CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

📡 Simple and ready-to-use tutorials for TensorFlow

High-Resolution Image Synthesis with Latent Diffusion Models

Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion

AirLLM 70B inference with single 4GB GPU

An Open Source text-to-speech system built by inverting Whisper.

Face Depixelizer based on "PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models" repository.

AI magics meet Infinite draw board.

Autonomously train research-agent LLMs on custom data using reinforcement learning and self-verification.

Load local LLMs effortlessly in a Jupyter notebook for testing purposes alongside Langchain or other agents. Contains Oobagooga and KoboldAI versions of the langchain notebooks with examples.

Comparing retrieval abilities from GPT4-Turbo and a RAG system on a toy example for various context lengths

COVID19 Response Repository; by the People for the People.

Generate Your Own Private Morning Radio for Commute