# Few-shot Defect Image Generation based on Consistency Modeling arXiv: https://arxiv.org/abs/2408.00372 ยท HTML: https://mlsanity.com/paper/2408.00372/ ## Key facts - Cited by 8 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 30 of its 40 references that are in the map. - First posted on arXiv 1 Aug 2024. ## 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, 30 of 30) - [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021) - [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020) - [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021) - [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021) - [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022) - [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022) - [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022) - [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023) - [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019) - [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022) - [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022) - [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022) - [Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2301.13826/) (2023) - [Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis](https://mlsanity.com/paper/2212.05032/) (2022) - [Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2305.16322/) (2023) - [WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation](https://mlsanity.com/paper/2303.14814/) (2023) - [VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance](https://mlsanity.com/paper/2204.08583/) (2022) - [AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection](https://mlsanity.com/paper/2310.18961/) (2023) - [LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation](https://mlsanity.com/paper/2303.17189/) (2023) - [DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models](https://mlsanity.com/paper/2303.11681/) (2023) - [Natural Synthetic Anomalies for Self-Supervised Anomaly Detection and Localization](https://mlsanity.com/paper/2109.15222/) (2021) - [AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model](https://mlsanity.com/paper/2312.05767/) (2023) - [DSR -- A dual subspace re-projection network for surface anomaly detection](https://mlsanity.com/paper/2208.01521/) (2022) - [XingGAN for Person Image Generation](https://mlsanity.com/paper/2007.09278/) (2020) - [Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspection](https://mlsanity.com/paper/2103.15158/) (2021) - [Few-Shot Defect Image Generation via Defect-Aware Feature Manipulation](https://mlsanity.com/paper/2303.02389/) (2023) - [CONFIG: Controllable Neural Face Image Generation](https://mlsanity.com/paper/2005.02671/) (2020) - [SinDDM: A Single Image Denoising Diffusion Model](https://mlsanity.com/paper/2211.16582/) (2022) - [MaskDiffusion: Boosting Text-to-Image Consistency with Conditional Mask](https://mlsanity.com/paper/2309.04399/) (2023) - [Defect Spectrum: A Granular Look of Large-Scale Defect Datasets with Rich Semantics](https://mlsanity.com/paper/2310.17316/) (2023) ## Built on by (most cited first, 8 of 8) - [A Survey on Industrial Anomaly Synthesis](https://mlsanity.com/paper/2502.16412/) (2025) - [Exploring Few-Shot Defect Segmentation in General Industrial Scenarios with Metric Learning and Vision Foundation Models](https://mlsanity.com/paper/2502.01216/) (2025) - [STAGE: Segmentation-oriented Industrial Anomaly Synthesis via Graded Diffusion with Explicit Mask Alignment](https://mlsanity.com/paper/2509.06693/) (2025) - [ASBench: Image Anomalies Synthesis Benchmark for Anomaly Detection](https://mlsanity.com/paper/2510.07927/) (2025) - [FAST: Foreground-aware Diffusion with Accelerated Sampling Trajectory for Segmentation-oriented Anomaly Synthesis](https://mlsanity.com/paper/2509.20295/) (2025) - [DeltaDeno: Zero-Shot Anomaly Generation via Delta-Denoising Attribution](https://mlsanity.com/paper/2511.16920/) (2025) - [FuDU: A Fuzzy Dual-dimensional Uncertainty Framework for Streaming Active Learning in Industrial Defect Detection](https://mlsanity.com/paper/2609.02212/) (2026) - [FLASH: A "Generate Once, Synthesize Many" Framework for Synthetic Anomaly Generation in Industrial Anomaly Detection](https://mlsanity.com/paper/2609.37314/) (2026) ## Abstract (arXiv) Image generation can solve insufficient labeled data issues in defect detection. Most defect generation methods are only trained on a single product without considering the consistencies among multiple products, leading to poor quality and diversity of generated results. To address these issues, we propose DefectDiffu, a novel text-guided diffusion method to model both intra-product background consistency and inter-product defect consistency across multiple products and modulate the consistency perturbation directions to control product type and defect strength, achieving diversified defect image generation. Firstly, we leverage a text encoder to separately provide consistency prompts for background, defect, and fusion parts of the disentangled integrated architecture, thereby disentangling defects and normal backgrounds. Secondly, we propose the double-free strategy to generate defect images through two-stage perturbation of consistency direction, thereby controlling product type and defect strength by adjusting the perturbation scale. Besides, DefectDiffu can generate defect mask annotations utilizing cross-attention maps from the defect part. Finally, to improve the generation quality of small defects and masks, we propose the adaptive attention-enhance loss to increase the attention to defects. Experimental results demonstrate that DefectDiffu surpasses state-of-the-art methods in terms of generation quality and diversity, thus effectively improving downstream defection performance. Moreover, defect perturbation directions can be transferred among various products to achieve zero-shot defect generation, which is highly beneficial for addressing insufficient data issues. The code are available at https://github.com/FFDD-diffusion/DefectDiffu.