Viacheslav Ivannikov

stable-diffusion. Jupyter Notebook

stable-diffusion-webui. Stable Diffusion web UI (neonsecret fork)

TTS-With-Voice-Cloning-Multilang. Clone a voice in a few seconds to generate arbitrary speech in real-time in multiple languages

neonpeacasso. Stable diffusion UI interface for experimenting with multimodal (text, image) models, GUI application

IF. Python

ai-challenge-legal. ARLC 2026 Agentic RAG Legal Challenge — Legal QA pipeline for DIFC court documents. Hybrid BM25 + vector retrieval, cross-encoder reranking, answer-grounded page verification.

xformers. Hackable and optimized Transformers building blocks, supporting a composable construction.

DiTFusion. PyTorch Implementation of "Scalable Diffusion Models with Transformers" with author's tweaks

Youtube-Video-Neural-Dubbing. Youtube video dubbing using machine learning

stable_diffusion-ait. Python

Q-Tacotron. Q-Tacotron implementation using Google's TPGST

animatediff-cli. i did a thing

sample-generator. Tools to train a generative model on arbitrary audio samples

Dreambooth-Stable-Diffusion. Implementation of Dreambooth (neon's tweaks) (https://arxiv.org/abs/2208.12242) with Stable Diffusion (tweaks focused on training faces)

t5-inq-rep. Jupyter Notebook

Cross-Lingual-Voice-Cloning. For monolingual voice cloning, see https://github.com/neonsecret/Real-Time-Voice-Cloning-Multilang