Random crashing iMac M1 8GB about imaginairy HOT 5 CLOSED

Generating 🖼  2/2: "a pile of cans" 512x512px seed:990104098 prompt-strength:7.5 steps:15 sampler-type:k_dpmpp_2m
 40%|█████████████████████████████████████████▏                                                             | 6/15 [02:18<03:27, 23.09s/it]
Traceback (most recent call last):
  File "/Users/blendersushi/miniconda3/bin/imagine", line 8, in <module>
    sys.exit(imagine_cmd())
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/click/core.py", line 1130, in __call__
    return self.main(*args, **kwargs)
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/click/core.py", line 1055, in main
    rv = self.invoke(ctx)
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/click/core.py", line 1404, in invoke
    return ctx.invoke(self.callback, **ctx.params)
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/click/core.py", line 760, in invoke
    return __callback(*args, **kwargs)
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/click/decorators.py", line 26, in new_func
    return f(get_current_context(), *args, **kwargs)
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/imaginairy/cmds.py", line 238, in imagine_cmd
    imagine_image_files(
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/imaginairy/api.py", line 74, in imagine_image_files
    for result in imagine(
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/imaginairy/api.py", line 308, in imagine
    samples = sampler.sample(
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/imaginairy/samplers/kdiff.py", line 117, in sample
    samples = self.sampler_func(
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
    return func(*args, **kwargs)
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/imaginairy/vendored/k_diffusion/sampling.py", line 735, in sample_dpmpp_2m
    denoised = model(x, sigmas[i] * s_in, **extra_args)
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1190, in _call_impl
    return forward_call(*input, **kwargs)
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/imaginairy/samplers/base.py", line 102, in forward
    noise_pred = get_noise_prediction(
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/imaginairy/samplers/base.py", line 150, in get_noise_prediction
    noise_pred_neutral, noise_pred_positive = denoise_func(
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/imaginairy/samplers/base.py", line 85, in _wrapper
    return self.inner_model(
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1190, in _call_impl
    return forward_call(*input, **kwargs)
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/imaginairy/vendored/k_diffusion/external.py", line 130, in forward
    eps = self.get_eps(input * c_in, self.sigma_to_t(sigma), **kwargs)
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/imaginairy/vendored/k_diffusion/external.py", line 160, in get_eps
    return self.inner_model.apply_model(*args, **kwargs)
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/imaginairy/modules/diffusion/ddpm.py", line 764, in apply_model
    x_recon = self.model(x_noisy, t, **cond)
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1190, in _call_impl
    return forward_call(*input, **kwargs)
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/imaginairy/modules/diffusion/ddpm.py", line 889, in forward
    out = self.diffusion_model(x, t, context=cc)
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1190, in _call_impl
    return forward_call(*input, **kwargs)
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/imaginairy/modules/diffusion/openaimodel.py", line 778, in forward
    h = module(h, emb, context)
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1190, in _call_impl
    return forward_call(*input, **kwargs)
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/imaginairy/modules/diffusion/openaimodel.py", line 85, in forward
    x = layer(x, context)
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1190, in _call_impl
    return forward_call(*input, **kwargs)
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/imaginairy/modules/attention.py", line 331, in forward
    x = block(x, context=context)
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1190, in _call_impl
    return forward_call(*input, **kwargs)
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/imaginairy/modules/attention.py", line 277, in forward
    return checkpoint(
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/imaginairy/modules/diffusion/util.py", line 149, in checkpoint
    return CheckpointFunction.apply(func, len(inputs), *args)
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/imaginairy/modules/diffusion/util.py", line 162, in forward
    output_tensors = ctx.run_function(*ctx.input_tensors)
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/imaginairy/modules/attention.py", line 283, in _forward
    x = self.attn1(self.norm1(x)) + x
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1190, in _call_impl
    return forward_call(*input, **kwargs)
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/imaginairy/modules/attention.py", line 167, in forward
    return self.forward_splitmem(x, context=context, mask=mask)
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/imaginairy/modules/attention.py", line 204, in forward_splitmem
    q, k, v = map(
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/imaginairy/modules/attention.py", line 205, in <lambda>
    lambda t: rearrange(t, "b n (h d) -> (b h) n d", h=h), (q_in, k_in, v_in)
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/einops/einops.py", line 424, in rearrange
    return reduce(tensor, pattern, reduction='rearrange', **axes_lengths)
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/einops/einops.py", line 368, in reduce
    return recipe.apply(tensor)
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/einops/einops.py", line 211, in apply
    return backend.reshape(tensor, final_shapes)
  File "/Users/blendersushi/miniconda3/lib/python3.9/site-packages/einops/_backends.py", line 84, in reshape
    return x.reshape(shape)
RuntimeError: current_allocated_size() >= m_low_watermark_limit INTERNAL ASSERT FAILED at "/Users/runner/work/pytorch/pytorch/pytorch/aten/src/ATen/mps/MPSAllocator.mm":389, please report a bug to PyTorch.