How to use ModelGraphSaver to save output of ModuleDeepCacheSpeedup

[zhangyongyu]

error:

Error occurred when executing ModelGraphSaver:

'UNetModel' object has no attribute '_deployable_module_model'

File "/home/ubuntu/custom-comfyui-deploy/ComfyUI/execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "/home/ubuntu/custom-comfyui-deploy/ComfyUI/execution.py", line 81, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) File "/home/ubuntu/custom-comfyui-deploy/ComfyUI/execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) File "/home/ubuntu/custom-comfyui-deploy/ComfyUI/custom_nodes/onediff_comfy_nodes/extras_nodes/nodes_oneflow_booster.py", line 497, in save_graph save_graph(diffusion_model, filename_prefix, "cuda", subfolder="unet") File "/home/ubuntu/custom-comfyui-deploy/ComfyUI/custom_nodes/onediff_comfy_nodes/modules/oneflow/utils/init.py", line 43, in save_graph str_cls_type = str(type(deploy_module._deployable_module_model._torch_module)) File "/home/ubuntu/miniconda3/envs/cf/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1709, in getattr raise AttributeError(f"'{type(self).name}' object has no attribute '{name}'")

[ccssu]

ModelGraphSaver 已经不维护，使用新的 load checkpoint - onediff 会自动缓存图。

deepcache_save_unet.json