- Durham, NC
- @pbaylies
Stars
Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, sparsely activated memory layers complement compute-heavy dense f…
Open Source API and interchange format for editorial timeline information.
State Management and Multiplayer Networking for Turn-Based Games
Render images in the terminal with Textual and rich
An 8-step inversion and 8-step editing process works effectively with the FLUX-dev model. (3x speedup with results that are comparable or even superior to baseline methods)
Official PyTorch implementation of paper "CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up".
This is a PyTorch-based reimplementation of CrossFlow, as proposed in 'Flowing from Words to Pixels: A Framework for Cross-Modality Evolution'
LOTUS: A semantic query engine for fast and easy LLM-powered data processing
ResiDual: Transformer with Dual Residual Connections, https://arxiv.org/abs/2304.14802
A generative world for general-purpose robotics & embodied AI learning.
Zero-Shot Monocular Depth Completion with Guided Diffusion
FastVideo is an open-source framework for accelerating large video diffusion model.
EDM2 and Autoguidance -- Official PyTorch implementation
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
A ComfyUI custom node that loads and applies B-LoRA models.
A JSON-like data structure (a CRDT) that can be modified concurrently by different users, and merged again automatically.
A geometry-shader-based, global CUDA sorted high-performance 3D Gaussian Splatting rasterizer. Can achieve a 5-10x speedup in rendering compared to the vanialla diff-gaussian-rasterization.
[SIGGRAPH Asia 2023 (Technical Communications)] EasyVolcap: Accelerating Neural Volumetric Video Research
Text and image to video generation: Kandinsky 4.0 (2024)
Large Concept Models: Language modeling in a sentence representation space
This repository provides a comprehensive benchmark for evaluating the performance of neural watermarking techniques. The benchmark includes a variety of datasets, evaluation metrics, and tools for …
Open and efficient video watermarking
Code for NeurIPS 2024 paper - The GAN is dead; long live the GAN! A Modern Baseline GAN - by Huang et al.
[2024-NeurIPS] TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Control
Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation".
[ECCV 2024] OMG: Occlusion-friendly Personalized Multi-concept Generation In Diffusion Models