Circular tiling

[stduhpf]

Vae tiling was not working nicely with --circular flags. This PR aims at improving that by making the tiling circular instead of the VAE itself.

Example with sd-cli.exe --diffusion-model ..\ComfyUI\models\unet\Flux\klein\flux-2-klein-9b-Q6_K.gguf --vae ..\ComfyUI\models\vae\flux\Flux.2-VAE.safetensors --llm ..\ComfyUI\models\clip\llms\Qwen3-8b.Q4_K_XL.gguf --cfg-scale 1.0 -p '360 HDRI panorama image, capturing a wide, 360-degree view of living room. Intimate atmosphere<lora:Klein_9B - HDRI_360_panoramic:1.3>' --scheduler smoothstep --steps 8 -W 1024 -H 512 --rng cpu --lora-model-dir ..\ComfyUI\models\loras\flux\klein9\ --circularx --vae-tiling --vae-tile-size 16

master	no circular VAE (1cdcdd5)	this PR

(lora: https://civitai.green/models/2413837/hdri-flux2klein-9b)

Example with sd-cli.exe --diffusion-model ..\ComfyUI\models\unet\Flux\klein\flux-2-klein-9b-Q6_K.gguf --vae ..\ComfyUI\models\vae\flux\Flux.2-VAE.safetensors --llm ..\ComfyUI\models\clip\llms\Qwen3-8b.Q4_K_XL.gguf --cfg-scale 1.0-p 'Aerial view of a very busy city' --preview proj --steps 8 -W 512 -H 512 --rng cpu --circular --scheduler smoothstep - -vae-tiling-vae-tile-size 16

master	this PR

[GreenShadows]

It is better not to implement this if it causes performance loss with active tiling, which is naturally used in all low-end systems with little VRAM.

[stduhpf]

it causes performance loss with active tiling, which is naturally used in all low-end systems with little VRAM.

Only when both tiling and circular are enabled. If either is disabled the performance is basically unchanged.