用了两个model都爆了:cuda：our of memory
LEOSAM HelloWorld 新世界 _ SDXL真实感大模型_v5.0
RealVisXL Turbo (SFW&NSFW) _v4 lightning

还有那个instantid face analysis应该选哪个啊？cuda 还是rocm。

好像显示核心一直在看戏，只有cpu在工作。

pytorch version: 2.1.2+cu118
要更新到2.3.1吗

换了anything 模型后
K采样器会报
'NoneType' object has no attribute 'shape'

!!! Exception during processing !!! 'NoneType' object has no attribute 'shape'
Traceback (most recent call last):
File "L:\AI\ComfyUI-aki-v1.1\execution.py", line 327, in execute
output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
File "L:\AI\ComfyUI-aki-v1.1\execution.py", line 202, in get_output_data
return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
File "L:\AI\ComfyUI-aki-v1.1\execution.py", line 174, in _map_node_over_list
process_inputs(input_dict, i)
File "L:\AI\ComfyUI-aki-v1.1\execution.py", line 163, in process_inputs
results.append(getattr(obj, func)(**inputs))
File "L:\AI\ComfyUI-aki-v1.1\nodes.py", line 1543, in sample
return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise)
File "L:\AI\ComfyUI-aki-v1.1\nodes.py", line 1510, in common_ksampler
samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
File "L:\AI\ComfyUI-aki-v1.1\custom_nodes\ComfyUI-Impact-Pack\modules\impact\sample_error_enhancer.py", line 9, in informative_sample
return original_sample(*args, **kwargs) # This code helps interpret error messages that occur within exceptions but does not have any impact on other operations.
File "L:\AI\ComfyUI-aki-v1.1\comfy\sample.py", line 45, in sample
samples = sampler.sample(noise, positive, negative, 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 "L:\AI\ComfyUI-aki-v1.1\comfy\samplers.py", line 1133, 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 "L:\AI\ComfyUI-aki-v1.1\comfy\samplers.py", line 1023, in sample
return cfg_guider.sample(noise, latent_image, sampler, sigmas, denoise_mask, callback, disable_pbar, seed)
File "L:\AI\ComfyUI-aki-v1.1\comfy\samplers.py", line 1008, in sample
output = executor.execute(noise, latent_image, sampler, sigmas, denoise_mask, callback, disable_pbar, seed)
File "L:\AI\ComfyUI-aki-v1.1\comfy\patcher_extension.py", line 110, in execute
return self.original(*args, **kwargs)
File "L:\AI\ComfyUI-aki-v1.1\comfy\samplers.py", line 976, in outer_sample
output = self.inner_sample(noise, latent_image, device, sampler, sigmas, denoise_mask, callback, disable_pbar, seed)
File "L:\AI\ComfyUI-aki-v1.1\comfy\samplers.py", line 959, in inner_sample
samples = executor.execute(self, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar)
File "L:\AI\ComfyUI-aki-v1.1\comfy\patcher_extension.py", line 110, in execute
return self.original(*args, **kwargs)
File "L:\AI\ComfyUI-aki-v1.1\comfy\samplers.py", line 738, in sample
samples = self.sampler_function(model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar, **self.extra_options)
File "L:\AI\ComfyUI-aki-v1.1\python\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "L:\AI\ComfyUI-aki-v1.1\comfy\k_diffusion\sampling.py", line 181, in sample_euler_ancestral
denoised = model(x, sigmas[i] * s_in, **extra_args)
File "L:\AI\ComfyUI-aki-v1.1\comfy\samplers.py", line 390, in __call__
out = self.inner_model(x, sigma, model_options=model_options, seed=seed)
File "L:\AI\ComfyUI-aki-v1.1\comfy\samplers.py", line 939, in __call__
return self.predict_noise(*args, **kwargs)
File "L:\AI\ComfyUI-aki-v1.1\comfy\samplers.py", line 942, in predict_noise
return sampling_function(self.inner_model, x, timestep, self.conds.get("negative", None), self.conds.get("positive", None), self.cfg, model_options=model_options, seed=seed)
File "L:\AI\ComfyUI-aki-v1.1\comfy\samplers.py", line 370, in sampling_function
out = calc_cond_batch(model, conds, x, timestep, model_options)
File "L:\AI\ComfyUI-aki-v1.1\comfy\samplers.py", line 206, in calc_cond_batch
return executor.execute(model, conds, x_in, timestep, model_options)
File "L:\AI\ComfyUI-aki-v1.1\comfy\patcher_extension.py", line 110, in execute
return self.original(*args, **kwargs)
File "L:\AI\ComfyUI-aki-v1.1\comfy\samplers.py", line 314, in _calc_cond_batch
c['control'] = control.get_control(input_x, timestep_, c, len(cond_or_uncond), transformer_options)
File "L:\AI\ComfyUI-aki-v1.1\comfy\controlnet.py", line 273, in get_control
control = self.control_model(x=x_noisy.to(dtype), hint=self.cond_hint, timesteps=timestep.to(dtype), context=context.to(dtype), **extra)
File "L:\AI\ComfyUI-aki-v1.1\python\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "L:\AI\ComfyUI-aki-v1.1\python\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "L:\AI\ComfyUI-aki-v1.1\comfy\cldm\cldm.py", line 416, in forward
assert y.shape[0] == x.shape[0]
AttributeError: 'NoneType' object has no attribute 'shape'

貌似是anything模型不能用sdxl的control net model ，导致上面错误。

工作流的具体名字叫啥

这个工作流我没有用过，他要求的模型是SDXL，instantid face analysis应该cuda。zluda还是走的cuda,rocm不支持580，

pytorch version: 最好更新到新版本，2.3.1+cuda118

our of memory只能说暴显存了，8+16G也小了点，你把系统虚拟内存加高一点试试。如果还暴就没有办法了，暴显存这是硬件条件不够。