Excited to share my latest project: TextDetect!
I've built a Python script that uses EasyOCR and OpenCV to detect and recognize text in images. With this tool, you can easily visualize detected text with bounding boxes and annotations.
Technologies
I am thinking about an AI model with multiple languages support especially devnagari script languages , we are planning to build an RAG to parse a document and provide the data to the LLM , is this idea feasible and useful suggestions are welcomed
We’re excited to launch Text Behind Image, a free, ad-free tool that lets you place text behind images effortlessly. No installations, no paywalls, no sign-ups—just a simple, clean tool to create stunning visuals.
Why is it useful?
✅ YouTube Thumbna
Excited to share my latest project: TextDetect!
I've built a Python script that uses EasyOCR and OpenCV to detect and recognize text in images. With this tool, you can easily visualize detected text with bounding boxes and annotations.
Technologies
ChatGPT now offers direct image generation!
You can now create images directly within ChatGPT, powered by the impressive DALL-E 3. Just describe what you want, and even make adjustments through text prompts.
However, note that only two image genera
See More
1 replies6 likes
Devashish Guliya
Build. • 2m
Unpixel - Wordle, but for Images
Guess the pixelated Image in 6 guesses with just 1 hint, the image gets less pixelated with each wrong guess. A new image to solve everyday.
Hey folks! I am building stroke.ai, a chrome extension that can extract text from videos and images. Need your feedback.
1. Do u see yourself using this ?
2. What all features would u want this chrome extension to have apart from extracting text
The A.i race is getting interesting ⚡️
Open Ai just dropped this banger news 🔥
⬇️ Key Updates ⬇️
■ Edit the image generated in real time
■Clear and accurate text output
■More realistic and lifelike image
■ Faster image generation
■Mutiple
See More
0 replies3 likes
The next billionaire
Unfiltered and real ... • 2m
DeepSeek just dropped open-source Janus Pro 7B for image understanding and generation!
— SOTA 0.8 on GenEval and 84.19 on DPG-Bench, beats DallE3 and SD3-Medium
— 72M synthetic images in pretraining
— good text rendering
Images are small (384x384)