UNet Loader doesn't identify qwen image 21 architecture

#31

by ShardoolShrivastava - opened 2 days ago

Have everything sorted out but getting this error when trying to run the default workflow made after following this method. I have done git pull already but I'm already on the latest version.
Anyone got any solution for this? Attaching the error code here .
Node threw an error during execution.

ComfyUI Error Report

Error Details

Node ID: 75
Node Type: UnetLoaderGGUF
Exception Type: ValueError
Exception Message: ValueError: Unexpected architecture type in GGUF file: 'qwen_image21'

Stack Trace

  File "/home/baba/ComfyUI/execution.py", line 547, in execute
    output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
                                                              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "/home/baba/ComfyUI/execution.py", line 352, in get_output_data
    return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "/home/baba/ComfyUI/execution.py", line 326, in _async_map_node_over_list
    await process_inputs(input_dict, i)

  File "/home/baba/ComfyUI/execution.py", line 314, in process_inputs
    result = f(**inputs)
             ^^^^^^^^^^^

  File "/home/baba/ComfyUI/custom_nodes/ComfyUI-GGUF/nodes.py", line 169, in load_unet
    sd, extra = gguf_sd_loader(unet_path)
                ^^^^^^^^^^^^^^^^^^^^^^^^^

  File "/home/baba/ComfyUI/custom_nodes/ComfyUI-GGUF/loader.py", line 110, in gguf_sd_loader
    raise ValueError(f"Unexpected architecture type in GGUF file: {arch_str!r}")

System Information

ComfyUI Version: 0.37.0
Arguments: main.py
OS: linux
Python Version: 3.11.16 (main, Sep 1 2026, 14:18:37) [Clang 22.1.3 ]
Embedded Python: false
PyTorch Version: 2.14.0+cu130

Devices

Name: cuda:0 NVIDIA GeForce RTX 3050 Laptop GPU : cudaMallocAsync
- Type: cuda
- VRAM Total: 3953393664
- VRAM Free: 3860529152
- Torch VRAM Total: 0
- Torch VRAM Free: 0

