Comparative Analysis of Generative Models: Enhancing Image Synthesis with VAEs, GANs, and Stable Diffusion
It provides a comparative analysis to help select generative models for various applications, but it is incremental as it reviews existing methods without introducing new ones.
This paper compared VAEs, GANs, and Stable Diffusion for image synthesis, finding that Stable Diffusion with Grounding DINO and Grounded SAM improves accuracy through segmentation and inpainting, though it is computationally demanding.
This paper examines three major generative modelling frameworks: Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), and Stable Diffusion models. VAEs are effective at learning latent representations but frequently yield blurry results. GANs can generate realistic images but face issues such as mode collapse. Stable Diffusion models, while producing high-quality images with strong semantic coherence, are demanding in terms of computational resources. Additionally, the paper explores how incorporating Grounding DINO and Grounded SAM with Stable Diffusion improves image accuracy by utilising sophisticated segmentation and inpainting techniques. The analysis guides on selecting suitable models for various applications and highlights areas for further research.