# DIAMOND: Directed Inference for Artifact Mitigation in Flow Matching Models

arXiv: https://arxiv.org/abs/2602.00883 · HTML: https://mlsanity.com/paper/2602.00883/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Flow matching, time series and science, one of 14 directions in Diffusion models.
- Builds on 24 of its 24 references that are in the map.
- First posted on arXiv 31 Jan 2026.

## Placed in

- Diffusion models / [Flow matching, time series and science](https://mlsanity.com/diffusion/flow-matching-time-series-and-science/)

## Builds on (most cited first, 24 of 24)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023)
- [Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2305.01569/) (2023)
- [Muse: Text-To-Image Generation via Masked Generative Transformers](https://mlsanity.com/paper/2301.00704/) (2023)
- [CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers](https://mlsanity.com/paper/2204.14217/) (2022)
- [Perception Prioritized Training of Diffusion Models](https://mlsanity.com/paper/2204.00227/) (2022)
- [Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Models](https://mlsanity.com/paper/2404.07724/) (2024)
- [TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition](https://mlsanity.com/paper/2307.12493/) (2023)
- [Self-correcting LLM-controlled Diffusion Models](https://mlsanity.com/paper/2311.16090/) (2023)
- [Perceptual Artifacts Localization for Image Synthesis Tasks](https://mlsanity.com/paper/2310.05590/) (2023)
- [HandRefiner: Refining Malformed Hands in Generated Images by Diffusion-based Conditional Inpainting](https://mlsanity.com/paper/2311.17957/) (2023)
- [BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inference](https://mlsanity.com/paper/2310.11142/) (2023)
- [Classifier-free Guidance with Adaptive Scaling](https://mlsanity.com/paper/2502.10574/) (2025)
- [Focus-N-Fix: Region-Aware Fine-Tuning for Text-to-Image Generation](https://mlsanity.com/paper/2501.06481/) (2025)
- [Temporal Score Analysis for Understanding and Correcting Diffusion Artifacts](https://mlsanity.com/paper/2503.16218/) (2025)
- [GeoGuide: Geometric guidance of diffusion models](https://mlsanity.com/paper/2407.12889/) (2024)
- [DiffDoctor: Diagnosing Image Diffusion Models Before Treating](https://mlsanity.com/paper/2501.12382/) (2025)
- [Self-Adaptive Reality-Guided Diffusion for Artifact-Free Super-Resolution](https://mlsanity.com/paper/2403.16643/) (2024)
- [HandCraft: Anatomically Correct Restoration of Malformed Hands in Diffusion Generated Images](https://mlsanity.com/paper/2411.04332/) (2024)
- [Synthesizing Artifact Dataset for Pixel-level Detection](https://mlsanity.com/paper/2509.19589/) (2025)
- [Refining Visual Artifacts in Diffusion Models via Explainable AI-based Flaw Activation Maps](https://mlsanity.com/paper/2512.08774/) (2025)

## Built on by (most cited first, 1 of 1)

- [FluxFlow: Conservative Flow-Matching for Astronomical Image Super-Resolution](https://mlsanity.com/paper/2605.03749/) (2026)

## Abstract (arXiv)

Despite impressive results from recent text-to-image models like FLUX, visual and anatomical artifacts remain a significant hurdle for practical and professional use. Existing methods for artifact reduction, typically work in a post-hoc manner, consequently failing to intervene effectively during the core image formation process. Notably, current techniques require problematic and invasive modifications to the model weights, or depend on a computationally expensive and time-consuming process of regional refinement. To address these limitations, we propose DIAMOND, a training-free method that applies trajectory correction to mitigate artifacts during inference. By reconstructing an estimate of the clean sample at every step of the generative trajectory, DIAMOND actively steers the generation process away from latent states that lead to artifacts. Furthermore, we extend the proposed method to standard Diffusion Models, demonstrating that DIAMOND provides a robust, zero-shot path to high-fidelity, artifact-free image synthesis without the need for additional training or weight modifications in modern generative architectures. Code is available at https://gmum.github.io/DIAMOND/