Name: Alessandro de Oliveira Faria (A.K.A.CABELO)
Type: User
Company: OITI TECHNOLOGIES
Bio: Professor at FIA University, Ambassador OpenSUSE Linux, Chapter Leader OWASP SP, OneAPI Innovator Intel, Founder of the openSUSE Linux INNOVATOR initiative.
Twitter: cabelo_linux
Location: Brasil
Blog: http://assuntonerd.com.br
Alessandro de Oliveira Faria (A.K.A.CABELO)'s Projects
🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022
openSUSE landing page which features Tumbleweed and Leap
High-Resolution Image Synthesis with Latent Diffusion Models
Lightweight Communications and Marshalling
Learn OpenCV : C++ and Python Examples
libavif - Library for encoding and decoding .avif files
Intel® RealSense™ SDK
towards the solving spoofing problem
LightRay
:unlock: Lip Reading - Cross Audio-Visual Recognition using 3D Architectures
Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate (100+ LLMs)
Make one portrait alive!
Port of Facebook's LLaMA model in C/C++
A trivial programmatic Llama 3 jailbreak. Sorry Zuck!
Distribute and run LLMs with a single file.
🔥🔥 LLaVA++: Extending LLaVA with Phi-3 and LLaMA-3 (LLaVA LLaMA-3, LLaVA Phi-3)
The code release of paper "AAAI Low-Light Image Enhancement with Normalizing Flow", AAAI 2022
This code helps to develop a local streamlit client for multiple model chat
Basic to Advanced LLM Glossary terms
:robot: The free, Open Source OpenAI alternative. Self-hosted, community-driven and local-first. Drop-in replacement for OpenAI running on consumer-grade hardware. No GPU required. Runs gguf, transformers, diffusers and many more models architectures. It allows to generate Text, Audio, Video, Images. Also with voice cloning capabilities.
Localizador de patentes con YOLO v4
A repository for the HoloPlay Core SDK, Looking Glass Factory's tool to enable integrations and custom rendering pipelines.
Official implementation of Magic Clothing: Controllable Garment-Driven Image Synthesis
MambaOut: Do We Really Need Mamba for Vision?
MARS5 speech model (TTS) from CAMB.AI
Video Tutorial Series on Mask RCNN
Cross-platform, customizable ML solutions for live and streaming media.