MPS backend out of memory (MPS allocated: 16.91 GB, other allocations: 2.77 MB, max allowed: 18.13 GB). Tried to allocate 1.28 GB on private pool. Use PYTORCH_MPS_HIGH_WATERMARK_RATIO=0.0 to

### Expected Behavior

解决错误MPS backend out of memory (MPS allocated: 16.91 GB, other allocations: 2.77 MB, max allowed: 18.13 GB). Tried to allocate 1.28 GB on private pool. Use PYTORCH_MPS_HIGH_WATERMARK_RATIO=0.0 to disable upper limit for memory allocations (may cause system failure).

### Actual Behavior

MAC MINI M4运行comfyUI，使用sd3.5_large.safetensors模型文生图时出现错误

### Steps to Reproduce

[SD3.5L_example_workflow.json](https://github.com/user-attachments/files/19162719/SD3.5L_example_workflow.json)

### Debug Logs

```powershell
# ComfyUI Error Report
## Error Details
- **Node ID:** 294
- **Node Type:** KSampler
- **Exception Type:** RuntimeError
- **Exception Message:** MPS backend out of memory (MPS allocated: 16.91 GB, other allocations: 2.77 MB, max allowed: 18.13 GB). Tried to allocate 1.28 GB on private pool. Use PYTORCH_MPS_HIGH_WATERMARK_RATIO=0.0 to disable upper limit for memory allocations (may cause system failure).
## Stack Trace

File "/Applications/ComfyUI.app/Contents/Resources/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 "/Applications/ComfyUI.app/Contents/Resources/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 "/Applications/ComfyUI.app/Contents/Resources/ComfyUI/execution.py", line 174, in _map_node_over_list
process_inputs(input_dict, i)

File "/Applications/ComfyUI.app/Contents/Resources/ComfyUI/execution.py", line 163, in process_inputs
results.append(getattr(obj, func)(**inputs))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/Applications/ComfyUI.app/Contents/Resources/ComfyUI/nodes.py", line 1542, in sample
return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/Applications/ComfyUI.app/Contents/Resources/ComfyUI/nodes.py", line 1509, in common_ksampler
samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/Applications/ComfyUI.app/Contents/Resources/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 "/Applications/ComfyUI.app/Contents/Resources/ComfyUI/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 "/Applications/ComfyUI.app/Contents/Resources/ComfyUI/comfy/samplers.py", line 1023, in sample
return cfg_guider.sample(noise, latent_image, sampler, sigmas, denoise_mask, callback, disable_pbar, seed)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/Applications/ComfyUI.app/Contents/Resources/ComfyUI/comfy/samplers.py", line 1008, in sample
output = executor.execute(noise, latent_image, sampler, sigmas, denoise_mask, callback, disable_pbar, seed)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/Applications/ComfyUI.app/Contents/Resources/ComfyUI/comfy/patcher_extension.py", line 110, in execute
return self.original(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/Applications/ComfyUI.app/Contents/Resources/ComfyUI/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 "/Applications/ComfyUI.app/Contents/Resources/ComfyUI/comfy/samplers.py", line 959, in inner_sample
samples = executor.execute(self, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/Applications/ComfyUI.app/Contents/Resources/ComfyUI/comfy/patcher_extension.py", line 110, in execute
return self.original(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/Applications/ComfyUI.app/Contents/Resources/ComfyUI/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 "/Users/s1000rr/Documents/ComfyUI/.venv/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^

File "/Applications/ComfyUI.app/Contents/Resources/ComfyUI/comfy/k_diffusion/sampling.py", line 741, in sample_dpmpp_2m
denoised = model(x, sigmas[i] * s_in, **extra_args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/Applications/ComfyUI.app/Contents/Resources/ComfyUI/comfy/samplers.py", line 390, in __call__
out = self.inner_model(x, sigma, model_options=model_options, seed=seed)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/Applications/ComfyUI.app/Contents/Resources/ComfyUI/comfy/samplers.py", line 939, in __call__
