madebyollin

/

sdxl-vae-fp16-fix

like 502

I have downloaded your sdxl_vae.safetensors file and placed it into the correct folder for my installation. However, when I select the vae from my VAE droplist, I get the following error message in my CMD window:

Applying attention optimization: xformers... done.
VAE weights loaded.
Loading VAE weights specified in settings: H:\Stable Diffusion - Automatic1111\sd.webui\webui\models\VAE\sdXL_vae.safetensors
changing setting sd_vae to sdXL_vae.safetensors: SafetensorError
Traceback (most recent call last):
File "H:\Stable Diffusion - Automatic1111\sd.webui\webui\modules\shared.py", line 633, in set
self.data_labels[key].onchange()
File "H:\Stable Diffusion - Automatic1111\sd.webui\webui\modules\call_queue.py", line 14, in f
res = func(*args, **kwargs)
File "H:\Stable Diffusion - Automatic1111\sd.webui\webui\webui.py", line 239, in
shared.opts.onchange("sd_vae", wrap_queued_call(lambda: modules.sd_vae.reload_vae_weights()), call=False)
File "H:\Stable Diffusion - Automatic1111\sd.webui\webui\modules\sd_vae.py", line 204, in reload_vae_weights
load_vae(sd_model, vae_file, vae_source)
File "H:\Stable Diffusion - Automatic1111\sd.webui\webui\modules\sd_vae.py", line 142, in load_vae
vae_dict_1 = load_vae_dict(vae_file, map_location=shared.weight_load_location)
File "H:\Stable Diffusion - Automatic1111\sd.webui\webui\modules\sd_vae.py", line 120, in load_vae_dict
vae_ckpt = sd_models.read_state_dict(filename, map_location=map_location)
File "H:\Stable Diffusion - Automatic1111\sd.webui\webui\modules\sd_models.py", line 253, in read_state_dict
pl_sd = safetensors.torch.load_file(checkpoint_file, device=device)
File "H:\Stable Diffusion - Automatic1111\sd.webui\system\python\lib\site-packages\safetensors\torch.py", line 259, in load_file
with safe_open(filename, framework="pt", device=device) as f:
safetensors_rust.SafetensorError: Error while deserializing header: HeaderTooLarge

Have I done something wrong? Do I need to update something else before I can use this VAE?|