs) File "C:\Projects\Stable_Diffusion\stable-diffusion-webui\repositories\k-diffusion\k_diffusion\sampling.py", line 148, in sample_euler_ancestral callback({'x': x, 'i': i, 'sigma': sigmas[i], 'sigma_hat': sigmas[i], 'denoised': denoised}) File "C:\Projects\Stable_Diffusion\stable-diffusion-webui\extensions\sd_save_intermediate_images\scripts\sd_save_intermediate_images.py", line 400, in callback_state if ssii_start_at_n % ssii_every_n == 0: ZeroDivisionError: float modulo
I still get that after trying the latest update
nevermind.. had to refresh browser tab aswel :)
And just another request.. could you support saving the last known settings chosen for everything in the script.. find myself often having to reclick and enter the same things for all the settings.. hopefully it can be supported.