johndpope

VASA-1-hack

Using Claude Opus to reverse engineer code from VASA white paper - WIP - (this is for La Raza 🎷)

MegaPortrait-hack

Using Claude Opus to reverse engineer code from MegaPortraits: One-shot Megapixel Neural Head Avatars

SPEAK-hack

Using Claude Sonnet to reverse engineer paper Listen, Disentangle, and Control: Controllable Speech-Driven Talking Head Generation

MegaPortrait

Implementation of Megaportrait

fsrt

Official implementation of the CVPR 2024 paper "FSRT: Facial Scene Representation Transformer for Face Reenactment from Factorized Appearance, Head-pose, and Facial Expression Features"

MRLR

A MULTI-RESOLUTION LOW-RANK TENSOR DECOMPOSITION - https://arxiv.org/pdf/2406.18560

ToonCrafter

a research paper for generative cartoon interpolation

AniFaceDiff-hack

ardit-tts.github.io

BIRD

This is the official implementation of "Blind Image Restoration via Fast Diffusion Inversion"

CIPSWithEfficientAttention

ComfyUI-StableAudioSampler

The New Stable Diffusion Audio Sampler 1.0 In a ComfyUI Node. Make some beats!

ComfyUI-V-Express

comparisonics-hack

CSCS

[ACM TOG, 2024] Identity-Preserving Face Swapping via Dual Surrogate Generative Models

DiffPortrait3D

Official Repository of [CVPR'24 Highlight Diffportrait3D: Controllable Diffusion for Zero-Shot Portrait View Synthesis]

Director3D

Code for "Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text".

DiscoPOP

Code for Discovering Preference Optimization Algorithms with and for Large Language Models

DMD2

EDTalk

[ECCV 2024] EDTalk - Official PyTorch Implementation

flops-profiler

pytorch-profiler

HPENet-hack

Using Claude Opus to reverse engineer code from white paper

LadaGAN-pytorch

Efficient generative adversarial networks using linear additive-attention Transformers

LazyCIPSGenerator

mash up of CIPS generator and lazy diffusion

MegFaceAnimate

mindiffusion

Repository of lessons exploring image diffusion models, focused on understanding and education.

representation-space-info-comparison

Code accompanying "Comparing information content of representation spaces for disentanglement with VAE ensembles"

sdfa-2019

PyTorch Implementation of our paper "Speech-Driven Facial Animation with Spectral Gathering and Temporal Attention" published in Springer FCS.

talkinghead

V-Express

V-Express aims to generate a talking head video under the control of a reference image, an audio, and a sequence of V-Kps images.