Implementation of Make-A-Video, new SOTA text to video generator
Implementation of Video Diffusion Models
AI Upscaler for Blender using Real-ESRGAN
Based on the Disco Diffusion, version of the AI art creation software
Image/video AI upscaler app (BSRGAN)
The most powerful and modular diffusion model GUI, api and backend
NVR with realtime local object detection for IP cameras
Multimodal AI Story Teller, built with Stable Diffusion, GPT, etc.
InvokeAI is a leading creative engine for Stable Diffusion models
Convert AI papers to GUI
AI based photo editing website for changing image background
Implementation of Phenaki Video, which uses Mask GIT
Implementation of a U-net complete with efficient attention
A walk along memory lane
Implementation of NÜWA, attention network for text to video synthesis
Database system for building simpler and faster AI-powered application
The Triton Inference Server provides an optimized cloud
Implementation of Recurrent Interface Network (RIN)
CLIP + FFT/DWT/RGB = text to image/video
Data Lake for Deep Learning. Build, manage, and query datasets
Build AI-powered semantic search applications
Build cross-modal and multimodal applications on the cloud
Convert models from GoldSource engine to Source engine with AI
Notebooks, models and techniques for the generation of AI Art
Generate images from texts. In Russian