No module named 'ComfyUI_StoryDiffusion.PuLID.flux.transformer_flux'

[greengerong]

How to solve this issue:

Prompt executed in 1.15 seconds
got prompt
!!! Exception during processing !!! No module named 'ComfyUI_StoryDiffusion.PuLID.flux.transformer_flux'
Traceback (most recent call last):
  File "/mnt/d/project/ComfyUI/execution.py", line 323, 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 "/mnt/d/project/ComfyUI/execution.py", line 198, 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 "/mnt/d/project/ComfyUI/execution.py", line 169, in _map_node_over_list
    process_inputs(input_dict, i)
  File "/mnt/d/project/ComfyUI/execution.py", line 158, in process_inputs
    results.append(getattr(obj, func)(**inputs))
  File "/mnt/d/project/ComfyUI/custom_nodes/ComfyUI_StoryDiffusion/Storydiffusion_node.py", line 1766, in story_model_loader
    from .PuLID.app_flux import FluxGenerator
  File "/mnt/d/project/ComfyUI/custom_nodes/ComfyUI_StoryDiffusion/PuLID/app_flux.py", line 7, in <module>
    from .flux.util import load_ae, load_clip, load_flow_model, load_t5, load_flow_model_quintized,SamplingOptions
  File "/mnt/d/project/ComfyUI/custom_nodes/ComfyUI_StoryDiffusion/PuLID/flux/util.py", line 5, in <module>
    from .transformer_flux import FluxTransformer2DModel

I had install new version diffusers : pip install git+https://github.com/huggingface/diffusers.git.

[smthemex]

Yes, this error was left over from my testing of NF4. You can delete that line of code or update to the latest plugin,

[sunyiwk]

你的repo_id文件是什么结构 能看一下么

[smthemex]

├──any_path/black-forest-labs/FLUX.1-dev | ├──model_index.json | ├──ae.safetensors | --- ├──vae | ├── config.json | ├── diffusion_pytorch_model.safetensors | --- ├──transformer | ├── config.json | ├──diffusion_pytorch_model-00001-of-00003.safetensors | ├──diffusion_pytorch_model-00002-of-00003.safetensors | ├──diffusion_pytorch_model-00003-of-00003.safetensors | ├── diffusion_pytorch_model.safetensors.index.json | --- ├──tokenizer | ├── special_tokens_map.json | ├── tokenizer_config.json | ├── vocab.json | ├── merges.txt | --- ├──tokenizer_2 | ├── special_tokens_map.json | ├── tokenizer_config.json | ├── spiece.model | ├── tokenizer.json | --- ├── text_encoder | ├── config.json | ├── model.safetensors | --- ├── text_encoder_2 | ├── config.json | ├── model-00001-of-00002.safetensors | ├── model-00002-of-00002.safetensors | ├── model.safetensors.index.json | --- ├── scheduler | ├── scheduler_config.json

[greengerong]

NF4.

thanks， this issue fixed。but it seem to 24G isn't enough, out of memory. Also tried the NF4 version.

[smthemex]

flux-pulid need more VRAM，but， nf4 maybe can try 10G or 8G...

[greengerong]

flux-pulid need more VRAM，but， nf4 maybe can try 10G or 8G...

NF4 also out of memory。 workflow ：

error：

[smthemex]

if using nf4，need fill nf4 in easy function，However, the PULID of NF4 can currently only generate noise, so it is not recommended to use it

[greengerong]

if using nf4，need fill nf4 in easy function，However, the PULID of NF4 can currently only generate noise, so it is not recommended to use it

thanks