本地大語言模型執行環境、AI 程式碼助手、推論引擎與前沿 RAG 架構。
25MB CPU-Only, Open-Source TTS Model
“https://huggingface.co/KittenML/kitten-tts-nano-0.1 https://github.com/KittenML/KittenTTS This is the model and Github page, this blog post looks very much AI generated.”
bstract programming language for computer vision
AI-powered tattoo artist, using Stable Diffusion
open source computer vision deployment
Build an open-source computer vision model in seconds using text
BetterOCR combines and corrects multiple OCR engines with an LLM
n open-weights TTS model for generating realistic dialogue
“just in case, another opensource project using same name https://wiki.gnome.org/Apps/Dia/ https://gitlab.gnome.org/GNOME/dia”
Search millions of prompts for Stable Diffusion and DALL-E
Qwen-2.5-32B is now the best open source OCR model
PDF to MD by LLMs – Extract Text/Tables/Image Descriptives by GPT4o
A character-level text diffusion model from scratch
I generated 70k audiobooks with OpenAI Text-to-Speech
Experimental website combining computer vision and web design