Christoph Schuhmann

improved-aesthetic-predictor. CLIP+MLP Aesthetic Score Predictor

4MC-4M-Image-Text-Pairs-with-CLIP-embeddings. I have created a dataset of Image-Text-Pairs by using the cosine similarity of the CLIP embeddings of the image & it's caption derrived from YFCC100M. I have also added propabilities from a NSFW detector & more.

dacvae-echo. Python

bing_image_downloader. Python library to download bulk of images from Bing.com

Wikipedia. A Pythonic wrapper for the Wikipedia API

open_clip. An open source implementation of CLIP.

crawlingathome-worker. Python

annotations. This repository provides access to human labeled datasets for training classifiers.

collaborative-latent-diffusion. Collaborative inference of latent diffusion via hivemind

school-bud-e-middleware. School Bud-E Middleware is a lightweight, privacy-first control center for AI chat, speech-to-text, and text-to-speech. Manage providers, routing, and costs with a simple Admin Console. Give users per-period credits, prices per model, and a shared Common Pool. EU-friendly via OpenAI-Format endüpoints or our optional Google Cloud Vertex proxy.

whisper-audio-caption. Python

clip-video-encode. Easily compute clip embeddings from video frames

Exam-Bud-E. Eigenständige digitale Prüfungsplattform für Schulen – Lehrer erstellen Prüfungen per Drag & Drop, Schüler legen sie per Zugangscode ab. Flask + SQLite, keine externe Abhängigkeiten.