SD3 models won't work have updated everything, re downloaded checkpoints and clip models
SD 3 models won't work I have updated everything, re downloaded checkpoints and clip models. Help get these two different errors while trying to run sd3_medium and sd3_medium_incl_clips_t5xxlfp8. Using basic and upscaling workflow no difference.
I tried running the sd3_medium_incl_clips but bypassing the TripleCLIPLoader node in both the basic and upscaling workflow. Should all be standard.
This error I get with sd3_medium_incl_clips_t5xxlfp8
Error occurred when executing CheckpointLoaderSimple:
Error while deserializing header: InvalidHeaderDeserialization
File "I:\New folder (4)\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "I:\New folder (4)\ComfyUI_windows_portable\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 "I:\New folder (4)\ComfyUI_windows_portable\ComfyUI\execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "I:\New folder (4)\ComfyUI_windows_portable\ComfyUI\nodes.py", line 516, in load_checkpoint
out = comfy.sd.load_checkpoint_guess_config(ckpt_path, output_vae=True, output_clip=True, embedding_directory=folder_paths.get_folder_paths("embeddings"))
File "I:\New folder (4)\ComfyUI_windows_portable\ComfyUI\comfy\sd.py", line 464, in load_checkpoint_guess_config
sd = comfy.utils.load_torch_file(ckpt_path)
File "I:\New folder (4)\ComfyUI_windows_portable\ComfyUI\comfy\utils.py", line 14, in load_torch_file
sd = safetensors.torch.load_file(ckpt, device=device.type)
File "I:\New folder (4)\ComfyUI_windows_portable\python_embeded\lib\site-packages\safetensors\torch.py", line 309, in load_file
with safe_open(filename, framework="pt", device=device) as f:
This error I get with sd3_medium mode:
Error occurred when executing TripleCLIPLoader:
Error while deserializing header: InvalidHeaderDeserialization
File "I:\New folder (4)\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "I:\New folder (4)\ComfyUI_windows_portable\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 "I:\New folder (4)\ComfyUI_windows_portable\ComfyUI\execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "I:\New folder (4)\ComfyUI_windows_portable\ComfyUI\comfy_extras\nodes_sd3.py", line 21, in load_clip
clip = comfy.sd.load_clip(ckpt_paths=[clip_path1, clip_path2, clip_path3], embedding_directory=folder_paths.get_folder_paths("embeddings"))
File "I:\New folder (4)\ComfyUI_windows_portable\ComfyUI\comfy\sd.py", line 378, in load_clip
clip_data.append(comfy.utils.load_torch_file(p, safe_load=True))
File "I:\New folder (4)\ComfyUI_windows_portable\ComfyUI\comfy\utils.py", line 14, in load_torch_file
sd = safetensors.torch.load_file(ckpt, device=device.type)
File "I:\New folder (4)\ComfyUI_windows_portable\python_embeded\lib\site-packages\safetensors\torch.py", line 309, in load_file
with safe_open(filename, framework="pt", device=device) as f:
Doing a git pull instead enough, you also need to:
pip install --upgrade torch torchvision torchaudio -r requirements.txt
Got this error when i thought i had the clip models downloaded but they were just 1k in length...had to manually download with LFS