TO INFINITY AND BEYOND ...
Posted on 14.Dec.24 by Usama Saqib
CreativePromptAI
A graphical user interface (GUI) to use open-source text-to-image large language model (LLM) from HuggingFace to generate images.
Introducing Creative Prompt AI: Your Ultimate AI-Powered Image Generation and Viewing Tool!
Are you ready to revolutionize the way you create and view images? Meet Creative Prompt AI, a powerful open-source desktop application designed to make AI image generation and viewing seamless and intuitive. Here's why you need to check it out:
Key Features:
- Easy Dependency Management: With a single click, install all necessary dependencies like
diffusers,torch, andPillow. No more hassle with manual installations! - Model Loading Made Simple: Load your preferred AI models effortlessly from HuggingFace. Just enter the model ID and download path, and let Creative Prompt AI handle the rest. It even supports LoRA weights for enhanced image generation.
- Customizable Prompts: Generate stunning images by simply entering your desired prompt. Whether it's "pixel, a cute corgi" or any other creative idea, watch your vision come to life.
- Interactive Image Viewer: View your generated images in a dedicated window with zoom functionality. Save your favorite images directly from the viewer.
- Batch Image Generation: Generate multiple images at once with customizable settings like negative prompts and guidance scales. Perfect for exploring different variations and styles.
- Progress Tracking: Stay informed with a real-time progress bar that updates you on the status of your model loading and image generation processes.
- Open Source and Extensible: Built around the Hugging Face API, Creative Prompt AI allows you to add any model from Hugging Face and incorporate LoRA weights. Customize and extend the tool to fit your unique needs.
How It Works:
Requirement: Nvidia CUDA Graphic Cards is a must!
- Install Dependencies: Click the "Install Dependencies" button to set up your environment.
- Copy Model: Copy model link from Hugging Face
- Load Model: Enter the model ID and download path, then click "Load Model" to initialize your AI model. (Note: If you change the model ID or LoRA weights then load the model again).
- Generate Images: Input your prompt and click "Generate Images" to create a batch of stunning visuals.
- View and Save: Use the interactive viewer to zoom in/out and save your favorite images.
Why Choose Creative Prompt AI?
- User-Friendly Interface: Designed with simplicity in mind, making it accessible for both beginners and experts.
- High-Quality Outputs: Leverage state-of-the-art AI models to produce high-resolution, visually appealing images.
- Versatile Applications: Ideal for artists, designers, and anyone looking to explore the creative possibilities of AI.
- Community-Driven: As an open-source project, you can contribute, customize, and enhance the tool to suit your specific needs.
Future Development Idea:
- Add support to include Image-to-Image model
- Add support to use LLM model for text generation
- Add multi-agent support
- much more!
Be part of the AI image generation revolution. With Creative Prompt AI, your creativity knows no bounds!
Get Started Today!
Posted on 14.SEPT.24 by Usama Saqib
Hi there!
I made a new open-source project called LOOC Mapper. I made this software sometimes ago to help me with my codebase work especially when I am task in designing and rewriting new codes. This software help me understand the structure of my codebase and decice how many lines of code do I need to work on.
Introducing LOCC Mapper
The ultimate tool for developers and teams to gain deep insights into their codebases. Whether you're working on a small project or managing a large-scale application, LOCC Mapper is designed to help you understand and optimize your code structure effortlessly.
Posted on 23.JAN.22 by Usama Saqib
Hi there!
Welcome to bitbytelab. My name is Usama Saqib. I received my Ph.D. in signal processing in robotics from Aalborg University, Denmark (2021), M.Sc in Embedded Systems Engineering (2015) and a B.Sc in Electrical Engineering (2011). I have a passion for cutting-edge technologies, especially, robotics and signal processing. During my Ph.D., I have authored several research papers and published my findings in several reputed conferences. My thesis is titled "Acoustic Echo Estimation using the model-based approach with Application to Spatial Map Construction in Robotics." In this blog, I share my passion for robotics and signal processing.
Posted on 19.OCT.23 by Usama Saqib
Working on a pitch estimator using WebAPI. This was my first attempt to learn and use webAPI to estimate pitch of an audio source. The application access a user's microphone and estimate the fundamental frequency of the sound recorded by the microphone. The corresponding estimate is displayed on the webpage.
Posted on 14.SEPT.22 by Usama Saqib
Repository for my IROS 2020 paper is available! [LINK]
In this work, we proposed an audio processing algorithm that was tested on a proof of concept robotic platform to construct spatial map of an environment using echolocation.
The hardware required to build a similar platform is shown in the image below:
