# ChatGarment: Garment Estimation, Generation and Editing via Large Language Models

arXiv: https://arxiv.org/abs/2412.17811 · HTML: https://mlsanity.com/paper/2412.17811/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Placed in Document understanding and multimodal RAG, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 56 of its 65 references that are in the map.
- First posted on arXiv 23 Dec 2024.

## Placed in

- Multimodal LLMs / vision-language models / [Document understanding and multimodal RAG](https://mlsanity.com/mllm/document-understanding-and-multimodal-rag/)

## Builds on (most cited first, 30 of 56)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization](https://mlsanity.com/paper/1905.05172/) (2019)
- [PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization](https://mlsanity.com/paper/2004.00452/) (2020)
- [Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis](https://mlsanity.com/paper/2111.04276/) (2021)
- [CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets](https://mlsanity.com/paper/2406.13897/) (2024)
- [PointLLM: Empowering Large Language Models to Understand Point Clouds](https://mlsanity.com/paper/2308.16911/) (2023)
- [ICON: Implicit Clothed humans Obtained from Normals](https://mlsanity.com/paper/2112.09127/) (2021)
- [Multi-Garment Net: Learning to Dress 3D People from Images](https://mlsanity.com/paper/1908.06903/) (2019)
- [BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion](https://mlsanity.com/paper/2306.16940/) (2023)
- [Controlling Text-to-Image Diffusion by Orthogonal Finetuning](https://mlsanity.com/paper/2306.07280/) (2023)
- [ECON: Explicit Clothed humans Optimized via Normal integration](https://mlsanity.com/paper/2212.07422/) (2022)
- [Self-Correction for Human Parsing](https://mlsanity.com/paper/1910.09777/) (2019)
- [SMPLicit: Topology-aware Generative Model for Clothed People](https://mlsanity.com/paper/2103.06871/) (2021)
- [StyleGAN-Human: A Data-Centric Odyssey of Human Generation](https://mlsanity.com/paper/2204.11823/) (2022)
- [SceneCraft: An LLM Agent for Synthesizing 3D Scene as Blender Code](https://mlsanity.com/paper/2403.01248/) (2024)
- [BCNet: Learning Body and Cloth Shape from A Single Image](https://mlsanity.com/paper/2004.00214/) (2020)
- [Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization](https://mlsanity.com/paper/2311.06243/) (2023)
- [TeCH: Text-guided Reconstruction of Lifelike Clothed Humans](https://mlsanity.com/paper/2308.08545/) (2023)
- [3D-GPT: Procedural 3D Modeling with Large Language Models](https://mlsanity.com/paper/2310.12945/) (2023)
- [The Power of Points for Modeling Humans in Clothing](https://mlsanity.com/paper/2109.01137/) (2021)
- [ChatPose: Chatting about 3D Human Pose](https://mlsanity.com/paper/2311.18836/) (2023)
- [TurboEdit: Text-Based Image Editing Using Few-Step Diffusion Models](https://mlsanity.com/paper/2408.00735/) (2024)
- [ShapeCrafter: A Recursive Text-Conditioned 3D Shape Generation Model](https://mlsanity.com/paper/2207.09446/) (2022)
- [4D-DRESS: A 4D Dataset of Real-world Human Clothing with Semantic Annotations](https://mlsanity.com/paper/2404.18630/) (2024)
- [Learning a Shared Shape Space for Multimodal Garment Design](https://mlsanity.com/paper/1806.11335/) (2018)

