AI Project: OCR-Free Document Parsing with Donut (Vision-to-JSON)
In Document QA Project, we used LayoutLM to read documents. But that required a separate OCR step to find the text first. Now, Hugging Face…
AI Project: Image Upscaling & Super Resolution (SwinIR)
We’ve generated images from scratch, but what about fixing old ones? Hugging Face Image Upscaling offers a powerful solution for this. Super Resolution is the…
AI Project: Depth Estimation with Hugging Face (Seeing in 3D)
We’ve taught AI to classify objects and segment pixels. Now, let’s explore Hugging Face Depth Estimation and teach AI to understand distance. Depth Estimation models…
AI Project: Build a Local “Jarvis” (Real-Time Voice Commands with Whisper)
We’ve generated audio and transcribed files. Now, let’s do it live with a Python Voice Assistant. We will build a script that: Step 1: Installation…
AI Project: Chat with Images (Visual QA with LLaVA)
We’ve done Image Captioning (getting a simple description). But what if you want to have a conversation about an image? That’s where Hugging Face LLaVA…
AI Project: Text-to-Music Generation (Meta MusicGen)
We have generated images, video, and speech. The final frontier of generative media is Music. let’s explore Text to Music Python and see how text…
AI Project: Text-to-Video Generation (Hugging Face diffusers)
We’ve generated text, audio, and images. The final frontier is Video. Now, Hugging Face Text to Video technology is opening up exciting new possibilities for…
AI Project: Controlling Stable Diffusion with ControlNet (Sketch-to-Image)
Standard Stable Diffusion is amazing, but it’s chaotic. You type “cat,” and you get a cat, but maybe not the cat pose you wanted. Hugging…
AI Project: Efficient Fine-Tuning with LoRA and PEFT (Train LLMs on Consumer Hardware)
In Fine-Tuning (Part 3: Evaluation & Sharing), we fine-tuned a small BERT model. But if you try to fine-tune a modern LLM (like Llama 3…
AI Project: Train on Your Own Data (Loading Local Files with datasets)
So far, we’ve used load_dataset to pull pre-made datasets (like “imdb“) from the Hugging Face Hub. But the real power is training an AI on…
