Multimodal Garment Designer
What it is
A research project implementing a Latent Diffusion Model (LDM) for fashion image editing. It enables the generation of human-centric fashion images by following multimodal prompts including text, human body poses, and garment sketches.
The problem it solves
Lack of high-quality, human-centric fashion image editing tools that can handle multiple input modalities like sketches and poses simultaneously.
What you could use it for
- Fashion illustration and design visualization
- Generating realistic clothing items based on sketches
- Creating human-centric fashion images with specific body poses
Read the source ↗Back to the library →
Summary written by an AI model from the source; check the source before you rely on it.