'NoneType' object has no attribute 'tokenize' error

[infarctus1]

Your question

Hello,

Hello, I'm new to using ComfyUI. I recently downloaded the Stable Diffusion 3.5 large model, but I encountered an error as shown below. I searched a bit but couldn’t fully understand the issue. To be honest, I’m still not very confident in what I’m doing as I'm in the learning phase. Apologies for taking up your time, and thank you in advance for any help you can provide. I’m sharing a screenshot and the error code below.

Logs

# ComfyUI Error Report
## Error Details
- **Node Type:** CLIPTextEncode
- **Exception Type:** AttributeError
- **Exception Message:** 'NoneType' object has no attribute 'tokenize'
## Stack Trace

  File "C:\Users\ulasc\OneDrive\Masaüstü\Others\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 "C:\Users\ulasc\OneDrive\Masaüstü\Others\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 "C:\Users\ulasc\OneDrive\Masaüstü\Others\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 169, in _map_node_over_list
    process_inputs(input_dict, i)

  File "C:\Users\ulasc\OneDrive\Masaüstü\Others\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 158, in process_inputs
    results.append(getattr(obj, func)(**inputs))
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "C:\Users\ulasc\OneDrive\Masaüstü\Others\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\nodes.py", line 64, in encode
    tokens = clip.tokenize(text)
             ^^^^^^^^^^^^^

System Information

• ComfyUI Version: v0.2.4
• Arguments: ComfyUI\main.py --windows-standalone-build
• OS: nt
• Python Version: 3.12.7 (tags/v3.12.7:0b05ead, Oct 1 2024, 03:06:41) [MSC v.1941 64 bit (AMD64)]
• Embedded Python: true
• PyTorch Version: 2.5.0+cu124

Devices

• Name: cuda:0 NVIDIA GeForce RTX 4090 Laptop GPU : cudaMallocAsync
  • Type: cuda
  • VRAM Total: 17170956288
  • VRAM Free: 15778971648
  • Torch VRAM Total: 0
  • Torch VRAM Free: 0

Logs

2024-10-27 20:32:27,900 - root - INFO - Total VRAM 16376 MB, total RAM 65304 MB
2024-10-27 20:32:27,900 - root - INFO - pytorch version: 2.5.0+cu124
2024-10-27 20:32:27,900 - root - INFO - Set vram state to: NORMAL_VRAM
2024-10-27 20:32:27,901 - root - INFO - Device: cuda:0 NVIDIA GeForce RTX 4090 Laptop GPU : cudaMallocAsync
2024-10-27 20:32:28,711 - root - INFO - Using pytorch cross attention
2024-10-27 20:32:29,686 - root - INFO - [Prompt Server] web root: C:\Users\ulasc\OneDrive\Masaüstü\Others\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\web
2024-10-27 20:32:30,076 - root - INFO - 
Import times for custom nodes:
2024-10-27 20:32:30,077 - root - INFO -    0.0 seconds: C:\Users\ulasc\OneDrive\Masaüstü\Others\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\custom_nodes\websocket_image_save.py
2024-10-27 20:32:30,078 - root - INFO -    0.1 seconds: C:\Users\ulasc\OneDrive\Masaüstü\Others\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Manager
2024-10-27 20:32:30,078 - root - INFO - 
2024-10-27 20:32:30,082 - root - INFO - Starting server

