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
53.49k stars 5.66k forks source link

Out of memory when using ControlNet on memory-constrained hardware in GPU mode #957

Open eduard-sukharev opened 1 year ago

eduard-sukharev commented 1 year ago

I'm using pretty much lowend laptop to generate images using ComfyUI, with MX150 and 2Gb Vram (split out of 16Gb RAM).

When using straightforward workflow with text2img + upscaler it runs fine in GPU mode. However, when I add a Load ControlNet + Apply ControlNet nodes, the KSampler node yields following error:

Error occurred when executing KSampler:

Allocation on device 0 would exceed allowed memory. (out of memory)
Currently allocated     : 1.70 GiB
Requested               : 10.00 MiB
Device limit            : 2.00 GiB
Free (according to CUDA): 0 bytes
PyTorch limit (set by user-supplied memory fraction)
                        : 17179869184.00 GiB

  File "E:\ComfyUI_windows_portable\ComfyUI\execution.py", line 145, in recursive_execute
    output_data, output_ui = get_output_data(obj, input_data_all)
  File "E:\ComfyUI_windows_portable\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 "E:\ComfyUI_windows_portable\ComfyUI\execution.py", line 68, in map_node_over_list
    results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
  File "E:\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1082, in sample
    return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise)
  File "E:\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1052, in common_ksampler
    samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
  File "E:\ComfyUI_windows_portable\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 "E:\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 671, in sample
    samples = getattr(k_diffusion_sampling, "sample_{}".format(self.sampler))(self.model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar)
  File "E:\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "E:\ComfyUI_windows_portable\ComfyUI\comfy\k_diffusion\sampling.py", line 138, in sample_euler
    denoised = model(x, sigma_hat * s_in, **extra_args)
  File "E:\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "E:\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 308, in forward
    out = self.inner_model(x, sigma, cond=cond, uncond=uncond, cond_scale=cond_scale, cond_concat=cond_concat, model_options=model_options, seed=seed)
  File "E:\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "E:\ComfyUI_windows_portable\ComfyUI\comfy\k_diffusion\external.py", line 125, in forward
    eps = self.get_eps(input * c_in, self.sigma_to_t(sigma), **kwargs)
  File "E:\ComfyUI_windows_portable\ComfyUI\comfy\k_diffusion\external.py", line 151, in get_eps
    return self.inner_model.apply_model(*args, **kwargs)
  File "E:\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 296, in apply_model
    out = sampling_function(self.inner_model.apply_model, x, timestep, uncond, cond, cond_scale, cond_concat, model_options=model_options, seed=seed)
  File "E:\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 274, in sampling_function
    cond, uncond = calc_cond_uncond_batch(model_function, cond, uncond, x, timestep, max_total_area, cond_concat, model_options)
  File "E:\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 232, in calc_cond_uncond_batch
    c['control'] = control.get_control(input_x, timestep_, c, len(cond_or_uncond))
  File "E:\ComfyUI_windows_portable\ComfyUI\comfy\sd.py", line 706, in get_control
    control = self.control_model(x=x_noisy, hint=self.cond_hint, timesteps=t, context=context, y=y)
  File "E:\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "E:\ComfyUI_windows_portable\ComfyUI\comfy\cldm\cldm.py", line 311, in forward
    h = module(h, emb, context)
  File "E:\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "E:\ComfyUI_windows_portable\ComfyUI\comfy\ldm\modules\diffusionmodules\openaimodel.py", line 82, in forward
    x = layer(x, emb)
  File "E:\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "E:\ComfyUI_windows_portable\ComfyUI\comfy\ldm\modules\diffusionmodules\openaimodel.py", line 271, in forward
    return checkpoint(
  File "E:\ComfyUI_windows_portable\ComfyUI\comfy\ldm\modules\diffusionmodules\util.py", line 123, in checkpoint
    return func(*inputs)
  File "E:\ComfyUI_windows_portable\ComfyUI\comfy\ldm\modules\diffusionmodules\openaimodel.py", line 295, in _forward
    h = self.out_layers(h)
  File "E:\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "E:\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\nn\modules\container.py", line 217, in forward
    input = module(input)
  File "E:\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "E:\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\nn\modules\activation.py", line 396, in forward
    return F.silu(input, inplace=self.inplace)
  File "E:\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\nn\functional.py", line 2059, in silu
    return torch._C._nn.silu(input)

Running in CPU mode works, albeit obviously very slow.

Both working and erroring workflows are attached: workflows.zip

sraliu commented 12 months ago

same error ~ (13400+64GB+4090)

Error occurred when executing KSamplerAdvanced:

Allocation on device 0 would exceed allowed memory. (out of memory) Currently allocated : 38.94 GiB Requested : 11.10 GiB Device limit : 23.99 GiB Free (according to CUDA): 0 bytes PyTorch limit (set by user-supplied memory fraction) : 17179869184.00 GiB