return self.predict_noise(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/Applications/ComfyUI.app/Contents/Resources/ComfyUI/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 "/Applications/ComfyUI.app/Contents/Resources/ComfyUI/comfy/samplers.py", line 370, in sampling_function
out = calc_cond_batch(model, conds, x, timestep, model_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/Applications/ComfyUI.app/Contents/Resources/ComfyUI/comfy/samplers.py", line 206, in calc_cond_batch
return executor.execute(model, conds, x_in, timestep, model_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/Applications/ComfyUI.app/Contents/Resources/ComfyUI/comfy/patcher_extension.py", line 110, in execute
return self.original(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/Applications/ComfyUI.app/Contents/Resources/ComfyUI/comfy/samplers.py", line 319, in _calc_cond_batch
output = model.apply_model(input_x, timestep_, **c).chunk(batch_chunks)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/Applications/ComfyUI.app/Contents/Resources/ComfyUI/comfy/model_base.py", line 133, in apply_model
return comfy.patcher_extension.WrapperExecutor.new_class_executor(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/Applications/ComfyUI.app/Contents/Resources/ComfyUI/comfy/patcher_extension.py", line 110, in execute
return self.original(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/Applications/ComfyUI.app/Contents/Resources/ComfyUI/comfy/model_base.py", line 165, in _apply_model
model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, **extra_conds).float()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/Users/s1000rr/Documents/ComfyUI/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/Users/s1000rr/Documents/ComfyUI/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/Applications/ComfyUI.app/Contents/Resources/ComfyUI/comfy/ldm/modules/diffusionmodules/mmdit.py", line 1028, in forward
return super().forward(x, timesteps, context=context, y=y, control=control, transformer_options=transformer_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/Applications/ComfyUI.app/Contents/Resources/ComfyUI/comfy/ldm/modules/diffusionmodules/mmdit.py", line 1011, in forward
x = self.forward_core_with_concat(x, c, context, control, transformer_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/Applications/ComfyUI.app/Contents/Resources/ComfyUI/comfy/ldm/modules/diffusionmodules/mmdit.py", line 966, in forward_core_with_concat
context, x = self.joint_blocks[i](
^^^^^^^^^^^^^^^^^^^^^

File "/Users/s1000rr/Documents/ComfyUI/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/Users/s1000rr/Documents/ComfyUI/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/Applications/ComfyUI.app/Contents/Resources/ComfyUI/comfy/ldm/modules/diffusionmodules/mmdit.py", line 665, in forward
return block_mixing(
^^^^^^^^^^^^^

File "/Applications/ComfyUI.app/Contents/Resources/ComfyUI/comfy/ldm/modules/diffusionmodules/mmdit.py", line 604, in block_mixing
return _block_mixing(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/Applications/ComfyUI.app/Contents/Resources/ComfyUI/comfy/ldm/modules/diffusionmodules/mmdit.py", line 620, in _block_mixing
attn = optimized_attention(
^^^^^^^^^^^^^^^^^^^^

File "/Applications/ComfyUI.app/Contents/Resources/ComfyUI/comfy/ldm/modules/attention.py", line 204, in attention_sub_quad
hidden_states = efficient_dot_product_attention(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/Applications/ComfyUI.app/Contents/Resources/ComfyUI/comfy/ldm/modules/sub_quadratic_attention.py", line 268, in efficient_dot_product_attention
compute_query_chunk_attn(

File "/Applications/ComfyUI.app/Contents/Resources/ComfyUI/comfy/ldm/modules/sub_quadratic_attention.py", line 170, in _get_attention_scores_no_kv_chunking
attn_probs = attn_scores.softmax(dim=-1)
^^^^^^^^^^^^^^^^^^^^^^^^^^^

## System Information
- **ComfyUI Version:** 0.3.26
- **Arguments:** /Applications/ComfyUI.app/Contents/Resources/ComfyUI/main.py --user-directory /Users/s1000rr/Documents/ComfyUI/user --input-directory /Users/s1000rr/Documents/ComfyUI/input --output-directory /Users/s1000rr/Documents/ComfyUI/output --front-end-root /Applications/ComfyUI.app/Contents/Resources/ComfyUI/web_custom_versions/desktop_app --base-directory /Users/s1000rr/Documents/ComfyUI --extra-model-paths-config /Users/s1000rr/Library/Application Support/ComfyUI/extra_models_config.yaml --log-stdout --listen 127.0.0.1 --port 8000
