# Towards Anatomically Plausible Human Image Generation via Synthetic Localized Preferences arXiv: https://arxiv.org/abs/2605.25759 ยท HTML: https://mlsanity.com/paper/2605.25759/ ## Key facts - Cited by 1 papers in the map (data through 14 Oct 2026). - Placed in Diffusion and multimodal model alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation. - Builds on 43 of its 46 references that are in the map. - First posted on arXiv 25 May 2026. ## Placed in - LLM alignment / RLHF / preference optimisation / [Diffusion and multimodal model alignment](https://mlsanity.com/alignment/diffusion-and-multimodal-model-alignment/) ## Builds on (most cited first, 30 of 43) - [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) - [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022) - [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019) - [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021) - [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020) - [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020) - [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023) - [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022) - [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023) - [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024) - [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022) - [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025) - [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022) - [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020) - [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025) - [Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2305.01569/) (2023) - [Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks](https://mlsanity.com/paper/2401.14159/) (2024) - [A General Theoretical Paradigm to Understand Learning from Human Preferences](https://mlsanity.com/paper/2310.12036/) (2023) - [Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis](https://mlsanity.com/paper/2306.09341/) (2023) - [Diffusion Model Alignment Using Direct Preference Optimization](https://mlsanity.com/paper/2311.12908/) (2023) - [The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only](https://mlsanity.com/paper/2306.01116/) (2023) - [Effective Whole-body Pose Estimation with Two-stages Distillation](https://mlsanity.com/paper/2307.15880/) (2023) - [Human Preference Score: Better Aligning Text-to-Image Models with Human Preference](https://mlsanity.com/paper/2303.14420/) (2023) - [HPSv3: Towards Wide-Spectrum Human Preference Score](https://mlsanity.com/paper/2508.03789/) (2025) - [Rich Human Feedback for Text-to-Image Generation](https://mlsanity.com/paper/2312.10240/) (2023) - [HumanSD: A Native Skeleton-Guided Diffusion Model for Human Image Generation](https://mlsanity.com/paper/2304.04269/) (2023) - [HyperHuman: Hyper-Realistic Human Generation with Latent Structural Diffusion](https://mlsanity.com/paper/2310.08579/) (2023) - [CosmicMan: A Text-to-Image Foundation Model for Humans](https://mlsanity.com/paper/2404.01294/) (2024) - [HumanRefiner: Benchmarking Abnormal Human Generation and Refining with Coarse-to-fine Pose-Reversible Guidance](https://mlsanity.com/paper/2407.06937/) (2024) ## Built on by (most cited first, 1 of 1) - [MPIE-Bench: Benchmarking Anatomically Plausible Multi-Person Interaction Editing](https://mlsanity.com/paper/2607.27616/) (2026) ## Abstract (arXiv) Large-scale text-to-image foundation models have achieved remarkable visual realism, yet generating human images with correct anatomical structures remains challenging. Existing approaches enforce anatomical constraints through part-specific modules or localized loss weighting during supervised fine-tuning on high-quality human photos, but such datasets are limited and often provide ambiguous optimization signals due to confounding factors such as lighting, pose, and background. Preference-based alignment offers an alternative, but standard Direct Preference Optimization (DPO) treats all pixels equally and therefore fails to exploit the localized nature of anatomical artifacts. To address this, we propose the framework of Alignment via Synthetic Anatomical Preference (ASAP), which constructs controlled preference pairs through a localized degradation mechanism applied to high-fidelity human images. This mechanism performs a controlled experiment on images by introducing explicit anatomical errors in targeted regions while preserving the remaining content. With this mechanism, we create the Human Anatomical Preference (HAP) dataset with over 10K curated pairs for effective anatomical alignment of text-to-image human image generative models. To better leverage the locality of these controlled preference pairs, we introduce a localized and margin-bounded variant of DPO that prioritizes optimization in targeted anatomical regions while enforcing a finite preference margin to prevent over-optimization and preserve global semantics. We further introduce HAF-Bench, a benchmark for systematic evaluation of anatomical fidelity. Extensive experiments demonstrate that ASAP consistently reduces anatomical errors across multiple foundation models while maintaining overall image quality.