Logs

2026-09-26T23:56:11.377583 - [32m[INFO][0m setup plugin alembic.autogenerate.schemas
2026-09-26T23:56:11.377650 - [32m[INFO][0m setup plugin alembic.autogenerate.tables
2026-09-26T23:56:11.377690 - [32m[INFO][0m setup plugin alembic.autogenerate.types
2026-09-26T23:56:11.377728 - [32m[INFO][0m setup plugin alembic.autogenerate.constraints
2026-09-26T23:56:11.377763 - [32m[INFO][0m setup plugin alembic.autogenerate.defaults
2026-09-26T23:56:11.377799 - [32m[INFO][0m setup plugin alembic.autogenerate.comments
2026-09-26T23:56:11.377839 - [32m[INFO][0m setup plugin alembic.ext.checkconstraint_byname
2026-09-26T23:56:17.600618 - [32m[INFO][0m Found comfy_kitchen backend triton: {'available': True, 'disabled': True, 'unavailable_reason': None, 'capabilities': ['adaln', 'apply_rope', 'apply_rope1', 'apply_rope1_', 'apply_rope_', 'apply_rope_split_half', 'apply_rope_split_half1', 'apply_rope_split_half1_', 'apply_rope_split_half_', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'int8_linear', 'na3d', 'quantize_and_rotate_rowwise', 'quantize_int8_rowwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'rms_adaln', 'rms_rope', 'rms_rope1', 'rms_rope1_', 'rms_rope_', 'rms_rope_split_half', 'rms_rope_split_half1', 'rms_rope_split_half1_', 'rms_rope_split_half_', 'w4a8_int8_linear']}
2026-09-26T23:56:17.600697 - [32m[INFO][0m Found comfy_kitchen backend eager: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['adaln', 'apply_rope', 'apply_rope1', 'apply_rope1_', 'apply_rope_', 'apply_rope_split_half', 'apply_rope_split_half1', 'apply_rope_split_half1_', 'apply_rope_split_half_', 'convrot_w4a4_linear', 'dequantize_convrot_w4a4_weight', 'dequantize_int8_convrot_weight', 'dequantize_int8_convrot_weight_dtype', 'dequantize_int8_embedding', 'dequantize_int8_simple', 'dequantize_int8_simple_dtype', 'dequantize_mxfp8', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'dequantize_w4a8_int8_weight', 'fp16_conv3d', 'fp16_linear', 'gemv_awq_w4a16', 'group_norm_silu_pad3d', 'int8_linear', 'na3d', 'prepare_int4_weight_for_int8_linear', 'quantize_and_rotate_rowwise', 'quantize_convrot_w4a4_weight', 'quantize_int8_convrot_weight', 'quantize_int8_rowwise', 'quantize_int8_tensorwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'quantize_svdquant_w4a4', 'quantize_w4a8_int8_weight', 'rms_adaln', 'rms_rope', 'rms_rope1', 'rms_rope1_', 'rms_rope_', 'rms_rope_split_half', 'rms_rope_split_half1', 'rms_rope_split_half1_', 'rms_rope_split_half_', 'rotate_int8_convrot_weight', 'scaled_mm_mxfp8', 'scaled_mm_nvfp4', 'scaled_mm_svdquant_w4a4', 'sol_attn', 'stochastic_rounding_fp8', 'w4a8_int8_linear']}
2026-09-26T23:56:17.600740 - [32m[INFO][0m Found comfy_kitchen backend hip: {'available': False, 'disabled': False, 'unavailable_reason': 'PyTorch ROCm/HIP runtime not available', 'capabilities': []}
2026-09-26T23:56:17.600786 - [32m[INFO][0m Found comfy_kitchen backend cuda: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['adaln', 'apply_rope', 'apply_rope1', 'apply_rope1_', 'apply_rope_', 'apply_rope_split_half', 'apply_rope_split_half1', 'apply_rope_split_half1_', 'apply_rope_split_half_', 'convrot_w4a4_linear', 'dequantize_convrot_w4a4_weight', 'dequantize_int8_convrot_weight', 'dequantize_int8_convrot_weight_dtype', 'dequantize_int8_simple', 'dequantize_int8_simple_dtype', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'dequantize_w4a8_int8_weight', 'fp16_conv3d', 'fp16_linear', 'gemv_awq_w4a16', 'group_norm_silu_pad3d', 