johndpope

John D. Pope's starred repositories

champ

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

Language:PythonMIT3977 223 114

ai-toolkit

Various AI scripts. Mostly Stable Diffusion stuff.

Language:PythonMIT2730 40 144

transformer-explainer

Transformer Explained Visually: Learn How LLM Transformer Models Work with Interactive Visualization

Language:JavaScriptMIT2606 27 15

magic-copy

Magic Copy is a Chrome extension that uses Meta's Segment Anything Model to extract a foreground object from an image and copy it to the clipboard.

Language:TypeScriptMIT2406 18 22

ComfyUI-AdvancedLivePortrait

Language:Python1348 7 33

DisCo

[CVPR2024] DisCo: Referring Human Dance Generation in Real World

Language:PythonApache-2.01051 42 98

x-flux-comfyui

Language:PythonApache-2.079600

MagicDance

[ICML 2024] MagicPose(also known as MagicDance): Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusion

Language:PythonNOASSERTION676 33 43

lollms

Lord of LLMS

Language:PythonApache-2.0264 15 16

GazeAnimationV2

Unsupervised High-Resolution Portrait Gaze Correction and Animation (TIP 2022)

Apache-2.0197 7 11

CFLD

[CVPR 2024 Highlight] Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesis

Language:Jupyter NotebookMIT165 5 31

neural_net_checklist

Language:PythonMIT137 10

segment-anything-services

Running segment-anything image embedding, prompting, and mask generation as torchserve services

Language:Jupyter NotebookApache-2.092 6 12

SAM2-UNet

SAM2-UNet: Segment Anything 2 Makes Strong Encoder for Natural and Medical Image Segmentation

Language:PythonApache-2.089 3 13

arxiv-frontpage

My personal frontpage app

Language:HTML74 2 2

relu_kan

Language:Python71 1 2

samapi

Segment Anything Model API

Language:PythonBSD-3-Clause70 2 14

X-Portrait

Source code for the SIGGRAPH 2024 paper "X-Portrait: Expressive Portrait Animation with Hierarchical Motion Attention"

Language:PythonApache-2.06700

LinguaLinker

LinguaLinker: Audio-Driven Portraits Animation with Implicit Facial Control Enhancement

Apache-2.05900

sdxl-comfyui-ultimate-workflow

Language:HTMLMIT51 4 5

idol

[ECCV 2024] IDOL: Unified Dual-Modal Latent Diffusion for Human-Centric Joint Video-Depth Generation

Apache-2.045 10

ttt-lm-kernels

Inference Speed Benchmark for Learning to (Learn at Test Time): RNNs with Expressive Hidden States

Language:Cuda32 3 2

TPoS

This repository is for The Power of Sound(TPoS): Audio Reactive Video Generation with Stable Diffusion (ICCV2023)

Language:Python1900

flux.1-dev-fp8

Inference app for a FP8-quantized flux1-dev model. This runs on graphic cards with 16 GB of VRAM.

Language:Python1100

SPiT

A Spitting Image: Modular Superpixel Tokenization in Vision Transformers

Language:Jupyter NotebookMIT8 3 1

DCAT

[ICCV 2023] Most Important Person-guided Dual-branch Cross-Patch Attention for Group Affect Recognition

Language:PythonMIT2 10

KAN-CUT

Language:Python100

wandb-scripts

Wandb scripts

Language:PythonMIT100

eden2

Language:Python100

ReLU_KAN_nanoGPT

Language:PythonMIT100