Score: 1

From Diffusion to One-Step Generation: A Comparative Study of Flow-Based Models with Application to Image Inpainting

Published: November 26, 2025 | arXiv ID: 2511.21215v1

By: Umang Agarwal, Rudraksh Sangore, Sumit Laddha

Potential Business Impact:

Makes pictures from scratch in one step.

Business Areas:
Simulation Software

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.

Country of Origin
🇮🇳 India

Repos / Data Links

Page Count
8 pages

Category
Computer Science:
CV and Pattern Recognition