'int8_linear', 'na3d', 'prepare_int4_weight_for_int8_linear', 'quantize_and_rotate_rowwise', 'quantize_convrot_w4a4_weight', 'quantize_int8_convrot_weight', 'quantize_int8_rowwise', 'quantize_int8_tensorwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'quantize_svdquant_w4a4', 'quantize_w4a8_int8_weight', 'rms_adaln', 'rms_rope', 'rms_rope1', 'rms_rope1_', 'rms_rope_', 'rms_rope_split_half', 'rms_rope_split_half1', 'rms_rope_split_half1_', 'rms_rope_split_half_', 'rotate_int8_convrot_weight', 'scaled_mm_nvfp4', 'scaled_mm_svdquant_w4a4', 'sol_attn', 'stochastic_rounding_fp8', 'w4a8_int8_linear']}
2026-09-26T23:56:17.611959 - [32m[INFO][0m Checkpoint files will always be loaded safely.
2026-09-26T23:56:17.750513 - [32m[INFO][0m Total VRAM 3770 MB, total RAM 14871 MB
2026-09-26T23:56:17.750851 - [32m[INFO][0m pytorch version: 2.14.0+cu130
2026-09-26T23:56:17.751072 - [32m[INFO][0m Set vram state to: NORMAL_VRAM
2026-09-26T23:56:17.751178 - [32m[INFO][0m Device: cuda:0 NVIDIA GeForce RTX 3050 Laptop GPU : cudaMallocAsync
2026-09-26T23:56:17.751310 - [32m[INFO][0m Using async weight offloading with 2 streams
2026-09-26T23:56:17.751976 - [32m[INFO][0m Enabled pinned memory 5948.0
2026-09-26T23:56:17.942359 - [32m[INFO][0m Using pytorch attention
2026-09-26T23:56:21.004170 - [32m[INFO][0m aimdo: /project/src/control.c:283:INFO:comfy-aimdo inited for GPU: NVIDIA GeForce RTX 3050 Laptop GPU (VRAM: 3770 MB)
2026-09-26T23:56:21.004268 - [32m[INFO][0m DynamicVRAM support detected and enabled
2026-09-26T23:56:21.004319 - [32m[INFO][0m Python version: 3.11.16 (main, Sep  1 2026, 14:18:37) [Clang 22.1.3 ]
2026-09-26T23:56:21.004351 - [32m[INFO][0m ComfyUI version: 0.37.0
2026-09-26T23:56:21.004802 - [32m[INFO][0m comfy-aimdo version: 0.5.5
2026-09-26T23:56:21.005346 - [32m[INFO][0m comfy-kitchen version: 0.2.35
2026-09-26T23:56:21.007707 - [32m[INFO][0m comfyui-frontend-package version: 1.53.6
2026-09-26T23:56:21.007755 - [32m[INFO][0m comfyui-workflow-templates version: 0.11.70
2026-09-26T23:56:21.007799 - [32m[INFO][0m comfyui-embedded-docs version: 0.5.12
2026-09-26T23:56:21.007838 - [32m[INFO][0m comfy-kitchen version: 0.2.35
2026-09-26T23:56:21.007872 - [32m[INFO][0m comfy-aimdo version: 0.5.5
2026-09-26T23:56:21.008588 - [32m[INFO][0m [Prompt Server] web root: /home/baba/ComfyUI/.venv/lib/python3.11/site-packages/comfyui_frontend_package/static
2026-09-26T23:56:21.009775 - [32m[INFO][0m Asset seeder disabled
2026-09-26T23:56:21.056556 - /home/baba/ComfyUI/.venv/lib/python3.11/site-packages/torch/jit/_script.py:1491: FutureWarning: `torch.jit.script` is deprecated. Please switch to `torch.compile` or `torch.export`.
  warnings.warn(
2026-09-26T23:56:21.474494 - [32m[INFO][0m No OpenGL_accelerate module loaded: No module named 'OpenGL_accelerate'
2026-09-26T23:56:22.578220 - [32m[INFO][0m ComfyUI-GGUF: Allowing full torch compile
2026-09-26T23:56:22.580964 - [32m[INFO][0m 
Import times for custom nodes:
2026-09-26T23:56:22.581019 - [32m[INFO][0m    0.0 seconds: /home/baba/ComfyUI/custom_nodes/websocket_image_save.py
2026-09-26T23:56:22.581066 - [32m[INFO][0m    0.0 seconds: /home/baba/ComfyUI/custom_nodes/ComfyUI-GGUF
2026-09-26T23:56:22.581094 - [32m[INFO][0m 
2026-09-26T23:56:22.585315 - [32m[INFO][0m Context impl SQLiteImpl.
2026-09-26T23:56:22.585369 - [32m[INFO][0m Will assume non-transactional DDL.
2026-09-26T23:56:22.650655 - [32m[INFO][0m Using RAM pressure cache.
2026-09-26T23:56:22.651090 - [32m[INFO][0m Starting server

