Error occurred when executing KSampler (Efficient): "An xformers bug"

[frukostkungen]

I've tried everything I can think of for the past couple days to get this to work, but still run into this same error.

I actually have the --disable-xformers argument, so I don't know why the "workaround" is mentioned in the error.

Windows 11 Nvidia 3090 RTX

Error occurred when executing KSampler (Efficient):

An xformers bug was encountered in AnimateDiff - this is unexpected, report this to Kosinkadink/ComfyUI-AnimateDiff-Evolved repo as an issue, and a workaround for now is to run ComfyUI with the --disable-xformers argument.

File "C:\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\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 "C:\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 "C:\ComfyUI_windows_portable\ComfyUI\custom_nodes\efficiency-nodes-comfyui\efficiency_nodes.py", line 713, in sample
samples, images, gifs, preview = process_latent_image(model, seed, steps, cfg, sampler_name, scheduler,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\ComfyUI_windows_portable\ComfyUI\custom_nodes\efficiency-nodes-comfyui\efficiency_nodes.py", line 601, in process_latent_image
samples = KSampler().sample(latent_upscale_model, hires_seed, hires_steps, cfg, sampler_name, scheduler,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1344, in sample
return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1314, in common_ksampler
samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-AnimateDiff-Evolved\animatediff\sampling.py", line 382, in motion_sample
latents = wrap_function_to_inject_xformers_bug_info(orig_comfy_sample)(model, noise, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-AnimateDiff-Evolved\animatediff\utils_model.py", line 380, in wrapped_function
raise RuntimeError(f"An xformers bug was encountered in AnimateDiff - this is unexpected, \

[frukostkungen]

So in the end this was user error. I somehow had the wrong version of diffusion_pytorch_model.safetensors VAE

I got the correct SD 1.4 version from here https://huggingface.co/CompVis/stable-diffusion-v1-4/tree/main/vae

I discovered this when I noticed a lot of missing VAE keys when queuing the graph

Missing VAE keys ['encoder.conv_in.weight', 'encoder.conv_in.bias', 'encoder.down.0.block.0.norm1.weight',
'encoder.down.0.block.0.norm1.bias', 'encoder.down.0.block.0.conv1.weight', 'encoder.down.0.block.0.conv1.bias',
'encoder.down.0.block.0.norm2.weight', 'encoder.down.0.block.0.norm2.bias', 'encoder.down.0.block.0.conv2.weight',
'encoder.down.0.block.0.conv2.bias', 'encoder.down.0.block.1.norm1.weight', 'encoder.down.0.block.1.norm1.bias',
'encoder.down.0.block.1.conv1.weight', 'encoder.down.0.block.1.conv1.bias', 'encoder.down.0.block.1.norm2.weight',
'encoder.down.0.block.1.norm2.bias'