Self-hostable TikTok feed for your clips. Make a TikTok feed with your own videos

Presize.io - Bulk Proprocess, Resize and Crop Your Images.

🎒 Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware JSON for LLM prompts. Spec, benchmarks, TypeScript SDK.

Replace 'hub' with 'ingest' in any GitHub URL to get a prompt-friendly extract of a codebase

AI powered speech denoising and enhancement

SVGBench: A challenging LLM benchmark that tests knowledge, coding, physical reasoning capabilities of LLMs.

Transcribe audio and add subtitles to videos using Whisper in ComfyUI

An app for creating audio-based content such as song covers and speech using Retrieval-based Voice Conversion.

Enable true multi gpu capability in Comfy UI using XDiT XFuser and FSDP

FamilyBench evaluation tool for testing the relational reasoning capabilities of Large Language Models (LLMs).

Linux GPU Configuration And Monitoring Tool

Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.

Reliable model swapping for any local OpenAI compatible server - llama.cpp, vllm, etc

A daemon that automatically manages the performance states of NVIDIA GPUs.

A minimal LLM chat app that runs entirely in your browser

Lets make video diffusion practical!

(CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

OpenAI Whisper ASR Webservice API

The button Redgifs.com forgot to add.

ClaraVerse is a privacy-first, fully local AI workspace featuring a Local LLM chat powered by LLama.cpp, along with support for any provider, tool calling, agent building, Stable Diffusion, and n8n…

Parse files (e.g. code repos) and websites to clipboard or a file for ingestions by AI / LLMs

Official PyTorch implementation for "Large Language Diffusion Models"

Official repository for "NoLiMa: Long-Context Evaluation Beyond Literal Matching"

ComfyUI nodes to crop before sampling and stitch back after sampling that speed up inpainting

ComfyUI nodes to use segment-anything-2

ComfyUI node for background removal, implementing InSPyreNet the best method up to date