AI tools for Image Synthesis

Native-Resolution Image Synthesis (NiT) is a novel generative modeling paradigm that enables the synthesis of images at arbitrary resolutions and aspect ratios. Unlike conventio

Pixel3DMM is a fine-tuned DINO ViT for per-pixel surface normal and uv-coordinate prediction. It is designed for single-image 3D face reconstruction and exploits the latent feat

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

VACE is an all-in-one video creation and editing framework developed to unify multiple video synthesis and editing tasks into a single, versatile model. It supports a wide range

EasyControl is a novel framework designed to add efficient and flexible conditional control to Diffusion Transformer (DiT) models, addressing the challenges faced by the emergin

Lumina-mGPT 2.0 is a cutting-edge, stand-alone autoregressive model designed to unify a broad spectrum of image generation tasks into a single, cohesive framework. Built from sc

SkyReels-V2 is a state-of-the-art open-source video generation framework developed by Skywork AI that enables the creation of infinite-length cinematic videos with high visual a

Bokeh Diffusion is an advanced text-to-image diffusion model framework that enables precise and physically grounded control over defocus blur, commonly known as the bokeh effect

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

UNO is a universal image generation framework developed by ByteDance, aimed at providing content creators and designers with unprecedented control and flexibility in generating

MAGI-1 is a state-of-the-art open-source video generation model developed by Sand AI, designed to enable high-quality, controllable video creation from text prompts, images, or

ACTalker is an advanced end-to-end video diffusion framework designed for natural talking head video generation with unprecedented control and realism. Unlike traditional system

VideoDiT is an advanced video generation framework that bridges the gap between image diffusion transformers and video synthesis. By integrating a Distribution-Preserving Variat

WaveSpeedAI delivers ultra-fast AI-powered image and video generation through its proprietary inference framework, enabling enterprise-grade content creation at unprecedented sp

Waveloom is an advanced visual workflow platform that enables users to build and deploy complex AI-powered applications through an intuitive drag-and-drop interface. The platfor

OmniHuman is an advanced end-to-end multimodal human video generation framework developed by ByteDance. It enables the creation of highly realistic human videos from a single in

Speech Illustrator is an AI-driven platform designed to transform written text into engaging video content featuring realistic avatars. This tool caters primarily to educators,

RF-Inversion is an innovative AI-powered tool for semantic image inversion and editing using rectified stochastic differential equations. This cutting-edge technology addresses

FacePoke is an intuitive online tool designed for editing and animating facial expressions in images with remarkable precision and ease. Users can upload a clear, front-facing p

Google Imagen 3 is the latest iteration of Google's advanced text-to-image generation model, developed by Google DeepMind. This AI-powered tool represents a significant leap for