real time face swap and one-click video deepfake with only a single image

Models and examples built with TensorFlow

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…

The original local LLM interface. Text, vision, tool-calling, training, and more. 100% offline.

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, Anthr…

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

Let us control diffusion models!

DALL·E Mini - Generate images from a text prompt

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor…

Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch

Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.

An open source multi-tool for exploring and publishing data

Semantic cache for LLMs. Fully integrated with LangChain and llama_index.

ClearML - Auto-Magical CI/CD to streamline your AI workload. Experiment Management, Data Management, Pipeline, Orchestration, Scheduling & Serving in one MLOps/LLMOps solution

[SIGGRAPH Asia 2024, Journal Track] ToonCrafter: Generative Cartoon Interpolation

Supercharge Your Model Training

A minimal Python framework for building custom AI inference servers with full control over logic, batching, and scaling.

🌊 A Human-in-the-Loop workflow for creating HD images from text

An unofficial styleguide and best practices summary for PyTorch

NeurIPS 2025 Spotlight; ICLR2024 Spotlight; CVPR 2024; EMNLP 2024

Fake Blender Python API module collection for the code completion.

Code and models for the paper "One Transformer Fits All Distributions in Multi-Modal Diffusion"

Used for AI model generation, next-generation Blender rendering engine, texture enhancement&generation (based on ComfyUI)

Official code for "Towards An End-to-End Framework for Flow-Guided Video Inpainting" (CVPR2022)

realtime motion tracking in blender using mediapipe and rigify

[SIGGRAPH'22] StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets

Transfer the ControlNet with any basemodel in diffusers🔥

Sketch Your Own GAN: Customizing a GAN model with hand-drawn sketches.

A port of GOBIG for Stable Diffusion