- **OS:** posix
- **Python Version:** 3.12.9 (main, Feb 12 2025, 15:09:19) [Clang 19.1.6 ]
- **Embedded Python:** false
- **PyTorch Version:** 2.7.0.dev20250305
## Devices

- **Name:** mps
- **Type:** mps
- **VRAM Total:** 17179869184
- **VRAM Free:** 4003643392
- **Torch VRAM Total:** 17179869184
- **Torch VRAM Free:** 4003643392

## Logs

2025-03-10T20:32:39.027151 - Adding extra search path custom_nodes /Users/s1000rr/Documents/ComfyUI/custom_nodes
2025-03-10T20:32:39.027194 - Adding extra search path download_model_base /Users/s1000rr/Documents/ComfyUI/models
2025-03-10T20:32:39.027213 - Adding extra search path custom_nodes /Applications/ComfyUI.app/Contents/Resources/ComfyUI/custom_nodes
2025-03-10T20:32:39.027226 - Setting output directory to: /Users/s1000rr/Documents/ComfyUI/output
2025-03-10T20:32:39.027241 - Setting input directory to: /Users/s1000rr/Documents/ComfyUI/input
2025-03-10T20:32:39.027249 - Setting user directory to: /Users/s1000rr/Documents/ComfyUI/user
2025-03-10T20:32:39.247684 - [START] Security scan2025-03-10T20:32:39.247699 -
2025-03-10T20:32:39.490142 - [DONE] Security scan2025-03-10T20:32:39.490173 -
2025-03-10T20:32:39.532177 - ## ComfyUI-Manager: installing dependencies done.2025-03-10T20:32:39.532212 -
2025-03-10T20:32:39.532231 - ** ComfyUI startup time:2025-03-10T20:32:39.532241 - 2025-03-10T20:32:39.532250 - 2025-03-10 20:32:39.5322025-03-10T20:32:39.532257 -
2025-03-10T20:32:39.532271 - ** Platform:2025-03-10T20:32:39.532279 - 2025-03-10T20:32:39.532286 - Darwin2025-03-10T20:32:39.532293 -
2025-03-10T20:32:39.532300 - ** Python version:2025-03-10T20:32:39.532307 - 2025-03-10T20:32:39.532314 - 3.12.9 (main, Feb 12 2025, 15:09:19) [Clang 19.1.6 ]2025-03-10T20:32:39.532324 -
2025-03-10T20:32:39.532331 - ** Python executable:2025-03-10T20:32:39.532338 - 2025-03-10T20:32:39.532345 - /Users/s1000rr/Documents/ComfyUI/.venv/bin/python2025-03-10T20:32:39.532351 -
2025-03-10T20:32:39.532358 - ** ComfyUI Path:2025-03-10T20:32:39.532365 - 2025-03-10T20:32:39.532371 - /Applications/ComfyUI.app/Contents/Resources/ComfyUI2025-03-10T20:32:39.532377 -
2025-03-10T20:32:39.532384 - ** ComfyUI Base Folder Path:2025-03-10T20:32:39.532390 - 2025-03-10T20:32:39.532397 - /Applications/ComfyUI.app/Contents/Resources/ComfyUI2025-03-10T20:32:39.532403 -
2025-03-10T20:32:39.532410 - ** User directory:2025-03-10T20:32:39.532416 - 2025-03-10T20:32:39.532422 - /Users/s1000rr/Documents/ComfyUI/user2025-03-10T20:32:39.532429 -
2025-03-10T20:32:39.532435 - ** ComfyUI-Manager config path:2025-03-10T20:32:39.532441 - 2025-03-10T20:32:39.532448 - /Users/s1000rr/Documents/ComfyUI/user/default/ComfyUI-Manager/config.ini2025-03-10T20:32:39.532454 -
2025-03-10T20:32:39.532462 - ** Log path:2025-03-10T20:32:39.532468 - 2025-03-10T20:32:39.532474 - /Users/s1000rr/Documents/ComfyUI/user/comfyui.log2025-03-10T20:32:39.532480 -
2025-03-10T20:32:39.749761 - [ComfyUI-Manager] Failed to restore comfyui-frontend-package
2025-03-10T20:32:39.749878 - expected str, bytes or os.PathLike object, not NoneType
2025-03-10T20:32:39.750001 -
Prestartup times for custom nodes:
2025-03-10T20:32:39.750036 - 0.7 seconds: /Applications/ComfyUI.app/Contents/Resources/ComfyUI/custom_nodes/ComfyUI-Manager
2025-03-10T20:32:39.750056 -
2025-03-10T20:32:40.456755 - Checkpoint files will always be loaded safely.
2025-03-10T20:32:40.474320 - Total VRAM 16384 MB, total RAM 16384 MB
2025-03-10T20:32:40.474387 - pytorch version: 2.7.0.dev20250305
2025-03-10T20:32:40.474466 - Set vram state to: SHARED
2025-03-10T20:32:40.474492 - Device: mps
2025-03-10T20:32:41.116188 - Using sub quadratic optimization for attention, if you have memory or speed issues try using: --use-split-cross-attention
2025-03-10T20:32:41.859570 - ComfyUI version: 0.3.26
2025-03-10T20:32:41.859641 - ComfyUI frontend version: 1...1.0...1.8
2025-03-10T20:32:41.861533 - [Prompt Server] web root: /Applications/ComfyUI.app/Contents/Resources/ComfyUI/web_custom_versions/desktop_app
2025-03-10T20:32:42.072658 - ### Loading: ComfyUI-Manager (V3.30.3)
2025-03-10T20:32:42.072896 - [ComfyUI-Manager] network_mode: public
