XPU out of memory Error after LoadImage and KSampler

[cedico]

Hi,
I'm using ComfYUI with Intl A770, and when I load the default Workflow all works fine I can generate a new image.
But if I replace the "Empty latent image" node by these 3 nodes : LoadImage--PadImageForInpainting--VAEencode (OR same thing with: LoadImage--VAEencode), I obtain the Error:
KSampler : XPU out of memory. Tried to allocate 128.00 GiB. GPU 0 has a total capacity of 15.56 GiB. Of the allocated memory 2.50 GiB is allocated by PyTorch, and 39.26 MiB is reserved by PyTorch but unallocated. Please use empty_cache to release all unoccupied cached memory.

Why 128GiB, is there any bug ? am I missing something ?

Error :
Requested to load AutoencoderKL
loaded completely 6372.3515625 159.55708122253418 True
scaled_dot_product_attention OOMed: switched to slice attention
out of memory error, increasing steps and trying again 4
Requested to load SD1ClipModel
loaded completely 14346.98505859375 235.84423828125 True
Requested to load BaseModel
loaded completely 13612.11984375 1639.4336013793945 True
0%| | 0/20 [00:00<?, ?it/s]
!!! Exception during processing !!! XPU out of memory. Tried to allocate 128.00 GiB. GPU 0 has a total capacity of 15.56 GiB. Of the allocated memory 2.90 GiB is allocated by PyTorch, and 47.65 MiB is reserved by PyTorch but unallocated. Please use empty_cache to release all unoccupied cached memory.
Traceback (most recent call last):
File "F:\AI\VideoComfy\ComfyUI\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 "F:\AI\VideoComfy\ComfyUI\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 "F:\AI\VideoComfy\ComfyUI\execution.py", line 174, in _map_node_over_list
process_inputs(input_dict, i)
File "F:\AI\VideoComfy\ComfyUI\execution.py", line 163, in process_inputs
results.append(getattr(obj, func)(**inputs))
File "F:\AI\VideoComfy\ComfyUI\nodes.py", line 1540, in sample
return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise)
File "F:\AI\VideoComfy\ComfyUI\nodes.py", line 1507, in common_ksampler
samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
File "F:\AI\VideoComfy\ComfyUI\custom_nodes\comfyui-impact-pack\modules\impact\sample_error_enhancer.py", line 22, in informative_sample
raise e
File "F:\AI\VideoComfy\ComfyUI\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 "F:\AI\VideoComfy\ComfyUI\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 "F:\AI\VideoComfy\ComfyUI\comfy\samplers.py", line 1110, 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 "F:\AI\VideoComfy\ComfyUI\comfy\samplers.py", line 1000, in sample
return cfg_guider.sample(noise, latent_image, sampler, sigmas, denoise_mask, callback, disable_pbar, seed)
File "F:\AI\VideoComfy\ComfyUI\comfy\samplers.py", line 985, in sample
output = executor.execute(noise, latent_image, sampler, sigmas, denoise_mask, callback, disable_pbar, seed)
File "F:\AI\VideoComfy\ComfyUI\comfy\patcher_extension.py", line 110, in execute
return self.original(*args, **kwargs)
File "F:\AI\VideoComfy\ComfyUI\comfy\samplers.py", line 953, in outer_sample
output = self.inner_sample(noise, latent_image, device, sampler, sigmas, denoise_mask, callback, disable_pbar, seed)
File "F:\AI\VideoComfy\ComfyUI\comfy\samplers.py", line 936, in inner_sample
samples = executor.execute(self, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar)
File "F:\AI\VideoComfy\ComfyUI\comfy\patcher_extension.py", line 110, in execute
return self.original(*args, **kwargs)
File "F:\AI\VideoComfy\ComfyUI\comfy\samplers.py", line 715, in sample
samples = self.sampler_function(model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar, **self.extra_options)
File "C:\Python310\lib\site-packages\torch\utils_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
File "F:\AI\VideoComfy\ComfyUI\comfy\k_diffusion\sampling.py", line 161, in sample_euler
denoised = model(x, sigma_hat * s_in, **extra_args)
File "F:\AI\VideoComfy\ComfyUI\comfy\samplers.py", line 379, in call
out = self.inner_model(x, sigma, model_options=model_options, seed=seed)
File "F:\AI\VideoComfy\ComfyUI\comfy\samplers.py", line 916, in call
return self.predict_noise(*args, **kwargs)
