SoulX-FlashHead: A unified 1.3B-parameter framework designed for high-fidelity, infinite-length, and real-time streaming portrait video generation.
Radar
New projects people are discovering or following across Pinokio.
Unify Efficient Fine-Tuning of 100+ LLMs https://github.com/hiyouga/LLaMA-Factory
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
[CVPR 2025] MatAnyone: Stable Video Matting with Consistent Memory Propagation
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
[ECCV 2022] ByteTrack: Multi-Object Tracking by Associating Every Detection Box
OpenAI-compatible endpoint powered by LiteLLM SDK. Supports 100+ AI providers with model name emulation.
AI-powered animation sprite studio — generate character sprite sheets with 8 directions and 100+ actions from a single text prompt (Wails + Go + React)
real time face swap and one-click video deepfake with only a single image
Qwen3-TTS Turkish fine-tuning with LoRA on ISSAI Turkish Speech Corpus
Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]