2025-03-10T20:32:42.081658 - ### ComfyUI Revision: UNKNOWN (The currently installed ComfyUI is not a Git repository)
2025-03-10T20:32:42.083067 -
Import times for custom nodes:
2025-03-10T20:32:42.083114 - 0.0 seconds: /Applications/ComfyUI.app/Contents/Resources/ComfyUI/custom_nodes/websocket_image_save.py
2025-03-10T20:32:42.083138 - 0.0 seconds: /Applications/ComfyUI.app/Contents/Resources/ComfyUI/custom_nodes/ComfyUI-Manager
2025-03-10T20:32:42.083158 -
2025-03-10T20:32:42.086302 - Starting server

2025-03-10T20:32:42.086678 - To see the GUI go to: http://127.0.0.1:8000
2025-03-10T20:32:42.562554 - [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json
2025-03-10T20:32:42.748326 - [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json
2025-03-10T20:32:42.957093 - [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json
2025-03-10T20:32:42.971482 - [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json
2025-03-10T20:32:43.783009 - [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json
2025-03-10T20:32:51.160245 - FETCH ComfyRegistry Data: 5/572025-03-10T20:32:51.160359 -
2025-03-10T20:32:59.303817 - FETCH ComfyRegistry Data: 10/572025-03-10T20:32:59.303866 -
2025-03-10T20:33:07.048909 - FETCH ComfyRegistry Data: 15/572025-03-10T20:33:07.049030 -
2025-03-10T20:33:11.474448 - got prompt
2025-03-10T20:33:11.583825 - model weight dtype torch.float16, manual cast: None
2025-03-10T20:33:11.584919 - model_type FLOW
2025-03-10T20:33:17.259475 - FETCH ComfyRegistry Data: 20/572025-03-10T20:33:17.259516 -
2025-03-10T20:33:42.971142 - FETCH ComfyRegistry Data: 25/572025-03-10T20:33:42.972165 -
2025-03-10T20:34:05.914111 - Using split attention in VAE
2025-03-10T20:34:06.053760 - Using split attention in VAE
2025-03-10T20:34:07.146018 - VAE load device: mps, offload device: cpu, dtype: torch.bfloat16
2025-03-10T20:34:07.226995 - no CLIP/text encoder weights in checkpoint, the text encoder model will not be loaded.
2025-03-10T20:34:07.257884 - loaded diffusion model directly to GPU
2025-03-10T20:34:07.261221 - Requested to load SD3
2025-03-10T20:34:07.267090 - 0 models unloaded.
2025-03-10T20:34:07.287803 - loaded completely 9.5367431640625e+25 15366.797485351562 True
2025-03-10T20:34:09.505333 - Requested to load SD3ClipModel_
2025-03-10T20:34:09.513476 - loaded completely 9.5367431640625e+25 10644.189453125 True
2025-03-10T20:34:09.515587 - CLIP/text encoder model load device: cpu, offload device: cpu, current: cpu, dtype: torch.float16
2025-03-10T20:34:10.472372 - FETCH ComfyRegistry Data: 30/572025-03-10T20:34:10.472396 -
2025-03-10T20:34:12.851766 - clip missing: ['text_projection.weight']
2025-03-10T20:34:17.372031 - FETCH ComfyRegistry Data: 35/572025-03-10T20:34:17.372099 -
2025-03-10T20:34:26.811843 - FETCH ComfyRegistry Data: 40/572025-03-10T20:34:26.811903 -
2025-03-10T20:34:33.783606 - FETCH ComfyRegistry Data: 45/572025-03-10T20:34:33.783706 -
2025-03-10T20:34:42.024288 - FETCH ComfyRegistry Data: 50/572025-03-10T20:34:42.024346 -
2025-03-10T20:34:48.484404 - FETCH ComfyRegistry Data: 55/572025-03-10T20:34:48.484487 -
2025-03-10T20:34:51.497742 - FETCH ComfyRegistry Data [DONE]2025-03-10T20:34:51.497839 -
2025-03-10T20:34:51.549668 - [ComfyUI-Manager] default cache updated: https://api.comfy.org/nodes
2025-03-10T20:34:52.912282 - nightly_channel:
https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/remote
2025-03-10T20:34:52.912968 - FETCH DATA from: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json2025-03-10T20:34:52.912986 - 2025-03-10T20:35:15.869267 - Token indices sequence length is longer than the specified maximum sequence length for this model (150 > 77). Running this sequence through the model will result in indexing errors
2025-03-10T20:35:15.875030 - Token indices sequence length is longer than the specified maximum sequence length for this model (150 > 77). Running this sequence through the model will result in indexing errors
2025-03-10T20:35:18.587879 - [DONE]2025-03-10T20:35:18.587917 -
2025-03-10T20:35:18.611460 - [ComfyUI-Manager] All startup tasks have been completed.
2025-03-10T20:35:19.622934 - Requested to load SD3
2025-03-10T20:35:19.754687 -
0%| | 0/40 [00:00