2024-10-27 20:32:30,082 - root - INFO - To see the GUI go to: http://127.0.0.1:8188
2024-10-27 20:32:34,168 - root - INFO - got prompt
2024-10-27 20:32:34,339 - root - INFO - model weight dtype torch.float16, manual cast: None
2024-10-27 20:32:34,341 - root - INFO - model_type FLOW
2024-10-27 20:32:36,081 - root - INFO - Using pytorch attention in VAE
2024-10-27 20:32:36,084 - root - INFO - Using pytorch attention in VAE
2024-10-27 20:32:36,190 - root - WARNING - no CLIP/text encoder weights in checkpoint, the text encoder model will not be loaded.
2024-10-27 20:32:37,833 - root - ERROR - !!! Exception during processing !!! 'NoneType' object has no attribute 'tokenize'
2024-10-27 20:32:37,834 - root - ERROR - Traceback (most recent call last):
  File "C:\Users\ulasc\OneDrive\Masaüstü\Others\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 "C:\Users\ulasc\OneDrive\Masaüstü\Others\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 "C:\Users\ulasc\OneDrive\Masaüstü\Others\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 169, in _map_node_over_list
    process_inputs(input_dict, i)
  File "C:\Users\ulasc\OneDrive\Masaüstü\Others\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 158, in process_inputs
    results.append(getattr(obj, func)(**inputs))
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\ulasc\OneDrive\Masaüstü\Others\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\nodes.py", line 64, in encode
    tokens = clip.tokenize(text)
             ^^^^^^^^^^^^^
AttributeError: 'NoneType' object has no attribute 'tokenize'

2024-10-27 20:32:37,836 - root - INFO - Prompt executed in 3.66 seconds
2024-10-27 20:34:15,408 - root - INFO - got prompt
2024-10-27 20:34:15,422 - root - ERROR - !!! Exception during processing !!! 'NoneType' object has no attribute 'tokenize'
2024-10-27 20:34:15,423 - root - ERROR - Traceback (most recent call last):
  File "C:\Users\ulasc\OneDrive\Masaüstü\Others\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 "C:\Users\ulasc\OneDrive\Masaüstü\Others\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 "C:\Users\ulasc\OneDrive\Masaüstü\Others\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 169, in _map_node_over_list
    process_inputs(input_dict, i)
  File "C:\Users\ulasc\OneDrive\Masaüstü\Others\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 158, in process_inputs
    results.append(getattr(obj, func)(**inputs))
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\ulasc\OneDrive\Masaüstü\Others\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\nodes.py", line 64, in encode
    tokens = clip.tokenize(text)
             ^^^^^^^^^^^^^
AttributeError: 'NoneType' object has no attribute 'tokenize'

2024-10-27 20:34:15,425 - root - INFO - Prompt executed in 0.01 seconds
2024-10-27 20:34:21,195 - root - INFO - got prompt
2024-10-27 20:34:21,202 - root - ERROR - !!! Exception during processing !!! 'NoneType' object has no attribute 'tokenize'
2024-10-27 20:34:21,204 - root - ERROR - Traceback (most recent call last):
  File "C:\Users\ulasc\OneDrive\Masaüstü\Others\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 "C:\Users\ulasc\OneDrive\Masaüstü\Others\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 "C:\Users\ulasc\OneDrive\Masaüstü\Others\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 169, in _map_node_over_list
    process_inputs(input_dict, i)
  File "C:\Users\ulasc\OneDrive\Masaüstü\Others\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 158, in process_inputs
    results.append(getattr(obj, func)(**inputs))
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\ulasc\OneDrive\Masaüstü\Others\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\nodes.py", line 64, in encode
    tokens = clip.tokenize(text)
             ^^^^^^^^^^^^^
AttributeError: 'NoneType' object has no attribute 'tokenize'

2024-10-27 20:34:21,207 - root - INFO - Prompt executed in 0.01 seconds
2024-10-27 20:34:34,274 - root - INFO - got prompt
2024-10-27 20:34:34,281 - root - ERROR - !!! Exception during processing !!! 'NoneType' object has no attribute 'tokenize'
2024-10-27 20:34:34,282 - root - ERROR - Traceback (most recent call last):
  File "C:\Users\ulasc\OneDrive\Masaüstü\Others\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 "C:\Users\ulasc\OneDrive\Masaüstü\Others\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 "C:\Users\ulasc\OneDrive\Masaüstü\Others\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 169, in _map_node_over_list
    process_inputs(input_dict, i)
  File "C:\Users\ulasc\OneDrive\Masaüstü\Others\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 158, in process_inputs
    results.append(getattr(obj, func)(**inputs))
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\ulasc\OneDrive\Masaüstü\Others\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\nodes.py", line 64, in encode
    tokens = clip.tokenize(text)
             ^^^^^^^^^^^^^
AttributeError: 'NoneType' object has no attribute 'tokenize'

