From Diffusion to One-Step Generation: A Comparative Study of Flow-Based Models with Application to Image Inpainting
By: Umang Agarwal, Rudraksh Sangore, Sumit Laddha
Potential Business Impact:
Makes pictures from scratch in one step.
We present a comprehensive comparative study of three generative modeling paradigms: Denoising Diffusion Probabilistic Models (DDPM), Conditional Flow Matching (CFM), and MeanFlow. While DDPM and CFM require iterative sampling, MeanFlow enables direct one-step generation by modeling the average velocity over time intervals. We implement all three methods using a unified TinyUNet architecture (<1.5M parameters) on CIFAR-10, demonstrating that CFM achieves an FID of 24.15 with 50 steps, significantly outperforming DDPM (FID 402.98). MeanFlow achieves FID 29.15 with single-step sampling -- a 50X reduction in inference time. We further extend CFM to image inpainting, implementing mask-guided sampling with four mask types (center, random bbox, irregular, half). Our fine-tuned inpainting model achieves substantial improvements: PSNR increases from 4.95 to 8.57 dB on center masks (+73%), and SSIM improves from 0.289 to 0.418 (+45%), demonstrating the effectiveness of inpainting-aware training.
Similar Papers
Efficiency vs. Fidelity: A Comparative Analysis of Diffusion Probabilistic Models and Flow Matching on Low-Resource Hardware
Machine Learning (CS)
Makes AI create pictures much faster on phones.
Decoupled MeanFlow: Turning Flow Models into Flow Maps for Accelerated Sampling
CV and Pattern Recognition
Makes AI create pictures much faster.
Improved Mean Flows: On the Challenges of Fastforward Generative Models
CV and Pattern Recognition
Makes AI create pictures faster and better.