2026-09-26T23:56:22.651343 - [32m[INFO][0m To see the GUI go to: http://127.0.0.1:8188
2026-09-26T23:57:02.246476 - [32m[INFO][0m got prompt
2026-09-26T23:57:02.318950 - [32m[INFO][0m Model storage policy: fast_disk=True paths=['/home/baba/ComfyUI/models/vae/qwen_image_2.1_vae_bf16.safetensors']
2026-09-26T23:57:02.324341 - [32m[INFO][0m Using pytorch attention in VAE
2026-09-26T23:57:02.325745 - [32m[INFO][0m Using pytorch attention in VAE
2026-09-26T23:57:02.584026 - [32m[INFO][0m VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16
2026-09-26T23:57:02.604369 - [32m[INFO][0m Found quantization metadata version 1
2026-09-26T23:57:02.604992 - [32m[INFO][0m Using MixedPrecisionOps for text encoder
2026-09-26T23:57:03.235595 - [32m[INFO][0m Model storage policy: fast_disk=True paths=['/home/baba/ComfyUI/models/text_encoders/qwen3vl_8b_int8_convrot.safetensors']
2026-09-26T23:57:03.297532 - [32m[INFO][0m CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cpu, dtype: torch.float16
2026-09-26T23:57:03.301532 - [32m[INFO][0m Requested to load QwenImage21TEModel_
2026-09-26T23:57:03.440050 - [32m[INFO][0m Model QwenImage21TEModel_ prepared for dynamic VRAM loading. 8916MB Staged. 0 patches attached. Force pre-loaded 255 weights: 849 KB.
2026-09-26T23:57:13.211126 - [32m[INFO][0m Model QwenImage21TEModel_ prepared for dynamic VRAM loading. 8916MB Staged. 0 patches attached. Force pre-loaded 255 weights: 849 KB.
2026-09-26T23:57:14.535539 - [1m[31m[ERROR][0m !!! Exception during processing !!! Unexpected architecture type in GGUF file: 'qwen_image21'
2026-09-26T23:57:14.538246 - [1m[31m[ERROR][0m Traceback (most recent call last):
  File "/home/baba/ComfyUI/execution.py", line 547, in execute
    output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
                                                              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/baba/ComfyUI/execution.py", line 352, in get_output_data
    return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/baba/ComfyUI/execution.py", line 326, in _async_map_node_over_list
    await process_inputs(input_dict, i)
  File "/home/baba/ComfyUI/execution.py", line 314, in process_inputs
    result = f(**inputs)
             ^^^^^^^^^^^
  File "/home/baba/ComfyUI/custom_nodes/ComfyUI-GGUF/nodes.py", line 169, in load_unet
    sd, extra = gguf_sd_loader(unet_path)
                ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/baba/ComfyUI/custom_nodes/ComfyUI-GGUF/loader.py", line 110, in gguf_sd_loader
    raise ValueError(f"Unexpected architecture type in GGUF file: {arch_str!r}")
ValueError: Unexpected architecture type in GGUF file: 'qwen_image21'