File "F:\AI\VideoComfy\ComfyUI\comfy\samplers.py", line 919, 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 "F:\AI\VideoComfy\ComfyUI\comfy\samplers.py", line 359, in sampling_function
out = calc_cond_batch(model, conds, x, timestep, model_options)
File "F:\AI\VideoComfy\ComfyUI\comfy\samplers.py", line 195, in calc_cond_batch
return executor.execute(model, conds, x_in, timestep, model_options)
File "F:\AI\VideoComfy\ComfyUI\comfy\patcher_extension.py", line 110, in execute
return self.original(*args, **kwargs)
File "F:\AI\VideoComfy\ComfyUI\comfy\samplers.py", line 308, in calc_cond_batch
output = model.apply_model(input_x, timestep, **c).chunk(batch_chunks)
File "F:\AI\VideoComfy\ComfyUI\comfy\model_base.py", line 132, in apply_model
return comfy.patcher_extension.WrapperExecutor.new_class_executor(
File "F:\AI\VideoComfy\ComfyUI\comfy\patcher_extension.py", line 110, in execute
return self.original(*args, **kwargs)
File "F:\AI\VideoComfy\ComfyUI\comfy\model_base.py", line 163, in _apply_model
model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, **extra_conds).float()
File "C:\Python310\lib\site-packages\torch\nn\modules\module.py", line 1751, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "C:\Python310\lib\site-packages\torch\nn\modules\module.py", line 1762, in _call_impl
return forward_call(*args, **kwargs)
File "F:\AI\VideoComfy\ComfyUI\comfy\ldm\modules\diffusionmodules\openaimodel.py", line 831, in forward
return comfy.patcher_extension.WrapperExecutor.new_class_executor(
File "F:\AI\VideoComfy\ComfyUI\comfy\patcher_extension.py", line 110, in execute
return self.original(*args, **kwargs)
File "F:\AI\VideoComfy\ComfyUI\comfy\ldm\modules\diffusionmodules\openaimodel.py", line 873, in _forward
h = forward_timestep_embed(module, h, emb, context, transformer_options, time_context=time_context, num_video_frames=num_video_frames, image_only_indicator=image_only_indicator)
File "F:\AI\VideoComfy\ComfyUI\comfy\ldm\modules\diffusionmodules\openaimodel.py", line 44, in forward_timestep_embed
x = layer(x, context, transformer_options)
File "C:\Python310\lib\site-packages\torch\nn\modules\module.py", line 1751, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "C:\Python310\lib\site-packages\torch\nn\modules\module.py", line 1762, in _call_impl
return forward_call(*args, **kwargs)
File "F:\AI\VideoComfy\ComfyUI\comfy\ldm\modules\attention.py", line 796, in forward
x = block(x, context=context[i], transformer_options=transformer_options)
File "C:\Python310\lib\site-packages\torch\nn\modules\module.py", line 1751, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "C:\Python310\lib\site-packages\torch\nn\modules\module.py", line 1762, in _call_impl
return forward_call(*args, **kwargs)
File "F:\AI\VideoComfy\ComfyUI\comfy\ldm\modules\attention.py", line 683, in forward
n = self.attn1(n, context=context_attn1, value=value_attn1)
File "C:\Python310\lib\site-packages\torch\nn\modules\module.py", line 1751, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "C:\Python310\lib\site-packages\torch\nn\modules\module.py", line 1762, in _call_impl
return forward_call(*args, **kwargs)
File "F:\AI\VideoComfy\ComfyUI\comfy\ldm\modules\attention.py", line 577, in forward
out = optimized_attention(q, k, v, self.heads, attn_precision=self.attn_precision)
File "F:\AI\VideoComfy\ComfyUI\comfy\ldm\modules\attention.py", line 455, in attention_pytorch
out = torch.nn.functional.scaled_dot_product_attention(q, k, v, attn_mask=mask, dropout_p=0.0, is_causal=False)
torch.OutOfMemoryError: XPU out of memory. Tried to allocate 128.00 GiB. GPU 0 has a total capacity of 15.56 GiB. Of the allocated memory 2.90 GiB is allocated by PyTorch, and 47.65 MiB is reserved by PyTorch but unallocated. Please use empty_cache to release all unoccupied cached memory.

Got an OOM, unloading all loaded models.
Prompt executed in 6.09 seconds

[cedico]

I've followed this tutorial and all works fine until 6'00" :
Outpainting

but at 6'00'', when I replace VAEdecode+SaveImage by LoadImage+PadImageForInpainting+VAEencode, I obtain that big error...

Any idea ?