Abhishek Maiti's repositories
stable-fashion
Stable Fashion: A prompt based virtual try on repository
replicate-img2img
Van Gogh style diffusion model on replicate
awesome-controlnets
List of awesome ControlNets with different conditionings
bookstore-copilot
A PoC of using Weaviate + DSPy to make a BookStore CoPilot
finetune-sd
Sample code and results for finetuning Stable Diffusion 1.5 using Huggingface
ACGPN
"Towards Photo-Realistic Virtual Try-On by Adaptively GeneratingโPreserving Image Content"๏ผCVPR 2020. (Modified from original with fixes for inference)
ailia-models
The collection of pre-trained, state-of-the-art AI models for ailia SDK
diffusers
๐ค Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch
dspy
DSPy: The framework for programmingโnot promptingโfoundation models
Flask-Web-App-Tutorial
Code for the note storing flask web app made during a YouTube video.
latex-css
LaTeX.css is a CSS library that makes your website look like a LaTeX document
MHFormer
[CVPR 2022] MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation
mrarkon.github.io
๐ My Portfolio Website | Powered by Hugo & PaperMod with tweaks
P-STMO
[ECCV2022] The PyTorch implementation for "P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimation"
PoseFormerV2
The project is an official implementation of our paper "PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation".
rembg
Rembg is a tool to remove images background.
stable-diffusion-webui
Stable Diffusion web UI
super-gradients
Easily train or fine-tune SOTA computer vision models with one open source training library. The home of Yolo-NAS.
ultralytics
NEW - YOLOv8 ๐ in PyTorch > ONNX > OpenVINO > CoreML > TFLite
VIBE
Official implementation of CVPR2020 paper "VIBE: Video Inference for Human Body Pose and Shape Estimation"
video-to-pose3D
Convert video to 3D pose in one-key.
yolov5
YOLOv5 ๐ in PyTorch > ONNX > CoreML > TFLite
yolov7
Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors