Lance
A 3B-active-parameter native unified multimodal model for image and video understanding, generation, and editing.
- 1.4k
- Python
- Apache-2.0
- 4 mo ago
A 3B-active-parameter native unified multimodal model for image and video understanding, generation, and editing.
[CVPR 2024 Highlightπ₯] Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding
UniWorld: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation
π© An Alfred 5 Workflow for using OpenAI Chat API to interact with GPT models π€π¬ It also allows image generation/editing/understanding πΌοΈ, speech-to-text conversion π€, and text-to-speech synthesis π
WACV 2024 Papers: Discover cutting-edge research from WACV 2024, the leading computer vision conference. Stay updated on the latest in computer vision and deep learning, with code included. β support visual intelligence development!
This is the implement of the paper "DynamicVis: An Efficient and General Visual Foundation Model for Remote Sensing Image Understanding"
Image text to text model.
π [Teaching] Class CVIU78101: Introduction to Computer Vision for Image Understanding Course
πΌοΈπE2E Multi-modal Document Preprocessing with Azure Document Intelligence
PicQ: Demo for MiniCPM-o 4.5 to answer questions about images using natural language.
π Miru β Multimodal reasoning tracer ποΈ. Answers questions over images/docs πΌοΈπ while visualizing step-by-step attention and reasoning π. Built for explainable vision-language AI π€β¨
Unified MiniMax MCP server for multimodal generation, Token Plan search, and image understanding.
Fallback multimodal vision skill for AI coding agents. Calls any OpenAI-compatible vision API (doubao, OpenAI, OpenRouter, Azure, vLLM, etc.) when the primary model fails to interpret images.