language:
- en
library_name: diffusers
license: apache-2.0
pipeline_tag: text-to-image
tags:
- text-to-image
- stable-diffusion
- garment generation
- multi-modality
IMAGGarment-1: Fine-Grained Garment Generation for Controllable Fashion Design
Project Page | Paper | Code
Introduction
IMAGGarment-1 addresses the challenges of multi-conditional controllability in personalized fashion design and digital apparel applications. Specifically, IMAGGarment-1 employs a two-stage training strategy to separately model global appearance and local details, while enabling unified and controllable generation through end-to-end inference. In the first stage, we propose a global appearance model that jointly encodes silhouette and color using a mixed attention module and a color adapter. In the second stage, we present a local enhancement model with an adaptive appearance-aware module to inject user-defined logos and spatial constraints, enabling accurate placement and visual consistency.
Sample Usage
To test the model, you can use the following inference code as demonstrated in the GitHub repository:
python inference_IMAGGarment-1.py \
--GAM_model_ckpt [GAM checkpoint] \
--LEM_model_ckpt [LEM chekcpoint] \
--sketch_path [your sketch path] \
--logo_path [your logo path] \
--mask_path [your mask path] \
--color_path [your color path] \
--prompt [your prompt] \
--output_path [your save path] \
--color_ckpt [color adapter checkpoint] \
--device [your device]