2024-10-27 20:34:34,284 - root - INFO - Prompt executed in 0.01 seconds
2024-10-27 20:37:53,721 - root - INFO - got prompt
2024-10-27 20:37:53,728 - root - ERROR - !!! Exception during processing !!! 'NoneType' object has no attribute 'tokenize'
2024-10-27 20:37:53,730 - root - ERROR - Traceback (most recent call last):
  File "C:\Users\ulasc\OneDrive\Masaüstü\Others\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 "C:\Users\ulasc\OneDrive\Masaüstü\Others\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 "C:\Users\ulasc\OneDrive\Masaüstü\Others\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 169, in _map_node_over_list
    process_inputs(input_dict, i)
  File "C:\Users\ulasc\OneDrive\Masaüstü\Others\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 158, in process_inputs
    results.append(getattr(obj, func)(**inputs))
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\ulasc\OneDrive\Masaüstü\Others\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\nodes.py", line 64, in encode
    tokens = clip.tokenize(text)
             ^^^^^^^^^^^^^
AttributeError: 'NoneType' object has no attribute 'tokenize'

2024-10-27 20:37:53,733 - root - INFO - Prompt executed in 0.01 seconds
2024-10-27 20:38:03,213 - root - INFO - got prompt
2024-10-27 20:38:03,224 - root - ERROR - !!! Exception during processing !!! 'NoneType' object has no attribute 'tokenize'
2024-10-27 20:38:03,227 - root - ERROR - Traceback (most recent call last):
  File "C:\Users\ulasc\OneDrive\Masaüstü\Others\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 "C:\Users\ulasc\OneDrive\Masaüstü\Others\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 "C:\Users\ulasc\OneDrive\Masaüstü\Others\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 169, in _map_node_over_list
    process_inputs(input_dict, i)
  File "C:\Users\ulasc\OneDrive\Masaüstü\Others\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 158, in process_inputs
    results.append(getattr(obj, func)(**inputs))
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\ulasc\OneDrive\Masaüstü\Others\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\nodes.py", line 64, in encode
    tokens = clip.tokenize(text)
             ^^^^^^^^^^^^^
AttributeError: 'NoneType' object has no attribute 'tokenize'

2024-10-27 20:38:03,229 - root - INFO - Prompt executed in 0.01 seconds
2024-10-27 20:41:43,955 - root - INFO - got prompt
2024-10-27 20:41:43,959 - root - ERROR - !!! Exception during processing !!! 'NoneType' object has no attribute 'tokenize'
2024-10-27 20:41:43,961 - root - ERROR - Traceback (most recent call last):
  File "C:\Users\ulasc\OneDrive\Masaüstü\Others\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 "C:\Users\ulasc\OneDrive\Masaüstü\Others\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 "C:\Users\ulasc\OneDrive\Masaüstü\Others\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 169, in _map_node_over_list
    process_inputs(input_dict, i)
  File "C:\Users\ulasc\OneDrive\Masaüstü\Others\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 158, in process_inputs
    results.append(getattr(obj, func)(**inputs))
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\ulasc\OneDrive\Masaüstü\Others\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\nodes.py", line 64, in encode
    tokens = clip.tokenize(text)
             ^^^^^^^^^^^^^
AttributeError: 'NoneType' object has no attribute 'tokenize'

2024-10-27 20:41:43,962 - root - INFO - Prompt executed in 0.00 seconds

Attached Workflow

Please make sure that workflow does not contain any sensitive information such as API keys or passwords.

