# TrioPose: Native Triple-Stream Diffusion Transformers for Pose-Guided Text-to-Image Generation

arXiv: https://arxiv.org/abs/2606.07053 · HTML: https://mlsanity.com/paper/2606.07053/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 33 of its 42 references that are in the map.
- First posted on arXiv 5 Jun 2026.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 30 of 33)

- [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)
- [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)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [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)
- [GLIGEN: Open-Set Grounded Text-to-Image Generation](https://mlsanity.com/paper/2301.07093/) (2023)
- [Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2305.16322/) (2023)
- [Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance](https://mlsanity.com/paper/2403.14781/) (2024)
- [Pose Guided Person Image Generation](https://mlsanity.com/paper/1705.09368/) (2017)
- [CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark](https://mlsanity.com/paper/1812.00324/) (2018)
- [Controllable Person Image Synthesis with Attribute-Decomposed GAN](https://mlsanity.com/paper/2003.12267/) (2020)
- [Progressive Pose Attention Transfer for Person Image Generation](https://mlsanity.com/paper/1904.03349/) (2019)
- [Pose2Seg: Detection Free Human Instance Segmentation](https://mlsanity.com/paper/1803.10683/) (2018)
- [HumanSD: A Native Skeleton-Guided Diffusion Model for Human Image Generation](https://mlsanity.com/paper/2304.04269/) (2023)
- [Synthesizing Coherent Story with Auto-Regressive Latent Diffusion Models](https://mlsanity.com/paper/2211.10950/) (2022)
- [Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes](https://mlsanity.com/paper/2303.02760/) (2023)
- [ViTPose++: Vision Transformer for Generic Body Pose Estimation](https://mlsanity.com/paper/2212.04246/) (2022)
- [PISE: Person Image Synthesis and Editing with Decoupled GAN](https://mlsanity.com/paper/2103.04023/) (2021)
- [Be Your Own Prada: Fashion Synthesis with Structural Coherence](https://mlsanity.com/paper/1710.07346/) (2017)
- [Learning Semantic Person Image Generation by Region-Adaptive Normalization](https://mlsanity.com/paper/2104.06650/) (2021)
- [GRPose: Learning Graph Relations for Human Image Generation with Pose Priors](https://mlsanity.com/paper/2408.16540/) (2024)
- [KPE: Keypoint Pose Encoding for Transformer-based Image Generation](https://mlsanity.com/paper/2203.04907/) (2022)
- [Stable-Pose: Leveraging Transformers for Pose-Guided Text-to-Image Generation](https://mlsanity.com/paper/2406.02485/) (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)

Pose-guided text-to-image generation often suffers from limb distortions and feature crosstalk in complex multi-person scenarios. While existing UNet-based adapters struggle with long-range spatial dependencies, emerging Multimodal Diffusion Transformers (MM-DiTs) offer superior global modeling. However, naive signal concatenation in MM-DiTs severely disrupts pre-trained latent distributions. To address this, we propose TrioPose, a native pose-driven framework built upon the SD3.5M architecture. Specifically, we introduce a Triple-Stream Pose-Aware DiT (TSPA-DiT) that treats pose as an independent modality. It employs layer-wise activation and zero-initialized dual-residual injection to smoothly enforce geometric constraints while preserving pre-trained latent stability. To resolve severe multi-instance occlusions, we design a Learnable Relational Bias Mask that categorizes topological connectivity into fine-grained physical states, mapping them into continuous attention soft constraints to effectively decouple inter-instance interference. Furthermore, a Pose-Guided Spatial Loss Weighting strategy modulates the native diffusion objective using heatmap-derived error maps, focusing anatomical supervision strictly on distortion-prone regions. Extensive experiments demonstrate that TrioPose achieves state-of-the-art performance across challenging benchmarks, including Human-Art, CrowdPose, and OCHuman. Notably, it attains an AP of 64.33 on Human-Art, representing a 30% improvement over prior arts, while setting new standards for visual fidelity and text-image semantic alignment in complex multi-human generation.