AI Forever

Kandinsky-2

Kandinsky 2 — multilingual text2image latent diffusion model

ghost

A new one shot face swap approach for image and video domains

Real-ESRGAN

PyTorch implementation of Real-ESRGAN model

Kandinsky-3

gigachain

⚡ Фреймворк для создания комплексных приложений с LLM ⚡

mgpt

Multilingual Generative Pretrained Model

KandinskyVideo

KandinskyVideo — multilingual end-to-end text2video latent diffusion model

sage

SAGE: Spelling correction, corruption and evaluation for multiple languages

deforum-kandinsky

Kandinsky x Deforum — generating short animations

ru-prompts

gigachat

Библиотека для доступа к GigaChat

MERA

MERA (Multimodal Evaluation for Russian-language Architectures) is a new open benchmark for the Russian language for evaluating fundamental models.

augmentex

Augmentex — a library for augmenting texts with errors

easy_sign

Easy_sign is an open source russian sign language recognition project that uses small CPU model for predictions and is designed for easy deployment via Streamlit.

DataProcessingFramework

Framework for processing and filtering datasets

gigaserve

GigaServe

KandiSuperRes

gigagraph

kandinsky3-diffusers

PHNet

Patch-based harmonization network

fsconnectors

gigagpts

deforumkandinsky.github.io

diffusers-new

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.

gigachain-elastic

Elasticsearch integration into GigaChain

gigachain-extract

🦜⛏️ Did you say you like data?

gigachain-google

gigadebug

🪢 Open source LLM engineering platform. Observability, metrics, evals, prompt management, testing, prompt playground, datasets, LLM evaluations -- 🍊YC W23 🤖 integrate via Typescript, Python / Decorators, OpenAI, Langchain, LlamaIndex, Litellm, Instructor, Mistral, Perplexity, Claude, Gemini, Vertex

kandinsky-video-1-1

mteb

MTEB: Massive Text Embedding Benchmark