HumanFlow: Controllable Human Image Generation via Flow Matching
ACM Transactions on Graphics · 03.07.2026 · 45 (4) · 1-17
DOI: 10.1145/3811361 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 03.07.2026. Verfasst von Wenzhuo Fan und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The National Natural Science Foundation of China, The Key Research and Development Program for Technological Innovation Project of Hubei Province.
Abstract (Originalsprache)
We present HumanFlow, a unified flow-matching-based framework that enables high-fidelity and controllable full-body human image generation under diverse human-centric control conditions. Despite recent progress, controllable human image generation poses a fundamental challenge in balancing high visual fidelity with strict adherence to human-centric control conditions. HumanFlow formulates human image generation as a conditional flow-matching process with deterministic generation dynamics. To incorporate such human-centric control conditions into the pretrained model, we introduce a unified control framework with Control Encoder and Token-ControlNet. A Control Encoder maps diverse conditions into a unified latent representation that is spatially aligned with the image latent space. Token-ControlNet is a lightweight control network architecturally aligned with the FLUX double-stream design. To address accurate structural control over human bodies, we further propose the Human Topology Consistency Loss (HTCL). HTCL regularizes conditional flow matching by constraining generated human configurations to a union of statistically grounded topology manifolds defined by normalized bone ratios and joint angles. To support large-scale training and systematic evaluation, we construct MiCoGen, a multi-condition human image dataset comprising over one million full-body human images with aligned text descriptions and rich human-centric control conditions. Extensive quantitative and qualitative evaluations on the MiCoGen dataset show that HumanFlow consistently achieves improved structural consistency than the existing diffusion-based and flow-matching-based methods, while maintaining high visual fidelity.
Förderung
- The National Natural Science Foundation of China
- The Key Research and Development Program for Technological Innovation Project of Hubei Province
Zitieren
APA
Fan, W., Zheng, H., Sun, J., Fang, F., Ding, H., & Xiao, C. (2026). HumanFlow: Controllable Human Image Generation via Flow Matching. ACM Transactions on Graphics, 45(4), 1-17. https://doi.org/10.1145/3811361
Vancouver
Fan W, Zheng H, Sun J, Fang F, Ding H, Xiao C. HumanFlow: Controllable Human Image Generation via Flow Matching. ACM Transactions on Graphics. 2026;45(4):1-17. doi:10.1145/3811361
BibTeX
@article{Fan2026,
author = {Fan, Wenzhuo and Zheng, Hongsheng and Sun, Jianchi and Fang, Fei and Ding, Hong and Xiao, Chunxia},
title = {HumanFlow: Controllable Human Image Generation via Flow Matching},
journal = {ACM Transactions on Graphics},
year = {2026},
volume = {45},
number = {4},
pages = {1--17},
doi = {10.1145/3811361}
}
EUVIMED