mlsanityData to 7 Oct 2026

Comparative Analysis of Generative Models: Enhancing Image Synthesis with VAEs, GANs, and Stable Diffusion

arXiv 2408.08751 ↗First posted 16 Aug 2024cs.CV eess.IVcited by 7

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

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.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 19 of its 31 references that are in the map. First posted on arXiv 16 Aug 2024.

Builds on

19 of 31 references.

Closest ancestors · 3

Same direction, newest first

  1. 2022Diffusion Models in Vision: A Survey10 Sep
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  3. 2021Diffusion Models Beat GANs on Image Synthesis11 May

Other references · 16

  1. 2014Conditional Generative Adversarial Netscited by 2,152
  2. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  3. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,903
  4. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  5. 2021Palette: Image-to-Image Diffusion Modelscited by 1,296
  6. 2022Denoising Diffusion Restoration Modelscited by 951
  7. 2021Blended Diffusion for Text-driven Editing of Natural Imagescited by 924
  8. 2016Tutorial on Variational Autoencoderscited by 404
  9. 2023Inpaint Anything: Segment Anything Meets Image Inpaintingcited by 233
  10. 2015Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networkscited by 214
  11. 2022Pretraining is All You Need for Image-to-Image Translationcited by 160
  12. 2021EditGAN: High-Precision Semantic Image Editingcited by 156
4 more
  1. 2018BAGAN: Data Augmentation with Balancing GANcited by 90
  2. 2019A Survey on Face Data Augmentationcited by 23
  3. 2022DrawingInStyles: Portrait Image Generation and Editing with Spatially Conditioned StyleGANcited by 18
  4. 2024Recursive InPainting (RIP): how much information is lost under recursive inferences?cited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 5; 2026: 1.

7 papers.

  1. 2025A Probabilistic Approach to Wildfire Spread Prediction Using a Denoising Diffusion Surrogate Modelcited by 10
  2. 2024PGCS: Physical Law embedded Generative Cloud Synthesis in Remote Sensing Imagescited by 0
  3. 2025MM-DADM: Multimodal Drug-Aware Diffusion Model for Virtual Clinical Trialscited by 0
  4. 2025FedRecon: Missing Modality Reconstruction in Heterogeneous Distributed Environmentscited by 0
  5. 2025Diffusion Models at the Drug Discovery Frontier: A Review on Generating Small Molecules versus Therapeutic Peptidescited by 0
  6. 2025Unified Control for Inference-Time Guidance of Denoising Diffusion Modelscited by 0
  7. 2026Structural MRI Synthesis for Alzheimer's Disease via Conditional Diffusion on Anatomical Maskscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Generative AI in Depth: A Survey of Recent Advances, Model Variants, and Real-World Applications
  2. 2025Generative AI for Vision: A Comprehensive Study of Frameworks and Applications
  3. 2023Conditional Image Generation with Pretrained Generative Model
  4. 2024Deep Generative Models for 3D Medical Image Synthesis
  5. 2022DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latents
  6. 2022Progressive Distillation for Fast Sampling of Diffusion Models
  7. 2025Image Inversion: A Survey from GANs to Diffusion and Beyond
  8. 2025Revisiting Diffusion Models: From Generative Pre-training to One-Step Generation