privateuseone is not supported for torch.Generator()

I'm getting this error when using the defult workflow with the samplers
dpmpp_sde_gpu
dpmpp_2m_sde_gpu
dpmpp_3m_sde_gpu
the outher samplers i have tried have worked
i have a AMD Radeon RX 5700 XT 8GB memory and 16gb shared memory

> Error occurred when executing KSampler:
>
> Device type privateuseone is not supported for torch.Generator() api.
>
> File "D:\AI\ComfyUI_AMD\ComfyUI\execution.py", line 152, in recursive_execute
> output_data, output_ui = get_output_data(obj, input_data_all)
> File "D:\AI\ComfyUI_AMD\ComfyUI\execution.py", line 82, in get_output_data
> return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
> File "D:\AI\ComfyUI_AMD\ComfyUI\execution.py", line 75, in map_node_over_list
> results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
> File "D:\AI\ComfyUI_AMD\ComfyUI\nodes.py", line 1236, in sample
> return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise)
> File "D:\AI\ComfyUI_AMD\ComfyUI\nodes.py", line 1206, in common_ksampler
> samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
> File "D:\AI\ComfyUI_AMD\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\sample_error_enhancer.py", line 22, in informative_sample
> raise e
> File "D:\AI\ComfyUI_AMD\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\sample_error_enhancer.py", line 9, in informative_sample
> return original_sample(*args, **kwargs)
> File "D:\AI\ComfyUI_AMD\ComfyUI\comfy\sample.py", line 97, 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 "D:\AI\ComfyUI_AMD\ComfyUI\comfy\samplers.py", line 785, in sample
> return sample(self.model, noise, positive, negative, cfg, self.device, sampler(), sigmas, self.model_options, latent_image=latent_image, denoise_mask=denoise_mask, callback=callback, disable_pbar=disable_pbar, seed=seed)
> File "D:\AI\ComfyUI_AMD\ComfyUI\comfy\samplers.py", line 690, in sample
> samples = sampler.sample(model_wrap, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar)
> File "D:\AI\ComfyUI_AMD\ComfyUI\comfy\samplers.py", line 630, in sample
> samples = getattr(k_diffusion_sampling, "sample_{}".format(sampler_name))(model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar, **extra_options)
> File "C:\Users\Drago87\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
> return func(*args, **kwargs)
> File "D:\AI\ComfyUI_AMD\ComfyUI\comfy\k_diffusion\sampling.py", line 706, in sample_dpmpp_sde_gpu
> noise_sampler = BrownianTreeNoiseSampler(x, sigma_min, sigma_max, seed=extra_args.get("seed", None), cpu=False) if noise_sampler is None else noise_sampler
> File "D:\AI\ComfyUI_AMD\ComfyUI\comfy\k_diffusion\sampling.py", line 119, in __init__
> self.tree = BatchedBrownianTree(x, t0, t1, seed, cpu=cpu)
> File "D:\AI\ComfyUI_AMD\ComfyUI\comfy\k_diffusion\sampling.py", line 85, in __init__
> self.trees = [torchsde.BrownianTree(t0, w0, t1, entropy=s, **kwargs) for s in seed]
> File "D:\AI\ComfyUI_AMD\ComfyUI\comfy\k_diffusion\sampling.py", line 85, in
> self.trees = [torchsde.BrownianTree(t0, w0, t1, entropy=s, **kwargs) for s in seed]
> File "C:\Users\Drago87\AppData\Local\Programs\Python\Python310\lib\site-packages\torchsde\_brownian\derived.py", line 155, in __init__
> self._interval = brownian_interval.BrownianInterval(t0=t0,
> File "C:\Users\Drago87\AppData\Local\Programs\Python\Python310\lib\site-packages\torchsde\_brownian\brownian_interval.py", line 554, in __init__
> W = self._randn(initial_W_seed) * math.sqrt(t1 - t0)
> File "C:\Users\Drago87\AppData\Local\Programs\Python\Python310\lib\site-packages\torchsde\_brownian\brownian_interval.py", line 248, in _randn
> return _randn(size, self._top._dtype, self._top._device, seed)
> File "C:\Users\Drago87\AppData\Local\Programs\Python\Python310\lib\site-packages\torchsde\_brownian\brownian_interval.py", line 31, in _randn
> generator = torch.Generator(device).manual_seed(int(seed))

Start in comfy/k_diffusion/sampling.py at BrownianTreeNoiseSampler and the sample_dpmpp_sde_gpu path, then reproduce the reported samplers on the AMD privateuseone device. Inspect how torchsde creates its torch.Generator and compare the working sampler paths. Done means the listed DPM++ SDE GPU samplers run without the privateuseone Generator error.

Written by the indexing model from the issue text.