momalave Goto Github PK

3d-ken-burns

an implementation of 3D Ken Burns Effect from a Single Image using PyTorch

basicsr

Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, etc. Also support StyleGAN2, DFDNet.

braineeg

c3d

C3D is a modified version of BVLC caffe to support 3D ConvNets.

codeformer

[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer

controlnet-v1-1-nightly

Nightly release of ControlNet 1.1

deep-search

Deep learning-powered search service to find segments of videos

demo-self-driving

Streamlit app demonstrating an image browser for the Udacity self-driving-car dataset with realtime object detection using YOLO.

densecap

Dense image captioning in Torch

densecap-1

Dense captioning with joint inference and visual context

densecap-2

Dense video captioning in PyTorch

densecap4rank

In this project, dense captioning is used to index/rank videos.

denserelationalcaptioning

Code of Dense Relational Captioning

densevid_eval

Evaluation code for Dense-Captioning Events in Videos

densevideocaptioning

Official Tensorflow Implementation of the paper "Bidirectional Attentive Fusion with Context Gating for Dense Video Captioning" in CVPR 2018, with code, model and prediction results.

draggan

Official Code for DragGAN (SIGGRAPH 2023)

dreambooth-stable-diffusion

Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion

dynamic3dgaussians

fast_blind_video_consistency

Learning Blind Video Temporal Consistency (ECCV 2018)

gfpgan

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

gigagan-pytorch

Implementation of GigaGAN, new SOTA GAN out of Adobe

grounded-video-description

Video Grounding and Captioning

image-super-resolution-via-iterative-refinement

Unofficial implementation of Image Super-Resolution via Iterative Refinement by Pytorch

imagestackalignator

Implementation of Google's Handheld Multi-Frame Super-Resolution algorithm (from Pixel 3 and Pixel 4 camera)

mat

MAT: Mask-Aware Transformer for Large Hole Image Inpainting

mediapipe

MediaPipe is a cross-platform framework for building multimodal applied machine learning pipelines

mingpt

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

minigpt-4

MiniGPT-4: Enhancing Vision-language Understanding with Advanced Large Language Models

mlc-llm

Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.

mystyle