"Requested to load AutoencoderKL"

[ShadyRaion]

Describe the bug

I'm tryna generate images but it always crashes when it gets to this line. I'm no expert when it comes to stable diffusion so i don't really know what's going..

Reproduction

got prompt
model weight dtype torch.float16, manual cast: None
model_type EPS
Using pytorch attention in VAE
Using pytorch attention in VAE
VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16
Requested to load SDXLClipModel
loaded completely 9.5367431640625e+25 1560.802734375 True
CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cuda:0, dtype: torch.float16
Requested to load SDXLClipModel
Requested to load ControlNet
Requested to load SDXL
loaded completely 5637.675 2396.797637939453 True
loaded partially 3240.872479248047 3240.87158203125 0
100%|██████████████████████████████████████████████████████████████████████████████████| 30/30 [01:15<00:00, 2.52s/it]
Requested to load AutoencoderKL

C:\AI\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable>pause
Press any key to continue . . .

Logs

System Info

ComfyUI version: 0.3.49
ComfyUI frontend version: 1.23.4
Python version: 3.12.10
Platform: Windows
GPU: RTX 4060
RAM: 16GB
VRAM: 8GB

Who can help?

No response

[asomoza]

Hi, you're using ComfyUI and by default it doesn't use diffusers as a backend, you should ask in the corresponding repository about the error you're getting.