Janus-Series: Unified Multimodal Understanding and Generation Models

An open-source implementation of MAVIS-SLAM.

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

DataComp for Language Models

Single Image to 3D using Cross-Domain Diffusion for 3D Generation

Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference

[ICCV2023] NeRF-LOAM: Neural Implicit Representation for Large-Scale Incremental LiDAR Odometry and Mapping

Infinite Photorealistic Worlds using Procedural Generation

[ICLR 2024 Spotlight] SyncDreamer: Generating Multiview-consistent Images from a Single-view Image

Official PyTorch implementation of the NeurIPS 2022 paper "Improving Diffusion Models for Inverse Problems using Manifold Constraints (https://arxiv.org/abs/2206.00941)"

🤖 AgentVerse 🪐 is designed to facilitate the deployment of multiple LLM-based agents in various applications, which primarily provides two frameworks: task-solving and simulation

MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion, NeurIPS 2023 (spotlight)

[ICCV 2023] VPD is a framework that leverages the high-level and low-level knowledge of a pre-trained text-to-image diffusion model to downstream visual perception tasks.

Generative Models by Stability AI

Generative Diffusion Prior for Unified Image Restoration and Enhancement (CVPR2023)

Nightly release of ControlNet 1.1

PyTorch Implementation of introducing diffusion approach to 3D depth perception ECCV 2024

[BMVC 2022] IronDepth: Iterative Refinement of Single-View Depth using Surface Normal and its Uncertainty

Text2Room generates textured 3D meshes from a given text prompt using 2D text-to-image models (ICCV2023).

Official Pytorch Implementation for "SceneScape: Text-Driven Consistent Scene Generation"

Official Code for DragGAN (SIGGRAPH 2023)

A unified framework for 3D content generation.

[SIGGRAPH Asia 2022] Text2Light: Zero-Shot Text-Driven HDR Panorama Generation

Asymmetric Tiling for stable-diffusion-webui

Tiled Diffusion and VAE optimize, licensed under CC BY-NC-SA 4.0

The wild west of cipherspace, welcome to DAOtown (WIP!!)

Official Pytorch Implementation for "MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation" presenting "MultiDiffusion" (ICML 2023)

Generate 3D objects conditioned on text or images

Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding