[ECCV2024] API code for T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy

Labeling tool with SAM(segment anything model),supports SAM, SAM2, SAM3, sam-hq, MobileSAM EdgeSAM etc.交互式半自动图像标注工具

使用onnxruntime部署GroundingDINO开放世界目标检测，包含C++和Python两个版本的程序

TextSCF: LLM-Enhanced Image Registration Model

Exploring Bark, the Open-Source Text-to-Audio Generative Model

`DYFLoadingManager` is an iOS management class that loads animation prompts, it displays a translucent mask with an indicator and labels while work is being done.

Zero-shot Industrial Anomaly Segmentation with Image-Aware Prompt Generation (PAKDD 2025)

ComfyUI integration for SAM3 (Segment Anything with Concepts) - Open-vocabulary text-based segmentation

TextSAM-EUS: Text Prompt Learning for SAM to Accurately Segment Tumor in Ultrasound Images

a simple UI to test chatgpt

API project leveraging Gemini AI for text prompt responses and image prompt response, with robust exception handling

TextualDiffuser is a text-to-image generation tool powered by Stable Diffusion. It transforms natural language prompts into high-quality visuals, making AI-powered creativity accessible for developers, designers, and artists.

Object detection via text prompt using OWLv2 and Gradio app in PyTorch

This project is a Streamlit application powered by OpenAI's DALL-E, offering seamless text-to-image generation. Users can input textual prompts to generate high-quality images, while rate limiting ensures controlled API usage. Visit the live demo for a firsthand experience.

Test and save image prompts

🎯 Enable seamless text-based segmentation using natural language with ComfyUI's SAM 3 integration for quick and accurate object identification.

🌟 Enhance ComfyUI with SAM3 for seamless text-prompt-based image segmentation, enabling precise object detection and visualization.

🔧 Streamline AI agents with this flexible prompt template and task specification project for effective instruction and memory management.