# MultiHuman-Testbench: Benchmarking Image Generation for Multiple Humans

arXiv: https://arxiv.org/abs/2506.20879 · HTML: https://mlsanity.com/paper/2506.20879/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 50 references that are in the map.
- First posted on arXiv 25 Jun 2025.

## Builds on (most cited first, 30 of 35)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [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)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2308.06721/) (2023)
- [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022)
- [GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment](https://mlsanity.com/paper/2310.11513/) (2023)
- [Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis](https://mlsanity.com/paper/2306.09341/) (2023)
- [Show-o: One Single Transformer to Unify Multimodal Understanding and Generation](https://mlsanity.com/paper/2408.12528/) (2024)
- [InstantID: Zero-shot Identity-Preserving Generation in Seconds](https://mlsanity.com/paper/2401.07519/) (2024)
- [OmniGen: Unified Image Generation](https://mlsanity.com/paper/2409.11340/) (2024)
- [Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2305.16322/) (2023)
- [FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention](https://mlsanity.com/paper/2305.10431/) (2023)
- [StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation](https://mlsanity.com/paper/2405.01434/) (2024)
- [PuLID: Pure and Lightning ID Customization via Contrastive Alignment](https://mlsanity.com/paper/2404.16022/) (2024)
- [MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance](https://mlsanity.com/paper/2406.07209/) (2024)
- [Training-Free Consistent Text-to-Image Generation](https://mlsanity.com/paper/2402.03286/) (2024)
- [Kandinsky: an Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion](https://mlsanity.com/paper/2310.03502/) (2023)
- [ACE++: Instruction-Based Image Creation and Editing via Context-Aware Content Filling](https://mlsanity.com/paper/2501.02487/) (2025)
- [OMG: Occlusion-friendly Personalized Multi-concept Generation in Diffusion Models](https://mlsanity.com/paper/2403.10983/) (2024)
- [λ-ECLIPSE: Multi-Concept Personalized Text-to-Image Diffusion Models by Leveraging CLIP Latent Space](https://mlsanity.com/paper/2402.05195/) (2024)
- [DreamStory: Open-Domain Story Visualization by LLM-Guided Multi-Subject Consistent Diffusion](https://mlsanity.com/paper/2407.12899/) (2024)
- [UniPortrait: A Unified Framework for Identity-Preserving Single- and Multi-Human Image Personalization](https://mlsanity.com/paper/2408.05939/) (2024)
- [Resolving Multi-Condition Confusion for Finetuning-Free Personalized Image Generation](https://mlsanity.com/paper/2409.17920/) (2024)
- [One Diffusion to Generate Them All](https://mlsanity.com/paper/2411.16318/) (2024)
- [Identity Decoupling for Multi-Subject Personalization of Text-to-Image Models](https://mlsanity.com/paper/2404.04243/) (2024)
- [InstantFamily: Masked Attention for Zero-shot Multi-ID Image Generation](https://mlsanity.com/paper/2404.19427/) (2024)

## Built on by (most cited first, 8 of 8)

- [Resolving the Identity Crisis in Text-to-Image Generation](https://mlsanity.com/paper/2510.01399/) (2025)
- [Ar2Can: An Architect and an Artist Leveraging a Canvas for Multi-Human Generation](https://mlsanity.com/paper/2511.22690/) (2025)
- [MIBE: Multi-subject Interaction Benchmark and Evaluator for Personalized Image Generation](https://mlsanity.com/paper/2607.01383/) (2026)
- [InsHuman: Towards Natural and Identity-Preserving Human Insertion](https://mlsanity.com/paper/2605.07402/) (2026)
- [Composing People Together: Iterative Pose-Image Generation for Multi-Person Interaction Scenes](https://mlsanity.com/paper/2605.23178/) (2026)
- [CogCanvas: A Benchmark for Evaluating Multi-Subject Reference-Based Image Generation](https://mlsanity.com/paper/2606.15867/) (2026)
- [MPIE-Bench: Benchmarking Anatomically Plausible Multi-Person Interaction Editing](https://mlsanity.com/paper/2607.27616/) (2026)
- [WithEveryone: Unified Planning and Identity Grounding for Group Image Generation](https://mlsanity.com/paper/2608.20336/) (2026)

## Abstract (arXiv)

Generation of images containing multiple humans, performing complex actions, while preserving their facial identities, is a significant challenge. A major factor contributing to this is the lack of a dedicated benchmark. To address this, we introduce MultiHuman-Testbench, a novel benchmark for rigorously evaluating generative models for multi-human generation. The benchmark comprises 1,800 samples, including carefully curated text prompts, describing a range of simple to complex human actions. These prompts are matched with a total of 5,550 unique human face images, sampled uniformly to ensure diversity across age, ethnic background, and gender. Alongside captions, we provide human-selected pose conditioning images which accurately match the prompt. We propose a multi-faceted evaluation suite employing four key metrics to quantify face count, ID similarity, prompt alignment, and action detection. We conduct a thorough evaluation of a diverse set of models, including zero-shot approaches and training-based methods, with and without regional priors. We also propose novel techniques to incorporate image and region isolation using human segmentation and Hungarian matching, significantly improving ID similarity. Our proposed benchmark and key findings provide valuable insights and a standardized tool for advancing research in multi-human image generation. The dataset and evaluation codes will be available at https://github.com/Qualcomm-AI-research/MultiHuman-Testbench.