2026-09-26T23:57:14.539360 - [32m[INFO][0m [32mPrompt executed in 12.29 seconds[0m
2026-09-27T00:00:45.150321 - [32m[INFO][0m got prompt
2026-09-27T00:00:45.234066 - [1m[31m[ERROR][0m !!! Exception during processing !!! Unexpected architecture type in GGUF file: 'qwen_image21'
2026-09-27T00:00:45.244846 - [1m[31m[ERROR][0m Traceback (most recent call last):
  File "/home/baba/ComfyUI/execution.py", line 547, in execute
    output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
                                                              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/baba/ComfyUI/execution.py", line 352, in get_output_data
    return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/baba/ComfyUI/execution.py", line 326, in _async_map_node_over_list
    await process_inputs(input_dict, i)
  File "/home/baba/ComfyUI/execution.py", line 314, in process_inputs
    result = f(**inputs)
             ^^^^^^^^^^^
  File "/home/baba/ComfyUI/custom_nodes/ComfyUI-GGUF/nodes.py", line 169, in load_unet
    sd, extra = gguf_sd_loader(unet_path)
                ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/baba/ComfyUI/custom_nodes/ComfyUI-GGUF/loader.py", line 110, in gguf_sd_loader
    raise ValueError(f"Unexpected architecture type in GGUF file: {arch_str!r}")
ValueError: Unexpected architecture type in GGUF file: 'qwen_image21'

2026-09-27T00:00:45.248397 - [32m[INFO][0m [32mPrompt executed in 0.08 seconds[0m

