AI-Generated Presets for Faithful 4K Color Style Transfer in Real Time [CVPR 2023]

Official Implementation of "Control-A-Video: Controllable Text-to-Video Generation with Diffusion Models"

This repository provides motion datasets collected by Bandai Namco Research Inc

[ICCV 2023] Few shot font generation via transferring similarity guided global and quantization local styles

Ground-A-Video: Zero-shot Grounded Video Editing using Text-to-image Diffusion Models (ICLR 2024)

Make videos smooth!

Official PyTorch implementation of "EdgeSAM: Prompt-In-the-Loop Distillation for On-Device Deployment of SAM"

[CVPR2024] StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On

[NeurIPS 2024] SlimSAM: 0.1% Data Makes Segment Anything Slim

[CVPR 2024] Alpha-CLIP: A CLIP Model Focusing on Wherever You Want

[ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior

[ICLR'24 Spotlight] Uni3D: 3D Visual Representation from BAAI

GeoDream: Disentangling 2D and Geometric Priors for High-Fidelity and Consistent 3D Generation

Instant voice cloning by MIT and MyShell. Audio foundation model.

[CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

[ECCV 2024] FreeInit: Bridging Initialization Gap in Video Diffusion Models

Let us democratise high-resolution generation! (CVPR 2024)

[ECCV 2024] Official repo for UDiffText: A Unified Framework for High-quality Text Synthesis in Arbitrary Images via Character-aware Diffusion Models

ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation (NeurIPS 2023 Spotlight)

A unified framework for 3D content generation.

Refine high-quality datasets and visual AI models

End-2-end speech synthesis with recurrent neural networks

[ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

🔊 Text-prompted Generative Audio Model - With the ability to clone voices

[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.

The AI Knowledge Editor

Official implementation of paper "MiniGPT-5: Interleaved Vision-and-Language Generation via Generative Vokens"

ModelScope: bring the notion of Model-as-a-Service to life.