AI
High-Resolution Image Synthesis with Latent Diffusion Models
Apply diffusion models using the new Hugging Face diffusers package to synthesize music instead of images.
Generates video game music using neural networks.
Machine Learning Containers for NVIDIA Jetson and JetPack-L4T
fast-stable-diffusion + DreamBooth
This is the docker image for gesen2egee/MoE-LLaVA-hf, a script that uses MoE-LLaVA to describe images. It is designed to prepare the training set caption for stable diffusion model training. (Docke…
The CS467 Capstone Project at Oregon State University in the Spring of 2021. Carzam is a web application that leverages an AI to identify vehicles, their make and model in a submitted picture.
The world's simplest facial recognition api for Python and the command line
Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".
Generative models for conditional audio generation
An open and free database for AI models
Stable Diffusion web UI
Official inference framework for 1-bit LLMs