Auto-Photoshop-StableDiffusion-Plugin icon indicating copy to clipboard operation
Auto-Photoshop-StableDiffusion-Plugin copied to clipboard

vae error, not vae list,unable generate,comfy ui

Open YmStrip opened this issue 8 months ago • 1 comments

Prompt executed in 1.98 seconds got prompt 100%|██████████████████████████████████████████████████████████████████████████████████| 15/15 [00:01<00:00, 7.91it/s] !!! Exception during processing!!! 'VAE' object has no attribute 'vae_dtype' Traceback (most recent call last): File "D:\ai\ComfyUI_windows_portable_nightly_pytorch\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ai\ComfyUI_windows_portable_nightly_pytorch\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 "D:\ai\ComfyUI_windows_portable_nightly_pytorch\ComfyUI\execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ai\ComfyUI_windows_portable_nightly_pytorch\ComfyUI\nodes.py", line 268, in decode return (vae.decode(samples["samples"]), ) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ai\ComfyUI_windows_portable_nightly_pytorch\ComfyUI\comfy\sd.py", line 293, in decode memory_used = self.memory_used_decode(samples_in.shape, self.vae_dtype) ^^^^^^^^^^^^^^ AttributeError: 'VAE' object has no attribute 'vae_dtype'

Prompt executed in 2.02 seconds everything works fine in webui and comfyui(direct generation)

but when you start ps for the first time, it accidentally refreshes the list of available vae, and when you click refresh again it disappears, and the error occurs regardless of whether or not a vae is selected.

ComfyUI Revision: 2216 [91542d4f] | Released on '2024-05-28'

some times

for input of size 409600 ..... ERROR lora diffusion_model.output_blocks.5.1.proj_out.weight shape '[1280, 1280, 1, 1]' is invalid for input of size 409600 100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [00:03<00:00, 5.90it/s] WARNING: No VAE weights detected, VAE not initalized. .....

  • KSampler 3:
    • Failed to convert an input value to a INT value: steps, None, int() argument must be a string, a bytes-like object or a real number, not 'NoneType' Output will be ignored .... After that, it's all like this. !!! Exception during processing!!! 'VAE' object has no attribute 'vae_dtype'

happen: txt2img(yes) img2img(yes) inpaint(yes) outpaint(yes)

Thanks

YmStrip avatar Jun 20 '24 23:06 YmStrip