## Built on by (most cited first, 23 of 23)

- [Dress-1-to-3: Single Image to Simulation-Ready 3D Outfit with Diffusion Prior and Differentiable Physics](https://mlsanity.com/paper/2502.03449/) (2025)
- [Human-Centric Foundation Models: Perception, Generation and Agentic Modeling](https://mlsanity.com/paper/2502.08556/) (2025)
- [GarmentDiffusion: 3D Garment Sewing Pattern Generation with Multimodal Diffusion Transformers](https://mlsanity.com/paper/2504.21476/) (2025)
- [GarmageNet: A Multimodal Generative Framework for Sewing Pattern Design and Generic Garment Modeling](https://mlsanity.com/paper/2504.01483/) (2025)
- [SMooGPT: Stylized Motion Generation using Large Language Models](https://mlsanity.com/paper/2509.04058/) (2025)
- [Image2Garment: Simulation-ready Garment Generation from a Single Image](https://mlsanity.com/paper/2601.09658/) (2026)
- [A Text-to-3D Framework for Joint Generation of CG-Ready Humans and Compatible Garments](https://mlsanity.com/paper/2503.12052/) (2025)
- [D-Garment: Physically Grounded Latent Diffusion for Dynamic Garment Deformations](https://mlsanity.com/paper/2504.03468/) (2025)
- [DressWild: Feed-Forward Pose-Agnostic Garment Sewing Pattern Generation from In-the-Wild Images](https://mlsanity.com/paper/2602.16502/) (2026)
- [NGL: Natural Garment Language for Training-Free Sewing Pattern Estimation](https://mlsanity.com/paper/2602.20700/) (2026)
- [From Air to Wear: Personalized 3D Digital Fashion with AR/VR Immersive 3D Sketching](https://mlsanity.com/paper/2505.09998/) (2025)
- [Grounding Intelligence in Movement](https://mlsanity.com/paper/2507.02771/) (2025)
- [Learning Sewing Patterns via Latent Flow Matching of Implicit Fields](https://mlsanity.com/paper/2601.17740/) (2026)
- [InverseDraping: Recovering Sewing Patterns from 3D Garment Surfaces via BoxMesh Bridging](https://mlsanity.com/paper/2604.02764/) (2026)
- [AnySurf: Any Surface Generation with Directed Edge](https://mlsanity.com/paper/2605.26149/) (2026)
- [Spatio-Temporal Garment Reconstruction Using Diffusion Mapping via Pattern Coordinates](https://mlsanity.com/paper/2602.24043/) (2026)
- [OmniFashion: Towards Generalist Fashion Intelligence via Multi-Task Vision-Language Learning](https://mlsanity.com/paper/2603.02658/) (2026)
- [FitVTON: Fit-aware Virtual Try-On via Body-Garment Size Control](https://mlsanity.com/paper/2606.12012/) (2026)
- [Fashion-3DLR: A Controllable 3D Garment Generation Using Pairwise Fashion Elements for Intelligent Design](https://mlsanity.com/paper/2607.23189/) (2026)
- [TailorCoPilot: Enabling Agentic Pattern Making with Version-Controlled State Tracking](https://mlsanity.com/paper/2608.25462/) (2026)
- [GarmentWeaver: Schema-Aware Structured Synthesis for Multimodal Sewing Patterns](https://mlsanity.com/paper/2608.30550/) (2026)
- [OmniFabric: Coherent UV Space Texture Synthesis for 3D Garment Reconstruction](https://mlsanity.com/paper/2609.30234/) (2026)
- [Inverse Garment Design with Visual Agents](https://mlsanity.com/paper/2610.15582/) (2026)

## Abstract (arXiv)

We introduce ChatGarment, a novel approach that leverages large vision-language models (VLMs) to automate the estimation, generation, and editing of 3D garments from images or text descriptions. Unlike previous methods that struggle in real-world scenarios or lack interactive editing capabilities, ChatGarment can estimate sewing patterns from in-the-wild images or sketches, generate them from text descriptions, and edit garments based on user instructions, all within an interactive dialogue. These sewing patterns can then be draped on a 3D body and animated. This is achieved by finetuning a VLM to directly generate a JSON file that includes both textual descriptions of garment types and styles, as well as continuous numerical attributes. This JSON file is then used to create sewing patterns through a programming parametric model. To support this, we refine the existing programming model, GarmentCode, by expanding its garment type coverage and simplifying its structure for efficient VLM fine-tuning. Additionally, we construct a large-scale dataset of image-to-sewing-pattern and text-to-sewing-pattern pairs through an automated data pipeline. Extensive evaluations demonstrate ChatGarment's ability to accurately reconstruct, generate, and edit garments from multimodal inputs, highlighting its potential to simplify workflows in fashion and gaming applications. Code and data are available at https://chatgarment.github.io/ .