Generative AI
Build real generative AI apps from image generation to LLM pipelines.
55+
completed
~24.5h
total time
9
projects
Text-to-Image Pipeline with Stable Diffusion
Stand up a local text-to-image pipeline with Hugging Face Diffusers and Stability AI's SDXL and SD3.5 checkpoints.
Build a Chatbot with Memory
Build a Claude-powered chatbot with two memory layers: short-term conversational state via a LangGraph checkpointer, and long-term recall.
Fine-tune a Diffusion Model on Custom Data
Train a LoRA adapter on top of SDXL using Diffusers' training scripts so the model reliably reproduces a specific subject or style.
Build a Multimodal Assistant
Build an assistant that reasons over images and text together using Claude's vision input, extended with tool use so it can act on what it sees.
Prompt Chaining and Orchestration
Build a multi-step content pipeline (research, draft, critique, revise) as a LangGraph state graph with conditional branching.
Voice Cloning Pipeline
Clone a voice from a short reference clip and generate new speech in that voice, including cross-lingual synthesis.
Image-to-Video Generation
Animate a still image into a short video clip using Stability AI's Stable Video Diffusion, chained with SDXL from a single text prompt.
Build a Style Transfer Tool
Build a style transfer tool using SDXL's IP-Adapter to apply a reference image's visual style to new generations, plus ControlNet.
Ship a Generative AI SaaS Product
Wrap a generation API behind FastAPI, gate it with Stripe subscription billing and per-tier usage limits, and handle billing webhooks.