Sani's starred repositories
Retrieval-based-Voice-Conversion-WebUI
Easily train a good VC model with voice data <= 10 mins!
PentestGPT
A GPT-empowered penetration testing tool
Track-Anything
Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.
Segment-Everything-Everywhere-All-At-Once
[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"
segment-geospatial
A Python package for segmenting geospatial data with the Segment Anything Model (SAM)
awesome-pretrained-models-for-information-retrieval
A curated list of awesome papers related to pre-trained models for information retrieval (a.k.a., pretraining for IR).
sd-webui-image-sequence-toolkit
Extension for AUTOMATIC111's WebUI
godot-dodo
Finetuning large language models for GDScript generation.
MachineLearning-DeepLearning-Code-for-my-YouTube-Channel
The full collection of all codes for my Youtube Channel segregated as per topic.
wait-but-why-gpt
AI search & chat for all Wait But Why posts.
segment-anything-u-specify
using clip and sam to segment any instance you specify with text prompt of any instance names
LLIE_Survey
Resources for our paper "Low-Light Image and Video Enhancement: A Comprehensive Survey and Beyond"
fold
πͺ A fast Adaptive Machine Learning library for Time-Series, that lets you build, deploy and update composite models easily. An order of magnitude speed-up, combined with flexibility and rigour. This is an internal project - documentation is not updated anymore and substantially differ from the current API.
losslessmix
Mixing models of stable diffusion without weights loss
icecube-2nd-place
Code for 2nd Place Icecube neutrino competition
text2phoneme
ζ₯ζ¬θͺζγι³η΄ εγΈε€ζγγγΉγ―γͺγγ