cannot load flux model anymore

### Expected Behavior

i can load flux model yesterday, but i don't know why there the error occur today.

### Actual Behavior

please check the coding

### Steps to Reproduce

it's not about the workflow, only happened in flux models.

### Debug Logs

```powershell
D:\ComfyUI_windows_portable>.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build
[START] Security scan
[DONE] Security scan
## ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2024-08-17 00:27:15.749790
** Platform: Windows
** Python version: 3.11.9 (tags/v3.11.9:de54cf5, Apr 2 2024, 10:12:12) [MSC v.1938 64 bit (AMD64)]
** Python executable: D:\ComfyUI_windows_portable\python_embeded\python.exe
** Log path: D:\ComfyUI_windows_portable\comfyui.log

Prestartup times for custom nodes:
0.5 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Manager

Total VRAM 24564 MB, total RAM 32606 MB
pytorch version: 2.3.1+cu121
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 4090 : cudaMallocAsync
Using pytorch cross attention
[Prompt Server] web root: D:\ComfyUI_windows_portable\ComfyUI\web
### Loading: ComfyUI-Manager (V2.38.1)
### ComfyUI Revision: 2532 [39fb74c5] *DETACHED | Released on '2024-08-13'
------------------------------------------
Comfyroll Studio v1.76 : 175 Nodes Loaded
------------------------------------------
** For changes, please see patch notes at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/blob/main/Patch_Notes.md
** For help, please see the wiki at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/wiki
------------------------------------------

Import times for custom nodes:
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\websocket_image_save.py
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\AIGODLIKE-COMFYUI-TRANSLATION
0.2 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_Comfyroll_CustomNodes
0.2 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Manager

Starting server

To see the GUI go to: http://127.0.0.1:8188
Exception in thread Thread-5 ():
Traceback (most recent call last):
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\aiohttp\connector.py", line 1137, in _start_tls_connection
tls_transport = await self._loop.start_tls(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "asyncio\base_events.py", line 1268, in start_tls
File "asyncio\sslproto.py", line 578, in _on_handshake_complete
ConnectionResetError

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "threading.py", line 1045, in _bootstrap_inner
File "threading.py", line 982, in run
File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Manager\glob\manager_server.py", line 1679, in
threading.Thread(target=lambda: asyncio.run(default_cache_update())).start()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "asyncio\runners.py", line 190, in run
File "asyncio\runners.py", line 118, in run
File "asyncio\base_events.py", line 654, in run_until_complete
File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Manager\glob\manager_server.py", line 1676, in default_cache_update
await asyncio.gather(a, b, c, d, e)
File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Manager\glob\manager_server.py", line 1663, in get_cache
json_obj = await core.get_data(uri, True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Manager\glob\manager_core.py", line 583, in get_data
async with session.get(uri) as resp:
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\aiohttp\client.py", line 1197, in __aenter__
self._resp = await self._coro
^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\aiohttp\client.py", line 581, in _request
conn = await self._connector.connect(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\aiohttp\connector.py", line 544, in connect
proto = await self._create_connection(req, traces, timeout)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\aiohttp\connector.py", line 942, in _create_connection
_, proto = await self._create_proxy_connection(req, traces, timeout)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\aiohttp\connector.py", line 1379, in _create_proxy_connection
return await self._start_tls_connection(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\aiohttp\connector.py", line 1157, in _start_tls_connection
raise client_error(req.connection_key, exc) from exc
aiohttp.client_exceptions.ClientConnectorError: Cannot connect to host raw.githubusercontent.com:443 ssl:default [None]
FETCH DATA from: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Manager\extension-node-map.json [DONE]
got prompt
model weight dtype torch.float8_e4m3fn, manual cast: torch.bfloat16
model_type FLUX
Using pytorch attention in VAE
Using pytorch attention in VAE
!!! Exception during processing!!! Allocation on device
Traceback (most recent call last):
File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 152, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 82, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 75, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\nodes.py", line 518, in load_checkpoint
out = comfy.sd.load_checkpoint_guess_config(ckpt_path, output_vae=True, output_clip=True, embedding_directory=folder_paths.get_folder_paths("embeddings"))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\sd.py", line 511, in load_checkpoint_guess_config
out = load_state_dict_guess_config(sd, output_vae, output_clip, output_clipvision, embedding_directory, output_model, model_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\sd.py", line 566, in load_state_dict_guess_config
clip = CLIP(clip_target, embedding_directory=embedding_directory, tokenizer_data=clip_sd, parameters=parameters)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\sd.py", line 77, in __init__
self.cond_stage_model = clip(**(params))
^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\text_encoders\flux.py", line 70, in __init__
super().__init__(dtype_t5=dtype_t5, device=device, dtype=dtype)
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\text_encoders\flux.py", line 42, in __init__
self.t5xxl = T5XXLModel(device=device, dtype=dtype_t5)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\text_encoders\flux.py", line 11, in __init__
super().__init__(device=device, layer=layer, layer_idx=layer_idx, textmodel_json_config=textmodel_json_config, dtype=dtype, special_tokens={"end": 1, "pad": 0}, model_class=comfy.text_encoders.t5.T5)
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\sd1_clip.py", line 98, in __init__
self.transformer = model_class(config, dtype, device, self.operations)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\text_encoders\t5.py", line 227, in __init__
self.encoder = T5Stack(self.num_layers, model_dim, model_dim, config_dict["d_ff"], config_dict["dense_act_fn"], config_dict["is_gated_act"], config_dict["num_heads"], config_dict["model_type"] != "umt5", dtype, device, operations)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\text_encoders\t5.py", line 198, in __init__
[T5Block(model_dim, inner_dim, ff_dim, ff_activation, gated_act, num_heads, relative_attention_bias=((not relative_attention) or (i == 0)), dtype=dtype, device=device, operations=operations) for i in range(num_layers)]
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\text_encoders\t5.py", line 198, in
[T5Block(model_dim, inner_dim, ff_dim, ff_activation, gated_act, num_heads, relative_attention_bias=((not relative_attention) or (i == 0)), dtype=dtype, device=device, operations=operations) for i in range(num_layers)]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\text_encoders\t5.py", line 186, in __init__
self.layer.append(T5LayerFF(model_dim, ff_dim, ff_activation, gated_act, dtype, device, operations))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\text_encoders\t5.py", line 57, in __init__
self.DenseReluDense = T5DenseGatedActDense(model_dim, ff_dim, ff_activation, dtype, device, operations)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\text_encoders\t5.py", line 39, in __init__
self.wi_0 = operations.Linear(model_dim, ff_dim, bias=False, dtype=dtype, device=device)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\linear.py", line 98, in __init__
self.weight = Parameter(torch.empty((out_features, in_features), **factory_kwargs))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
torch.cuda.OutOfMemoryError: Allocation on device

Got an OOM, unloading all loaded models.
Prompt executed in 4.54 seconds
```

### Other

_No response_