Attached Workflow

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

{"id":"ce5b4c47-4d39-4ced-b239-fbaab507a32f","revision":0,"last_node_id":77,"last_link_id":83,"nodes":[{"id":9,"type":"SaveImage","pos":[1279.9999726783708,319.9999392082668],"size":[300,420],"flags":{},"order":9,"mode":0,"inputs":[{"localized_name":"images","name":"images","type":"IMAGE","link":80},{"localized_name":"filename_prefix","name":"filename_prefix","type":"STRING","widget":{"name":"filename_prefix"},"link":null}],"outputs":[{"localized_name":"images","name":"images","type":"IMAGE","links":null}],"properties":{"Node name for S&R":"SaveImage","cnr_id":"comfy-core","ver":"0.3.64","enableTabs":false,"tabWidth":65,"tabXOffset":10,"hasSecondTab":false,"secondTabText":"Send Back","secondTabOffset":80,"secondTabWidth":65},"widgets_values":["ComfyUI"],"widgets_values_named":{"filename_prefix":"ComfyUI"}},{"id":62,"type":"CLIPLoader","pos":[-239.9999987113997,420.0000536491848],"size":[340,169.3125],"flags":{},"order":0,"mode":0,"inputs":[{"localized_name":"clip_name","name":"clip_name","type":"COMBO","widget":{"name":"clip_name"},"link":null},{"localized_name":"type","name":"type","type":"COMBO","widget":{"name":"type"},"link":null},{"localized_name":"device","name":"device","shape":7,"type":"COMBO","widget":{"name":"device"},"link":null}],"outputs":[{"localized_name":"CLIP","name":"CLIP","type":"CLIP","links":[79,81]}],"properties":{"Node name for S&R":"CLIPLoader","cnr_id":"comfy-core","ver":"0.3.73","models":[{"name":"qwen_3_4b.safetensors","url":"https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/text_encoders/qwen_3_4b.safetensors","directory":"text_encoders"}],"enableTabs":false,"tabWidth":65,"tabXOffset":10,"hasSecondTab":false,"secondTabText":"Send Back","secondTabOffset":80,"secondTabWidth":65},"widgets_values":["qwen3vl_8b_int8_convrot.safetensors","qwen_image","default"],"widgets_values_named":{"clip_name":"qwen3vl_8b_int8_convrot.safetensors","type":"qwen_image","device":"default"}},{"id":63,"type":"VAELoader","pos":[659.9998200904802,699.9998629143215],"size":[320,106.65625],"flags":{},"order":1,"mode":0,"inputs":[{"localized_name":"vae_name","name":"vae_name","type":"COMBO","widget":{"name":"vae_name"},"link":null}],"outputs":[{"localized_name":"VAE","name":"VAE","type":"VAE","links":[74]}],"properties":{"Node name for S&R":"VAELoader","cnr_id":"comfy-core","ver":"0.3.73","models":[{"name":"ae.safetensors","url":"https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/vae/ae.safetensors","directory":"vae"}],"enableTabs":false,"tabWidth":65,"tabXOffset":10,"hasSecondTab":false,"secondTabText":"Send Back","secondTabOffset":80,"secondTabWidth":65},"widgets_values":["qwen_image_2.1_vae_bf16.safetensors"],"widgets_values_named":{"vae_name":"qwen_image_2.1_vae_bf16.safetensors"}},{"id":65,"type":"VAEDecode","pos":[1019.9998200904802,319.9999392082668],"size":[225,96],"flags":{},"order":8,"mode":0,"inputs":[{"localized_name":"samples","name":"samples","type":"LATENT","link":73},{"localized_name":"vae","name":"vae","type":"VAE","link":74}],"outputs":[{"localized_name":"IMAGE","name":"IMAGE","type":"IMAGE","slot_index":0,"links":[80]}],"properties":{"Node name for S&R":"VAEDecode","cnr_id":"comfy-core","ver":"0.3.64","enableTabs":false,"tabWidth":65,"tabXOffset":10,"hasSecondTab":false,"secondTabText":"Send Back","secondTabOffset":80,"secondTabWidth":65}},{"id":67,"type":"CLIPTextEncode","pos":[170.00001082534345,290.0000536491848],"size":[410,160],"flags":{},"order":4,"mode":0,"inputs":[{"localized_name":"clip","name":"clip","type":"CLIP","link":79},{"localized_name":"text","name":"text","type":"STRING","widget":{"name":"text"},"link":null}],"outputs":[{"localized_name":"CONDITIONING","name":"CONDITIONING","type":"CONDITIONING","links":[76]}],"properties":{"Node name for S&R":"CLIPTextEncode","cnr_id":"comfy-core","ver":"0.3.73","enableTabs":false,"tabWidth":65,"tabXOffset":10,"hasSecondTab":false,"secondTabText":"Send Back","secondTabOffset":80,"secondTabWidth":65},"widgets_values":["anime RPG game style, cute anime girl with gigantic fennec ears and a big fluffy fox tail with long wavy blonde hair and large blue eyes blonde colored eyelashes wearing a pink sweater a large oversized gold trimmed black winter coat and a long blue maxi skirt and a red scarf, she is sitting beside a campfire in the wilderness at night playing guitar with a milky way galaxy sky"],"widgets_values_named":{"text":"anime RPG game style, cute anime girl with gigantic fennec ears and a big fluffy fox tail with long wavy blonde hair and large blue eyes blonde colored eyelashes wearing a pink sweater a large oversized gold trimmed black winter coat and a long blue maxi skirt and a red scarf, she is sitting beside a campfire in the wilderness at night playing guitar with a milky way galaxy sky"}},{"id":68,"type":"EmptySD3LatentImage","pos":[310.0000489723161,700.0000155022121],"size":[260,168],"flags":{},"order":2,"mode":0,"inputs":[{"localized_name":"width","name":"width","type":"INT","widget":{"name":"width"},"link":null},{"localized_name":"height","name":"height","type":"INT","widget":{"name":"height"},"link":null},{"localized_name":"batch_size","name":"batch_size","type":"INT","widget":{"name":"batch_size"},"link":null}],"outputs":[{"localized_name":"LATENT","name":"LATENT","type":"LATENT","slot_index":0,"links":[78]}],"properties":{"Node