text_encoder_2

[lior007]

OSError: Error no file named pytorch_model.bin, model.safetensors, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory D:/ComfyUI_windows_portable_nvidia/ComfyUI_windows_portable/ComfyUI/black-forest-labs/FLUX.1-dev/text_encoder_2.

i have this files:

| ├── config.json | ├── model-00001-of-00002.safetensors | ├── model-00002-of-00002.safetensors | ├── model.safetensors.index.json

what to do?

[smthemex]

using flux dev repo need all the files below: and make sure your repo path like D:/ComfyUI_windows_portable_nvidia/ComfyUI_windows_portable/ComfyUI/black-forest-labs/FLUX.1-dev or show me your comfyUI console error.

[lior007]

using flux dev repo need all the files below: and make sure your repo path like D:/ComfyUI_windows_portable_nvidia/ComfyUI_windows_portable/ComfyUI/black-forest-labs/FLUX.1-dev or show me your comfyUI console error.

thank you this is my repo D:/ComfyUI_windows_portable_nvidia/ComfyUI_windows_portable/ComfyUI/black-forest-labs/FLUX.1-dev

[lior007]

the error is:

got prompt Process using 2 roles,mode is img2img.... total_vram is 16379.5,aggressive_offload is True,offload is True using repo_id and ckpt ,start flux-pulid processing... !!! Exception during processing !!! exceptions must derive from BaseException Traceback (most recent call last): File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\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 "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\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 "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 169, in _map_node_over_list process_inputs(input_dict, i) File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 158, in process_inputs results.append(getattr(obj, func)(**inputs)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_StoryDiffusion\Storydiffusion_node.py", line 1396, in story_model_loader pipe=flux_loader(folder_paths,ckpt_path,repo_id,AutoencoderKL,save_model,model_type,pulid,clip_vision_path,NF4,vae_id,offload,aggressive_offload,pulid_ckpt,quantized_mode, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_StoryDiffusion\model_loader_utils.py", line 591, in flux_loader raise "Now,using pulid must choice ae from comfyUI vae menu" TypeError: exceptions must derive from BaseException File

[smthemex]

use flux pulid need choice a ae

[lior007]

OK HERE IS NEW PRINT SCREEN NOW THERE IS NEW ERROR

!!! Exception during processing !!! 'list' object has no attribute 'replace' Traceback (most recent call last): File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\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 "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\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 "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 169, in _map_node_over_list process_inputs(input_dict, i) File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 158, in process_inputs results.append(getattr(obj, func)(inputs)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_StoryDiffusion\Storydiffusion_node.py", line 1689, in story_sampler for value in gen: File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_StoryDiffusion\Storydiffusion_node.py", line 700, in process_generation id_image = pipe.generate_image( ^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\utils_contextlib.py", line 116, in decorate_context return func(*args, *kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_StoryDiffusion\PuLID\app_flux.py", line 126, in generate_image inp = prepare(t5=self.t5, clip=self.clip, img=x, prompt=opts.text,if_repo=self.if_repo) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_StoryDiffusion\PuLID\flux\sampling.py", line 49, in prepare txt = t5(prompt) ^^^^^^^^^^ File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1736, in _wrapped_call_impl return self._call_impl(args, kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1747, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_StoryDiffusion\PuLID\flux\modules\conditioner.py", line 49, in forward tokens = self.clip_cf.tokenize(text) ^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\comfy\sd.py", line 113, in tokenize return self.tokenizer.tokenize_with_weights(text, return_word_ids) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\comfy\text_encoders\flux.py", line 27, in tokenize_with_weights out["l"] = self.clip_l.tokenize_with_weights(text, return_word_ids) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\comfy\sd1_clip.py", line 462, in tokenize_with_weights text = escape_important(text) ^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\comfy\sd1_clip.py", line 283, in escape_important text = text.replace("\)", "\0\1") ^^^^^^^^^^^^ AttributeError: 'list' object has no attribute 'replace'

[smthemex]

please flow this example。 this

[lior007]

please flow this example。 this

do like this... and got this. whay?

[smthemex]

use unet checkpoints，like this huggingface please read readme

[lior007]

use unet checkpoints，like this huggingface please read readme

1. unet checkpoint in your link : https://huggingface.co/Kijai/flux-fp8/tree/main Do I need to download the flux1-dev-fp8.safetensors file and change it to flux1-kj-dev-fp8.safetensors and put it in the UNET folder?

2.I used exactly the same settings as in this example: https://github.com/smthemex/ComfyUI_StoryDiffusion/blob/main/examples/flux_pulid_new.png

[lior007]

OK. NOW ITS WORLING!! THANKS