Crash in XY Plot when processing Flux mode

[wei-crypto]

escription:
The program crashes during AutoencodingEngine loading when using XY Plot to process multiple Flux LoRA files. The crash occurs during data type conversion from float8_e4m3fn to bfloat16.
Environment:
Python 3.10.11
PyTorch 2.4.1+cu124
CUDA 12.4
GPU: RTX 4060 Ti
ComfyUI version: aki-v1.4
Issue Details:

1. Loading and using Flux LoRA files individually works fine
   Crashes when using XY Plot for batch processing
   Crash occurs when loading the first LoRA file
   Issue appears with both advanced xyPlot and advPlot images nodes
   Error Log:
   Starting server
   To see the GUI go to: http://127.0.0.1:8188
   G:\comfyui\ComfyUI-aki-v1.4\ComfyUI-aki-v1.4\custom_nodes\comfyui-mixlab-nodes\webApp\lib/photoswipe-lightbox.esm.min.js
   FETCH DATA from: G:\comfyui\ComfyUI-aki-v1.4\ComfyUI-aki-v1.4\custom_nodes\ComfyUI-Manager\extension-node-map.json [DONE]
   G:\comfyui\ComfyUI-aki-v1.4\ComfyUI-aki-v1.4\custom_nodes\comfyui-mixlab-nodes\webApp\lib/photoswipe.min.css
   G:\comfyui\ComfyUI-aki-v1.4\ComfyUI-aki-v1.4\custom_nodes\comfyui-mixlab-nodes\webApp\lib/pickr.min.js
   G:\comfyui\ComfyUI-aki-v1.4\ComfyUI-aki-v1.4\custom_nodes\comfyui-mixlab-nodes\webApp\lib/classic.min.css
   G:\comfyui\ComfyUI-aki-v1.4\ComfyUI-aki-v1.4\custom_nodes\comfyui-mixlab-nodes\webApp\lib/model-viewer.min.js
   G:\comfyui\ComfyUI-aki-v1.4\ComfyUI-aki-v1.4\custom_nodes\comfyui-mixlab-nodes\webApp\lib/juxtapose.min.js
   G:\comfyui\ComfyUI-aki-v1.4\ComfyUI-aki-v1.4\custom_nodes\comfyui-mixlab-nodes\webApp\lib/juxtapose.css
   QualityOfLifeSuit_Omar92::NSP ready
   ['flux1-canny-dev-lora.safetensors', 'flux1-depth-dev-lora.safetensors']
   ['flux1-canny-dev-lora.safetensors', 'flux1-depth-dev-lora.safetensors']
   got prompt
   Using xformers attention in VAE
   Using xformers attention in VAE
   Requested to load FluxClipModel_
   Loading 1 new model
   loaded completely 0.0 4777.53759765625 True
   clip missing: ['text_projection.weight']
   G:\comfyui\ComfyUI-aki-v1.4\ComfyUI-aki-v1.4\comfy\ldm\modules\attention.py:407: UserWarning: 1Torch was not compiled with flash attention. (Triggered internally at C:\actions-runner\work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\transformers\cuda\sdp_utils.cpp:555.)
   out = torch.nn.functional.scaled_dot_product_attention(q, k, v, attn_mask=mask, dropout_p=0.0, is_causal=False)
   (URLError(gaierror(11004, 'getaddrinfo failed')),)
   model weight dtype torch.float8_e4m3fn, manual cast: torch.bfloat16
   model_type FLUX
   Requested to load Flux
   Loading 1 new model
   loaded completely 0.0 11350.048889160156 True
   Requested to load AutoencodingEngine
   Stack Trace:
   Windows fatal exception: access violation
   Stack (most recent call first):
   File "G:\comfyui\ComfyUI-aki-v1.4\ComfyUI-aki-v1.4\python\lib\site-packages\torch\storage.py", line 354 in getitem
   File "G:\comfyui\ComfyUI-aki-v1.4\ComfyUI-aki-v1.4\python\lib\site-packages\safetensors\torch.py", line 315 in load_file
   File "G:\comfyui\ComfyUI-aki-v1.4\ComfyUI-aki-v1.4\comfy\utils.py", line 34 in load_torch_file
   File "G:\comfyui\ComfyUI-aki-v1.4\ComfyUI-aki-v1.4\comfy\sd.py", line 694 in load_diffusion_model
   File "G:\comfyui\ComfyUI-aki-v1.4\ComfyUI-aki-v1.4\nodes.py", line 882 in load_unet
   File "G:\comfyui\ComfyUI-aki-v1.4\ComfyUI-aki-v1.4\custom_nodes\ComfyUI_tinyterraNodes\ttNpy\ttNexecutor.py", line 209 in map_node_over_list
   Attempted Solutions:
   Tried different versions of ComfyUI_tinyterraNodes (including the latest)
2. Tested different Plot nodes
   Verified model file integrity
   Expected Behavior:
   XY Plot should be able to process multiple Flux LoRA files without crashing.

[TinyTerra]

Do you have a sample workflow i can use to test this against?