DeepFashion MultiModal
Fashion images with rich visual and language annotations for controlled multimodal research.
What the resource contains
- 44,096 human fashion images
- Parsing, pose-related and attribute annotations
- Text descriptions describing clothing appearance
Potential uses
- Research text-guided fashion editing
- Train parsing and attribute models
- Evaluate image-language alignment
Access & formats
Images / annotation files. External dependencies. Follow the project’s instructions on GitHub; some resources require external files, registration or approval.
License & reuse
The publisher limits the dataset to noncommercial research and restricts redistribution and commercial derivatives.
Important limitations
Images of people and derived annotations must remain within publisher conditions. This is not a commercial catalog feed.
Source & attribution
yumingj — original GitHub project ↗
Documentation reviewed 2026-09-24. Review scope and licensing notes. Suggest a correction.
Related resources
Fashion-MNIST
zalandoresearch
A compact fashion-image classification benchmark suitable for learning and quick model comparisons.
IDX / image arrays · Repository / linked release
FEIDEGGER
zalandoresearch
Fashion photographs paired with multiple German descriptions for multimodal retrieval research.
Images / text annotations · Repository / linked release
DeepFashion2
switchablenorms
Clothing images with detailed annotations for detection, segmentation and consumer-to-shop retrieval.
Images / JSON annotations · External dependencies