FastHunyuan?
Any chance you can do the GGUF Quants for FastHunyuan? Macs dont support fp8 so need gguf :S
just upgraded our node; you could use the new gguf convertor (alpha) to convert safetensors to gguf under comfyui now; see the steps; help yourself
I tried using the GGUF Convertor (Alpha) node but it gave me an error saying the safetensors file had a unknown architecture. Tried to convert "hunyuan_video_FastVideo_720_fp8_e4m3fn.safetensors" in the "Kijai/HunyuanVideo_comfy" repository. Am I doing something wrong?
got prompt
!!! Exception during processing !!! Unknown model architecture!
Traceback (most recent call last):
File "/content/ComfyUI/execution.py", line 327, 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 "/content/ComfyUI/execution.py", line 202, 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 "/content/ComfyUI/execution.py", line 174, in _map_node_over_list
process_inputs(input_dict, i)
File "/content/ComfyUI/execution.py", line 163, in process_inputs
results.append(getattr(obj, func)(**inputs))
File "/content/ComfyUI/custom_nodes/gguf/nodes.py", line 634, in save
writer, state_dict, model_arch = load_model(path)
File "/content/ComfyUI/custom_nodes/gguf/nodes.py", line 518, in load_model
model_arch = detect_arch(state_dict)
File "/content/ComfyUI/custom_nodes/gguf/nodes.py", line 497, in detect_arch
assert model_arch is not None, "Unknown model architecture!"
AssertionError: Unknown model architecture!