I recently worked on a

I recently worked on a multimodal Generative AI notebook that demonstrates practical AI use cases in a single workflow. The project includes:

Text-to-image generation using Stable Diffusion and Diffusers Prompt engineering, negative prompting, and parameter tuning Image-to-image generation for creative transformations Text-to-speech generation using Bark This project reflects my interest in applying deep learning in a hands-on, creative, and real-world way. I’m especially interested in building AI systems that are not only technically impressive but also useful in modern creative workflows.

GitHub: https://github.com/Mehadii-Hassan/FSDS-with-GenAI/blob/main/11.%20Deep%20Learning/3.%20RNN/GenAI%20YT/7_Multimodel_demo.ipynb

#GenerativeAI #StableDiffusion #Diffusers #HuggingFace #PromptEngineering #DeepLearning #MachineLearning #Python #AIProjects #TextToImage #ImageToImage #TextToSpeech #OpenSource #Innovation