AI tools for Code Quality

Artlist.io is an all-in-one subscription platform catering primarily to video creators, filmmakers, and social media content producers who require high-quality digital assets un

Macabacus delivers a suite of tools designed to revolutionize workflows within the Microsoft 365 environment. Leveraging the power of modern technology, it streamlines writing p

In the fast-paced world of software development, maintaining code quality and swiftly merging changes are paramount. Codoki is designed to address these challenges head-on, offe

Qwen-Image-Edit is an advanced image editing model built upon the robust 20B Qwen-Image foundation model. It excels in precise text editing capabilities, allowing for bilingual

NVIDIA Nemotron Nano 2 is an advanced family of hybrid Mamba-Transformer large language models (LLMs) designed to push the boundaries of reasoning accuracy while delivering sign

FLUX.1 Krea [dev] is a 12B param. rectified-flow model distilled from Krea 1, a research collaboration between Krea and Black Forest Labs. The model is designed to offer superio

Yume is an interactive world generation model that creates dynamic worlds from images, text, or videos, allowing exploration and control via peripheral devices or neural signals

Diffuman4D is a novel approach to 4D consistent human view synthesis from sparse-view videos. It enables high-fidelity free-viewpoint rendering of human performances from sparse

Direct3D-S2 is a scalable 3D generation framework based on sparse volumes that achieves superior output quality with dramatically reduced training costs. It introduces a Spatial

OmniConsistency is a model-agnostic framework that enables style-agnostic consistency from paired stylization data. It is a code implementation of the paper 'OmniConsistency: Le

Moondream is a cutting-edge open-source visual language model designed to bring advanced image understanding to a wide range of applications. Unlike traditional computer vision

OpenAI Codex is a cutting-edge AI-powered coding assistant designed to streamline and revolutionize the software development process. Built on the codex-1 model, which is a spec

Step1X-3D is an open framework for high-fidelity and controllable generation of textured 3D assets. It addresses the challenges of data scarcity, algorithmic limitations, and ec

PixelHacker is a diffusion-based model designed for image inpainting with structural and semantic consistency. Recent state-of-the-art methods have explored novel attention mech

ACE-Step is a next-generation open-source music generation foundation model designed to bridge the gap between speed, coherence, and creative control in digital music production

Qwen3 is the latest generation of large language models developed by Alibaba Group, designed to deliver exceptional performance across a wide range of reasoning, language unders

EdgeTAM is a research-driven framework developed by Facebook Research that focuses on efficient and accurate semantic segmentation, particularly tailored for edge devices. The c

FantasyTalking is a cutting-edge framework for generating realistic talking portrait videos from a single static image and an audio track. Built upon a powerful video diffusion

StdGEN is an innovative pipeline designed to generate semantically decomposed, high-quality 3D characters from single images, significantly advancing the fields of virtual reali

SkyReels-A2 is an advanced open-source video generation framework that excels in creating controllable, high-quality videos by synthesizing multiple visual elements such as char

Hi3DGen is a cutting-edge framework designed to generate high-fidelity 3D geometry from single 2D images by leveraging a novel normal bridging technique. Traditional methods oft