{"last_node_id":9,"last_link_id":9,"nodes":[{"id":7,"type":"CLIPTextEncode","pos":{"0":413,"1":389},"size":{"0":425.27801513671875,"1":180.6060791015625},"flags":{},"order":3,"mode":0,"inputs":[{"name":"clip","type":"CLIP","link":5}],"outputs":[{"name":"CONDITIONING","type":"CONDITIONING","links":[6],"slot_index":0}],"properties":{"Node name for S&R":"CLIPTextEncode"},"widgets_values":["text, watermark"]},{"id":6,"type":"CLIPTextEncode","pos":{"0":415,"1":186},"size":{"0":422.84503173828125,"1":164.31304931640625},"flags":{},"order":2,"mode":0,"inputs":[{"name":"clip","type":"CLIP","link":3}],"outputs":[{"name":"CONDITIONING","type":"CONDITIONING","links":[4],"slot_index":0}],"properties":{"Node name for S&R":"CLIPTextEncode"},"widgets_values":["beautiful scenery nature glass bottle landscape, , purple galaxy bottle,"]},{"id":3,"type":"KSampler","pos":{"0":863,"1":186},"size":{"0":315,"1":262},"flags":{},"order":4,"mode":0,"inputs":[{"name":"model","type":"MODEL","link":1},{"name":"positive","type":"CONDITIONING","link":4},{"name":"negative","type":"CONDITIONING","link":6},{"name":"latent_image","type":"LATENT","link":2}],"outputs":[{"name":"LATENT","type":"LATENT","links":[7],"slot_index":0}],"properties":{"Node name for S&R":"KSampler"},"widgets_values":[600775422529072,"randomize",20,8,"euler","normal",1]},{"id":8,"type":"VAEDecode","pos":{"0":1209,"1":188},"size":{"0":210,"1":46},"flags":{},"order":5,"mode":0,"inputs":[{"name":"samples","type":"LATENT","link":7},{"name":"vae","type":"VAE","link":8}],"outputs":[{"name":"IMAGE","type":"IMAGE","links":[9],"slot_index":0}],"properties":{"Node name for S&R":"VAEDecode"},"widgets_values":[]},{"id":9,"type":"SaveImage","pos":{"0":1451,"1":189},"size":{"0":210,"1":58},"flags":{},"order":6,"mode":0,"inputs":[{"name":"images","type":"IMAGE","link":9}],"outputs":[],"properties":{},"widgets_values":["ComfyUI"]},{"id":5,"type":"EmptyLatentImage","pos":{"0":466,"1":650},"size":{"0":315,"1":106},"flags":{},"order":0,"mode":0,"inputs":[],"outputs":[{"name":"LATENT","type":"LATENT","links":[2],"slot_index":0}],"properties":{"Node name for S&R":"EmptyLatentImage"},"widgets_values":[512,512,1]},{"id":4,"type":"CheckpointLoaderSimple","pos":{"0":26,"1":474},"size":{"0":315,"1":98},"flags":{},"order":1,"mode":0,"inputs":[],"outputs":[{"name":"MODEL","type":"MODEL","links":[1],"slot_index":0},{"name":"CLIP","type":"CLIP","links":[3,5],"slot_index":1},{"name":"VAE","type":"VAE","links":[8],"slot_index":2}],"properties":{"Node name for S&R":"CheckpointLoaderSimple"},"widgets_values":["sd3.5_large.safetensors"]}],"links":[[1,4,0,3,0,"MODEL"],[2,5,0,3,3,"LATENT"],[3,4,1,6,0,"CLIP"],[4,6,0,3,1,"CONDITIONING"],[5,4,1,7,0,"CLIP"],[6,7,0,3,2,"CONDITIONING"],[7,3,0,8,0,"LATENT"],[8,4,2,8,1,"VAE"],[9,8,0,9,0,"IMAGE"]],"groups":[],"config":{},"extra":{"ds":{"scale":1,"offset":[0,0]}},"version":0.4}

Additional Context

(Please add any additional context or steps to reproduce the error here)

### Other

_No response_

[vivi-gomez]

You are using the clip from the model. Try the node calles triple clip. And use clip_g clip_l and 5xx? (Dont remember the name)

[LukeG89]

@infarctus1 Here you will find instructions, all the models you need and an example workflow: https://blog.comfy.org/sd3-5-comfyui/

[infarctus1]

You are using the clip from the model. Try the node calles triple clip. And use clip_g clip_l and 5xx? (Dont remember the name)

Hello,

I check it your link and i believe i do same things there what write.

i will share you some screen shots,

and still same error.

