I got ComfyUI and Wan 2.2 going but my container crashes on this last step using the ti2v workflow. Is it not enough to have 16GB of RAM available? I have a 4080 Super, this shouldn't crash yeah? I have CUDA and everything installed in the container.

>got prompt
>Using pytorch attention in VAE
>Using pytorch attention in VAE
>VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16
>Requested to load Wan
>VAE loaded completely 8961.125 >1344.0869674682617 True
>Requested to load WanTE
>Model loaded completely 9.5367431640625e+25 10835.4765625 True
>CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cuda:0, dtype: torch.float16
>model_type FLOW
>Requested to load WAN22
crash