# Grounding Free-Form Instructions for Fashion Complementary Image Generation

arXiv: https://arxiv.org/abs/2608.23302 · HTML: https://mlsanity.com/paper/2608.23302/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 40 references that are in the map.
- First posted on arXiv 24 Aug 2026.

## Builds on (most cited first, 22 of 22)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [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)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [Which Training Methods for GANs do actually Converge?](https://mlsanity.com/paper/1801.04406/) (2018)
- [VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization](https://mlsanity.com/paper/2103.16874/) (2021)
- [Dress Code: High-Resolution Multi-Category Virtual Try-On](https://mlsanity.com/paper/2204.08532/) (2022)
- [LaDI-VTON: Latent Diffusion Textual-Inversion Enhanced Virtual Try-On](https://mlsanity.com/paper/2305.13501/) (2023)
- [Multimodal Garment Designer: Human-Centric Latent Diffusion Models for Fashion Image Editing](https://mlsanity.com/paper/2304.02051/) (2023)
- [Visually-Aware Fashion Recommendation and Design with Generative Image Models](https://mlsanity.com/paper/1711.02231/) (2017)
- [Diffusion Models for Generative Outfit Recommendation](https://mlsanity.com/paper/2402.17279/) (2024)
- [A Review of Modern Fashion Recommender Systems](https://mlsanity.com/paper/2202.02757/) (2022)
- [Explainable Outfit Recommendation with Joint Outfit Matching and Comment Generation](https://mlsanity.com/paper/1806.08977/) (2018)
- [HieraFashDiff: Hierarchical Fashion Design with Multi-stage Diffusion Models](https://mlsanity.com/paper/2401.07450/) (2024)
- [Semi-supervised Adversarial Learning for Complementary Item Recommendation](https://mlsanity.com/paper/2303.05812/) (2023)

## Abstract (arXiv)

Fashion complementary image generation (CIG) aims to create garments that stylistically match a seed item based on user intent, making it a natural multimodal grounding problem where models must interpret language in visual context. Existing CIG benchmarks rely on rigid template prompts (e.g., "a photo of a skirt"), failing to reflect natural user queries and obscuring model behavior across levels of linguistic specificity. We introduce fashion complementary image generation with free-form instructions, a multimodal language-grounding setting where a model generates a compatible garment from a seed image and a natural-language instruction. To this end, we enrich three CIG benchmarks with low-, medium-, and high-specificity instructions generated by a vision-language model and validated by human annotators. We instantiate the task with StyleFlow, a Rectified Flow Matching model that jointly conditions on the seed image and instruction within a single multimodal transformer. Across image quality metrics, catalog-alignment analysis, ablations, and human evaluation, StyleFlow consistently produces instruction-aligned and stylistically coherent garments while reducing architectural complexity and inference cost relative to auxiliary-module approaches.