Analyze fashion items in images with bounding boxes and masks
Meta Llama3 8b with Llava Multimodal capabilities
Interact with Florence-2 to analyze images and generate descriptions
Run 3D human pose estimation with images
Generate depth map from images
Gaze Target Estimation
Compute normals for images and videos
Segment human parts in images
Tag images with NSFW labels
Visual Retrieval with ColPali and Vespa
Visualize attention maps for images using selected models
Tag images to find ratings, characters, and tags
Art Institute of Chicago Gallery
Facere is an AI-powered tool designed to analyze fashion items within images. It automatically detects and identifies fashion-related objects, providing bounding boxes and masks to highlight the detected items. This makes it a valuable resource for fashion enthusiasts, designers, and retailers looking to extract insights from visual data.
• Object Detection: Accurately identifies fashion items like clothing, accessories, and footwear in images.
• Bounding Boxes: Draws precise boxes around detected items for easy visualization.
• Masks: Generates segmentation masks to isolate fashion items from the background.
• Multi-Item Detection: Detects multiple fashion items in a single image.
• high accuracy: Leveraging advanced AI models for reliable detection and segmentation.
What type of images can Facere analyze?
Facere works best with clear, high-quality images of fashion items. It supports standard image formats like PNG, JPG, and JPEG.
Is Facere available online or as a downloadable tool?
Facere is typically accessible as a web-based tool, allowing users to upload images directly through a browser.
Can Facere detect multiple items in a single image?
Yes, Facere supports multi-item detection, making it ideal for analyzing crowded or complex fashion scenes.