# Long-Tail Adaptive Flow Matching with Explicit Conditional Consistency Guidance for Precise Multimodal Face Synthesis

arXiv: https://arxiv.org/abs/2609.29581 · HTML: https://mlsanity.com/paper/2609.29581/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 39 of its 51 references that are in the map.
- First posted on arXiv 14 Sep 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 39)

- [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)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (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)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.08453/) (2023)
- [StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery](https://mlsanity.com/paper/2103.17249/) (2021)
- [GLIGEN: Open-Set Grounded Text-to-Image Generation](https://mlsanity.com/paper/2301.07093/) (2023)
- [MaskGAN: Towards Diverse and Interactive Facial Image Manipulation](https://mlsanity.com/paper/1907.11922/) (2019)
- [OminiControl: Minimal and Universal Control for Diffusion Transformer](https://mlsanity.com/paper/2411.15098/) (2024)
- [General Facial Representation Learning in a Visual-Linguistic Manner](https://mlsanity.com/paper/2112.03109/) (2021)
- [Flow Matching in Latent Space](https://mlsanity.com/paper/2307.08698/) (2023)
- [ControlNeXt: Powerful and Efficient Control for Image and Video Generation](https://mlsanity.com/paper/2408.06070/) (2024)
- [State of the Art on Diffusion Models for Visual Computing](https://mlsanity.com/paper/2310.07204/) (2023)
- [Collaborative Diffusion for Multi-Modal Face Generation and Editing](https://mlsanity.com/paper/2304.10530/) (2023)
- [Diffusion Models in Low-Level Vision: A Survey](https://mlsanity.com/paper/2406.11138/) (2024)
- [On the Design Fundamentals of Diffusion Models: A Survey](https://mlsanity.com/paper/2306.04542/) (2023)
- [Diverse Semantic Image Synthesis via Probability Distribution Modeling](https://mlsanity.com/paper/2103.06878/) (2021)
- [E2Style: Improve the Efficiency and Effectiveness of StyleGAN Inversion](https://mlsanity.com/paper/2104.07661/) (2021)
- [High-Fidelity 3D Face Generation from Natural Language Descriptions](https://mlsanity.com/paper/2305.03302/) (2023)
- [Face Generation and Editing with StyleGAN: A Survey](https://mlsanity.com/paper/2212.09102/) (2022)
- [FT2TF: First-Person Statement Text-To-Talking Face Generation](https://mlsanity.com/paper/2312.05430/) (2023)

## Abstract (arXiv)

Although diffusion-based methods have substantially improved the controllability of multimodal face synthesis, their semantic alignment remains suboptimal because most existing approaches rely on implicit latent-space objectives to model the relationship between denoising variables and multimodal conditions. Such implicit modeling is often insufficient to enforce precise correspondence between synthesized faces and conditional inputs, especially under long-tailed semantic mask distributions where rare attributes receive weak optimization signals. To address these limitations, we propose ECtextsuperscript2Face, a multimodal face synthesis framework that improves semantic alignment through explicit semantic supervision and distribution-aware optimization. First, we introduce Explicit Conditional Consistency Guidance (ECCG), which imposes direct consistency supervision in pixel space by decoding an approximate reverse estimate of the clean latent and explicitly aligning the synthesized image with textual descriptions and semantic masks. A temporal dynamic modulation function is further designed to adapt the supervision strength according to the timestep-dependent reliability of reverse estimation. Second, we propose Long-Tail Adaptive Flow Matching (LAFM), which reweights spatial optimization signals based on semantic attribute frequency, with normalized weights to maintain numerical stability during training. Importantly, all additional modules are used only during training and introduce no extra inference overhead. Extensive experiments show that ECtextsuperscript2Face consistently outperforms competitive baselines in both generation quality and semantic alignment, achieving a 29.38% improvement in mask accuracy on rare attributes.