The image resolution is reflected in the size of the latent image tensor. The size of the latent image is 4x64x64 for 512×512 images only. It is 4x96x64 for a 768×512 portrait image. That’s why it takes longer and more VRAM to generate a larger image.
Since NovArch AI is fine-tuned on 768×512 images, generating images larger than 768×768 could result in duplicate objects, e.g., two master beds in a wide bedroom.
Was this article helpful?
That’s Great!
Thank you for your feedback
Sorry! We couldn't be helpful
Thank you for your feedback
Feedback sent
We appreciate your effort and will try to fix the article