name for S&R":"EmptySD3LatentImage","cnr_id":"comfy-core","ver":"0.3.64","enableTabs":false,"tabWidth":65,"tabXOffset":10,"hasSecondTab":false,"secondTabText":"Send Back","secondTabOffset":80,"secondTabWidth":65},"widgets_values":[1024,1024,1],"widgets_values_named":{"width":1024,"height":1024,"batch_size":1}},{"id":69,"type":"ModelSamplingAuraFlow","pos":[220.00001082534345,110.00000596546897],"size":[310,104],"flags":{},"order":6,"mode":0,"inputs":[{"localized_name":"model","name":"model","type":"MODEL","link":83},{"localized_name":"shift","name":"shift","type":"FLOAT","widget":{"name":"shift"},"link":null},{"localized_name":"sampling","name":"sampling","shape":7,"type":"COMBO","widget":{"name":"sampling"},"link":null}],"outputs":[{"localized_name":"MODEL","name":"MODEL","type":"MODEL","slot_index":0,"links":[75]}],"properties":{"Node name for S&R":"ModelSamplingAuraFlow","cnr_id":"comfy-core","ver":"0.3.64","enableTabs":false,"tabWidth":65,"tabXOffset":10,"hasSecondTab":false,"secondTabText":"Send Back","secondTabOffset":80,"secondTabWidth":65},"widgets_values":[3,"flow"],"widgets_values_named":{"shift":3,"sampling":"flow"}},{"id":70,"type":"KSampler","pos":[659.9998200904802,319.9999392082668],"size":[315,341.3125],"flags":{},"order":7,"mode":0,"inputs":[{"localized_name":"model","name":"model","type":"MODEL","link":75},{"localized_name":"positive","name":"positive","type":"CONDITIONING","link":76},{"localized_name":"negative","name":"negative","type":"CONDITIONING","link":82},{"localized_name":"latent_image","name":"latent_image","type":"LATENT","link":78},{"localized_name":"seed","name":"seed","type":"INT","widget":{"name":"seed"},"link":null},{"localized_name":"steps","name":"steps","type":"INT","widget":{"name":"steps"},"link":null},{"localized_name":"cfg","name":"cfg","type":"FLOAT","widget":{"name":"cfg"},"link":null},{"localized_name":"sampler_name","name":"sampler_name","type":"COMBO","widget":{"name":"sampler_name"},"link":null},{"localized_name":"scheduler","name":"scheduler","type":"COMBO","widget":{"name":"scheduler"},"link":null},{"localized_name":"denoise","name":"denoise","type":"FLOAT","widget":{"name":"denoise"},"link":null}],"outputs":[{"localized_name":"LATENT","name":"LATENT","type":"LATENT","slot_index":0,"links":[73]}],"properties":{"Node name for S&R":"KSampler","cnr_id":"comfy-core","ver":"0.3.64","enableTabs":false,"tabWidth":65,"tabXOffset":10,"hasSecondTab":false,"secondTabText":"Send Back","secondTabOffset":80,"secondTabWidth":65},"widgets_values":[42,"fixed",8,1,"res_multistep","simple",1],"widgets_values_named":{"seed":42,"control_after_generate":"fixed","steps":8,"cfg":1,"sampler_name":"res_multistep","scheduler":"simple","denoise":1}},{"id":71,"type":"CLIPTextEncode","pos":[170.00001082534345,520.0000536491848],"size":[405.46875,140],"flags":{},"order":5,"mode":0,"inputs":[{"localized_name":"clip","name":"clip","type":"CLIP","link":81},{"localized_name":"text","name":"text","type":"STRING","widget":{"name":"text"},"link":null}],"outputs":[{"localized_name":"CONDITIONING","name":"CONDITIONING","type":"CONDITIONING","links":[82]}],"properties":{"Node name for S&R":"CLIPTextEncode","cnr_id":"comfy-core","ver":"0.3.73","enableTabs":false,"tabWidth":65,"tabXOffset":10,"hasSecondTab":false,"secondTabText":"Send Back","secondTabOffset":80,"secondTabWidth":65},"widgets_values":["low quality, bad anatomy, extra digits, missing digits, extra limbs, missing limbs"],"widgets_values_named":{"text":"low quality, bad anatomy, extra digits, missing digits, extra limbs, missing limbs"}},{"id":75,"type":"UnetLoaderGGUF","pos":[-128.75710562987018,115.34309036227104],"size":[270,58],"flags":{},"order":3,"mode":0,"inputs":[{"localized_name":"unet_name","name":"unet_name","type":"COMBO","widget":{"name":"unet_name"},"link":null}],"outputs":[{"localized_name":"MODEL","name":"MODEL","type":"MODEL","links":[83]}],"properties":{"Node name for S&R":"UnetLoaderGGUF"},"widgets_values":["qwen-image-2.1-UC-Q4_0.gguf"],"widgets_values_named":{"unet_name":"qwen-image-2.1-UC-Q4_0.gguf"}}],"links":[[73,70,0,65,0,"LATENT"],[74,63,0,65,1,"VAE"],[75,69,0,70,0,"MODEL"],[76,67,0,70,1,"CONDITIONING"],[78,68,0,70,3,"LATENT"],[79,62,0,67,0,"CLIP"],[80,65,0,9,0,"IMAGE"],[81,62,0,71,0,"CLIP"],[82,71,0,70,2,"CONDITIONING"],[83,75,0,69,0,"MODEL"]],"groups":[],"config":{},"extra":{"ds":{"scale":0.7698357679477227,"offset":[456.0322409194524,180.14972852525608]}},"version":0.4}

Additional Context

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

fizzlepoof

2 days ago

I was about to ask why you're using a GGUF on a cuda capable nvidia gpu but then I read the rest of the console log. Carry on 🫡.

The issue you're running in to is that a lot of custom nodes are still being updated to accommodate Qwen21 and it's variants like the ones in this repo. The gguf loaders are among them. See the thread below for a couple of options to fix/upgrade your node .
https://huggingface.co/abenzerps/Qwen-Image-2.1-Uncensored-GGUF/discussions/17#6ab3b53988381d760e7411de

ShardoolShrivastava

2 days ago

Thank you so much man . It worked!!
And my poor 4GB 3050 laptop started ticking like a bomb when I first ran this XD

ShardoolShrivastava changed discussion status to closed 2 days ago

ShardoolShrivastava changed discussion status to open 2 days ago

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment