无需训练即可消除生成图像中的伪影，提升视觉质量。
DIAMOND: Directed Inference for Artifact Mitigation in Flow Matching Models
- 通过轨迹修正，在生成过程中实时纠正潜在的伪影路径。
- 在FLUX等模型上实现零样本去伪影，无需修改权重或额外训练。
- 适用于流匹配与扩散模型，适合追求高质量图像的开发者使用。
尽管FLUX等近期文本到图像模型取得了令人瞩目的成果，但视觉和解剖伪影仍是其在实际与专业场景中应用的重大障碍。现有去伪影方法多为事后处理，难以在核心图像生成过程中有效干预。尤其当前技术往往需要对模型权重进行问题重重且侵入性的修改，或依赖计算成本高、耗时长的区域精修过程。为此，我们提出DIAMOND——一种无需训练的方法，通过在推理阶段对生成轨迹进行修正来缓解伪影。该方法在每一步重构干净样本的估计值，主动引导生成过程避开导致伪影的潜在状态。此外，我们将该方法扩展至标准扩散模型，证明DIAMOND可在现代生成架构中提供鲁棒的零样本路径，实现高保真、无伪影图像合成，且无需额外训练或权重修改。代码已开源：https://gmum.github.io/DIAMOND/
原文摘要 · Abstract (English)
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/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。