Surya T - Secondary's repositories
ArtSpew
An infinite number of monkeys randomly throwing paint at a canvas
cog-InterpAny-Clearer
Cog wrapper for zzh-tech / InterpAny-Clearer
cog-kandinsky-v3.0-text2img-img2img
Kandinsky v3.0 model (repository for replicate.com)
comprehensive-rust
Rust tutorial
DemoFusion
Let us democratise high-resolution generation! (arXiv 2023)
edge-tts
Use Microsoft Edge's online text-to-speech service from Python WITHOUT needing Microsoft Edge or Windows or an API key
EdgeSAM
Official PyTorch implementation of "EdgeSAM: Prompt-In-the-Loop Distillation for On-Device Deployment of SAM"
faster-lcm
Faster LCM is a script which enables to transfer image styles at more than 30fps with A100.
gpt-fast
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
hibp
Go library for HaveIBeenPwned.org's pwned passwords API.
llamafile
Distribute and run LLMs with a single file.
magic-animate
MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model
open-iris
Open Iris Recognition Inference System (IRIS)
open-resume
OpenResume is a powerful open-source resume builder and resume parser. https://open-resume.com/
openvino_notebooks
📚 Jupyter notebook tutorials for OpenVINO™
oslash
OSlash is an open-source browser extension that lets you convert your URLs into simple, readable, and memorable shortcuts. Contact opensource@oslash.com for support
OutfitAnyone
Outfit Anyone: Ultra-high quality virtual try-on for Any Clothing and Any Person
pdf-appliance
Auto start machines that will generate PDFs for your application
playground-v2-1024px-aesthetic
Playground v2 is a diffusion-based text-to-image generative model. The model was trained from scratch by the research team at Playground.
pypush
Cross-platform iMessage POC
restate
Restate server and CLI
stylex
StyleX is the styling system for ambitious user interfaces.
svd-playground
A repo for SVD experiments
virtual-kubelet
Virtual Kubelet is an open source Kubernetes kubelet implementation.
voice-cloning-create-dataset
Create your own RVC v2 dataset from a youtube video
voice-cloning-training
Voice data <= 10 mins can also be used to train a good VC model!