You are using the clip from the model. Try the node calles triple clip. And use clip_g clip_l and 5xx? (Dont remember the name)

Sory but realy i didnt understund. I am so new about this. And already its seems to me so complicated this comfui nodes. Can you explaine a bit more. Thanks. :(

[LukeG89]

@infarctus1 You need to load the text encoder models through TripleCLIPLoader node and use it instead.

[infarctus1]

@infarctus1 You need to load the text encoder models through TripleCLIPLoader node and use it instead.

Hi Luke,

Thank you so much bro. After 3 hour search (where i can add tripleclip loader) I found by myself :)

Now its working. Thank you again.

[amthedrk]

Thank you for this query and guidance.
I recently got to know about the SD 3.5 and wanted to test out my new 4080 Super.

I ran into the same error and followed the steps - copy pasted the files in the target folders and it's running perfectly now.

[Septemberlemon]

@infarctus1 You need to load the text encoder models through TripleCLIPLoader node and use it instead.

nice and thank u very much!

[kanilmari]

@infarctus1 You need to load the text encoder models through TripleCLIPLoader node and use it instead.

Hi Luke,

Thank you so much bro. After 3 hour search (where i can add tripleclip loader) I found by myself :)

Now its working. Thank you again.

Can you tell us how exactly did you do it? In ComfyUI, you right-click on the empty area and what exactly do you do then?

[ltdrdata]

@infarctus1 You need to load the text encoder models through TripleCLIPLoader node and use it instead.

Hi Luke,
Thank you so much bro. After 3 hour search (where i can add tripleclip loader) I found by myself :)
Now its working. Thank you again.

Can you tell us how exactly did you do it? In ComfyUI, you right-click on the empty area and what exactly do you do then?

double click empty area and search triple that is the most easy way.

[jon-bondy]

I ran into the same error and followed the steps - copy pasted the files in the target folders and it's running perfectly now.

Please specify which files and which target folders. Mine is still not running properly. I can see the TripleCLIPLoader but cannot specify any of the 3 file names.

[jon-bondy]

@infarctus1 You need to load the text encoder models through TripleCLIPLoader node and use it instead.

It would be helpful to me if someone showed the ENTIRE topography of all of the windows, not just this small sub-section. I have TripleCLIPLoader attached properly to Positive Prompt and Negative Prompt, but have no idea how the latter 2 are attached. I am using SD3.5M_example_workflow.json. It seems that is incorrect or incomplete (else why would I need to add TripleCLIPLoader?). Is there a better workflow file I should be using, please?

[jon-bondy]

I went here

https://comfyui-wiki.com/tutorial/advanced/stable-diffusion-3-5-comfyui-workflow.en-US

and found a button named "Download sd3.5-t2i-fp16-workflow.json" (I cannot provide the URL the button uses because the page has been locked in some manner).

With that workflow, I am told that some of the TripleCLIPLoader values are not in some list. When I click on the names, to try to correct them, they change to "undefined". I have no idea how to enter or select the correct names. The three files (clip_I, clip_g, and t5xxxl are all in the models/clip folder, as instructed, so they should be present/correct and selectable.

[ltdrdata]

@infarctus1 You need to load the text encoder models through TripleCLIPLoader node and use it instead.

It would be helpful to me if someone showed the ENTIRE topography of all of the windows, not just this small sub-section. I have TripleCLIPLoader attached properly to Positive Prompt and Negative Prompt, but have no idea how the latter 2 are attached. I am using SD3.5M_example_workflow.json. It seems that is incorrect or incomplete (else why would I need to add TripleCLIPLoader?). Is there a better workflow file I should be using, please?

You can find official workflows from here.
https://comfyanonymous.github.io/ComfyUI_examples/

Each image contains worfklow, so drag & drop to your ComfyUI.