I get a error
[INFO] Prompt executed in 0.07 seconds
[INFO] got prompt
[ERROR] !!! Exception during processing !!! This model is not currently supported - (Unknown model architecture!)
[ERROR] Traceback (most recent call last):
File "E:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-GGUF\loader.py", line 103, in gguf_sd_loader
arch_str = detect_arch(set(val[0] for val in tensors)).arch
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-GGUF\tools\convert.py", line 169, in detect_arch
assert model_arch is not None, "Unknown model architecture!"
^^^^^^^^^^^^^^^^^^^^^^
AssertionError: Unknown model architecture!
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "E:\ComfyUI_windows_portable\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 "E:\ComfyUI_windows_portable\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 "E:\ComfyUI_windows_portable\ComfyUI\execution.py", line 326, in _async_map_node_over_list
await process_inputs(input_dict, i)
File "E:\ComfyUI_windows_portable\ComfyUI\execution.py", line 314, in process_inputs
result = f(**inputs)
^^^^^^^^^^^
File "E:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-GGUF\nodes.py", line 169, in load_unet
sd, extra = gguf_sd_loader(unet_path)
^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-GGUF\loader.py", line 105, in gguf_sd_loader
raise ValueError(f"This model is not currently supported - ({e})")
ValueError: This model is not currently supported - (Unknown model architecture!)
You have two easy ways to resolve this:
Option 1 (Recommended - Use the maintained fork):
leejet (author of stable-diffusion.cpp) actively maintains ComfyUI-GGUF and just added native Qwen-Image 2.1 support yesterday (commit f912d5e5):
cd ComfyUI/custom_nodes
rm -rf ComfyUI-GGUF
git clone https://github.com/leejet/ComfyUI-GGUF
Restart ComfyUI and the model.
Option 2 (Manual 30-second fix for your existing install):
If you prefer not to reinstall the node, open: ComfyUI/custom_nodes/ComfyUI-GGUF/tools/convert.py
Right above arch_list = [...] (around line 150), add:
class ModelQwenImage(ModelTemplate):
arch = "qwen_image"
keys_detect = [
("img_in.weight", "modulation.1.weight"),
]
And add ModelQwenImage to the end of the arch_list array:
arch_list = [ModelFlux, ModelSD3, ModelAura, ModelHiDream, CosmosPredict2,
ModelLTXV, ModelHyVid, ModelWan, ModelSDXL, ModelSD1, ModelLumina2, ModelQwenImage]
Save and restart ComfyUI.