search

comfyanonymous / ComfyUI

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
https://www.comfy.org/
GNU General Public License v3.0
52.02k stars 5.47k forks source link

Error when using ddim #935

Open caniyabanci76 opened 1 year ago

caniyabanci76 commented 1 year ago

after an update today, I now get the following error when using ddim sampler:

Error occurred when executing KSampler:

"round_cuda" not implemented for 'Long'

File "/home/usera/ai/ComfyUI/execution.py", line 145, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "/home/usera/ai/ComfyUI/execution.py", line 75, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "/home/usera/ai/ComfyUI/execution.py", line 68, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "/home/usera/ai/ComfyUI/nodes.py", line 1082, in sample
return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise)
File "/home/usera/ai/ComfyUI/nodes.py", line 1052, in common_ksampler
samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
File "/home/usera/ai/ComfyUI/comfy/sample.py", line 88, in sample
samples = sampler.sample(noise, positive_copy, negative_copy, cfg=cfg, latent_image=latent_image, start_step=start_step, last_step=last_step, force_full_denoise=force_full_denoise, denoise_mask=noise_mask, sigmas=sigmas, callback=callback, disable_pbar=disable_pbar, seed=seed)
File "/home/usera/ai/ComfyUI/comfy/samplers.py", line 631, in sample
samples, _ = sampler.sample_custom(ddim_timesteps=timesteps,
File "/home/usera/anaconda3/envs/comfyui/lib/python3.9/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "/home/usera/ai/ComfyUI/comfy/ldm/models/diffusion/ddim.py", line 89, in sample_custom
samples, intermediates = self.ddim_sampling(conditioning, x_T.shape,
File "/home/usera/anaconda3/envs/comfyui/lib/python3.9/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "/home/usera/ai/ComfyUI/comfy/ldm/models/diffusion/ddim.py", line 231, in ddim_sampling
outs = self.p_sample_ddim(img, cond, ts, index=index, use_original_steps=ddim_use_original_steps,
File "/home/usera/anaconda3/envs/comfyui/lib/python3.9/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "/home/usera/ai/ComfyUI/comfy/ldm/models/diffusion/ddim.py", line 265, in p_sample_ddim
model_output = denoise_function(x, t, **extra_args)
File "/home/usera/ai/ComfyUI/comfy/k_diffusion/external.py", line 94, in predict_eps_discrete_timestep
sigma = self.t_to_sigma(t.round())
comfyanonymous commented 1 year ago

Should be fixed now: https://github.com/comfyanonymous/ComfyUI/commit/e032ca613859695ae1153987c6266e77d5411deb