AMEERAZAM08

OpenVoice

Instant voice cloning by MyShell.

llm.c

LLM training in simple, raw C/CUDA

AniPortrait

AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation

SyncTalk

[CVPR 2024] This is the official source for our paper "SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis"

StreamingT2V

StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text

ConsistentID

Customized ID Consistent for human

SVD_Xtend

Stable Video Diffusion Training Code and Extensions.

lightning-whisper-mlx

An extremely fast implementation of whisper optimized for Apple Silicon using MLX.

GP-VTON

Official Implementation for CVPR2023 paper "GP-VTON: Towards General Purpose Virtual Try-on via Collaborative Local-Flow Global-Parsing Learning"

LargeLanguageModelsProjects

Large Language Model Projects

FLAME-Universe

Summary of publicly available ressources such as code, datasets, and scientific papers for the FLAME 3D head model

ImagenHub

A one-stop library to standardize the inference and evaluation of all the conditional image generation models. (ICLR 2024)

MVDiffusion_plusplus

MVDiffusion++: A Dense High-resolution Multi-view Diffusion Model for Single or Sparse-view 3D Object Reconstruction

Make-Your-3D

[ECCV 2024] Make-Your-3D: Fast and Consistent Subject-Driven 3D Content Generation

singing-songstarter

Sing an idea ➡️ AI music sample🔥🎶

CVTHead

[WACV 2024] "CVTHead: One-shot Controllable Head Avatar with Vertex-feature Transformer"

DragNoise

[CVPR2024] Official code for Drag Your Noise: Interactive Point-based Editing via Diffusion Semantic Propagation

LipSync3D

StyleCineGAN

StyleCineGAN: Landscape Cinemagraph Generation using a Pre-trained StyleGAN [CVPR 2024]

TryOn-Adapter

Official repository for our paper, "TryOn-Adapter: Efficient Fine-Grained Clothing Identity Adaptation for High-Fidelity Virtual Try-On"

DCP-GAN

[CVPR 2024] Diversity-aware Channel Pruning for StyleGAN Compression

AnimateZoo

AURA

AURA is an innovative assistant designed to revolutionize the way students learn. Harnessing Pathway's cutting-edge LLMApp capabilities, AURA architecturally weaves real-time, Large Language Model-driven data pipelines in Python, amalgamating diverse input sources.

res-adapter

Official implementation of "ResAdapter: Domain Consistent Resolution Adapter for Diffusion Models".

champ

Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance

ConsistentID

Customized ID Consistent for human

DragAnything

Official code for 'DragAnything: Motion Control for Anything using Entity Representation'

GaussianAvatars

Official repo for "GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians"

InstantStyle

ML-QA