# HumanSD: A Native Skeleton-Guided Diffusion Model for Human Image Generation

arXiv: https://arxiv.org/abs/2304.04269 · HTML: https://mlsanity.com/paper/2304.04269/

## Key facts

- Cited by 105 papers in the map (data through 14 Oct 2026).
- Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models.
- Builds on 47 of its 59 references that are in the map.
- First posted on arXiv 9 Apr 2023.

## Placed in

- Diffusion models / [3D, point cloud and scene generation](https://mlsanity.com/diffusion/3d-point-cloud-and-scene-generation/)

## Builds on (most cited first, 30 of 47)

- [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)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.08453/) (2023)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [GLIGEN: Open-Set Grounded Text-to-Image Generation](https://mlsanity.com/paper/2301.07093/) (2023)
- [NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding](https://mlsanity.com/paper/1905.04757/) (2019)
- [BABEL: Bodies, Action and Behavior with English Labels](https://mlsanity.com/paper/2106.09696/) (2021)
- [GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions](https://mlsanity.com/paper/2104.14806/) (2021)
- [Pose Guided Person Image Generation](https://mlsanity.com/paper/1705.09368/) (2017)
- [HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation](https://mlsanity.com/paper/1908.10357/) (2019)
- [Design Guidelines for Prompt Engineering Text-to-Image Generative Models](https://mlsanity.com/paper/2109.06977/) (2021)
- [Controllable Person Image Synthesis with Attribute-Decomposed GAN](https://mlsanity.com/paper/2003.12267/) (2020)
- [One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer](https://mlsanity.com/paper/2303.16160/) (2023)
- [HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modeling](https://mlsanity.com/paper/2204.13686/) (2022)
- [Deep Image Spatial Transformation for Person Image Generation](https://mlsanity.com/paper/2003.00696/) (2020)
- [Synthesizing Coherent Story with Auto-Regressive Latent Diffusion Models](https://mlsanity.com/paper/2211.10950/) (2022)
- [Exploring Dual-task Correlation for Pose Guided Person Image Generation](https://mlsanity.com/paper/2203.02910/) (2022)
- [Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes](https://mlsanity.com/paper/2303.02760/) (2023)
- [SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos](https://mlsanity.com/paper/2112.13715/) (2021)

## Built on by (most cited first, 30 of 105)

- [Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks](https://mlsanity.com/paper/2401.14159/) (2024)
- [PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding](https://mlsanity.com/paper/2312.04461/) (2023)
- [Effective Whole-body Pose Estimation with Two-stages Distillation](https://mlsanity.com/paper/2307.15880/) (2023)
- [Semantic Image Inversion and Editing using Rectified Stochastic Differential Equations](https://mlsanity.com/paper/2410.10792/) (2024)
- [ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback](https://mlsanity.com/paper/2404.07987/) (2024)
- [Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code](https://mlsanity.com/paper/2310.01506/) (2023)
- [Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control](https://mlsanity.com/paper/2503.14492/) (2025)
- [TeCH: Text-guided Reconstruction of Lifelike Clothed Humans](https://mlsanity.com/paper/2308.08545/) (2023)
- [HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting](https://mlsanity.com/paper/2311.17061/) (2023)
- [Controllable Generation with Text-to-Image Diffusion Models: A Survey](https://mlsanity.com/paper/2403.04279/) (2024)
- [DreamWaltz: Make a Scene with Complex 3D Animatable Avatars](https://mlsanity.com/paper/2305.12529/) (2023)
- [HyperHuman: Hyper-Realistic Human Generation with Latent Structural Diffusion](https://mlsanity.com/paper/2310.08579/) (2023)
- [ControlVAR: Exploring Controllable Visual Autoregressive Modeling](https://mlsanity.com/paper/2406.09750/) (2024)
- [EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning](https://mlsanity.com/paper/2509.20360/) (2025)
- [FullDiT: Multi-Task Video Generative Foundation Model with Full Attention](https://mlsanity.com/paper/2503.19907/) (2025)
- [ConsistentID: Portrait Generation with Multimodal Fine-Grained Identity Preserving](https://mlsanity.com/paper/2404.16771/) (2024)
- [BrushEdit: All-In-One Image Inpainting and Editing](https://mlsanity.com/paper/2412.10316/) (2024)
- [CosmicMan: A Text-to-Image Foundation Model for Humans](https://mlsanity.com/paper/2404.01294/) (2024)
- [TOSS:High-quality Text-guided Novel View Synthesis from a Single Image](https://mlsanity.com/paper/2310.10644/) (2023)
- [RelationAdapter: Learning and Transferring Visual Relation with Diffusion Transformers](https://mlsanity.com/paper/2506.02528/) (2025)
- [SmartControl: Enhancing ControlNet for Handling Rough Visual Conditions](https://mlsanity.com/paper/2404.06451/) (2024)
- [HumanRefiner: Benchmarking Abnormal Human Generation and Refining with Coarse-to-fine Pose-Reversible Guidance](https://mlsanity.com/paper/2407.06937/) (2024)
- [Edify Image: High-Quality Image Generation with Pixel Space Laplacian Diffusion Models](https://mlsanity.com/paper/2411.07126/) (2024)
- [Referring to Any Person](https://mlsanity.com/paper/2503.08507/) (2025)
- [Boosting Camera Motion Control for Video Diffusion Transformers](https://mlsanity.com/paper/2410.10802/) (2024)
- [ClassDiffusion: More Aligned Personalization Tuning with Explicit Class Guidance](https://mlsanity.com/paper/2405.17532/) (2024)
- [Towards Effective Usage of Human-Centric Priors in Diffusion Models for Text-based Human Image Generation](https://mlsanity.com/paper/2403.05239/) (2024)
- [VirtualModel: Generating Object-ID-retentive Human-object Interaction Image by Diffusion Model for E-commerce Marketing](https://mlsanity.com/paper/2405.09985/) (2024)
- [MoLE: Enhancing Human-centric Text-to-image Diffusion via Mixture of Low-rank Experts](https://mlsanity.com/paper/2410.23332/) (2024)
- [Simulating the Real World: A Unified Survey of Multimodal Generative Models](https://mlsanity.com/paper/2503.04641/) (2025)

## Abstract (arXiv)

Controllable human image generation (HIG) has numerous real-life applications. State-of-the-art solutions, such as ControlNet and T2I-Adapter, introduce an additional learnable branch on top of the frozen pre-trained stable diffusion (SD) model, which can enforce various conditions, including skeleton guidance of HIG. While such a plug-and-play approach is appealing, the inevitable and uncertain conflicts between the original images produced from the frozen SD branch and the given condition incur significant challenges for the learnable branch, which essentially conducts image feature editing for condition enforcement. In this work, we propose a native skeleton-guided diffusion model for controllable HIG called HumanSD. Instead of performing image editing with dual-branch diffusion, we fine-tune the original SD model using a novel heatmap-guided denoising loss. This strategy effectively and efficiently strengthens the given skeleton condition during model training while mitigating the catastrophic forgetting effects. HumanSD is fine-tuned on the assembly of three large-scale human-centric datasets with text-image-pose information, two of which are established in this work. As shown in Figure 1, HumanSD outperforms ControlNet in terms of accurate pose control and image quality, particularly when the given skeleton guidance is sophisticated.