Sign in

Repository Index

56,139 visible repositories in the index

Tags: All Tags
Tags

A repository shows when it has any selected Tag.

Filters (1)

Filters

Clear all filters

241–264 of 1,239 · Most stars

Zonos-v0.1 is a leading open-weight text-to-speech model trained on more than 200k hours of varied multilingual speech, delivering expressiveness and quality on par with—or even surpassing—top TTS providers.

🔥 The fastest and powerful Python library for Instagram Private API 2026 with HikerAPI SaaS

  • instagram-api
  • instagram
  • instagram-client
  • instagram-downloader

TranslatedA voice input tool for PC with offline recognition, high accuracy and low latency, supporting hotwords and LLM polishing. Hold CapsLock or the mouse side button X2 and speak; release it and the text is entered on screen automatically.

[ICCV 2023] ProPainter: Improving Propagation and Transformer for Video Inpainting

  • object-removal
  • video-completion
  • video-inpainting
  • video-outpainting

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.

  • segment-anything
  • video-object-segmentation
  • interactive-tracking
  • track-anything

🔩 Like builtins, but boltons. 250+ constructs, recipes, and snippets which extend (and rely on nothing but) the Python standard library. Nothing like Michael Bolton.

Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022

  • document-ai
  • eccv-2022
  • multimodal-pre-trained-model
  • ocr

TranslatedFree proxy node aggregator. Daily updated vmess/vless/trojan/ss. Wall-climbing (bypassing the firewall), ladder (circumvention tool), scientific internet access (circumvention), airport subscriptions (proxy service subscriptions), network acceleration, VPN, no need to climb the wall, one-click import

TranslatedA pure-protocol reverse-engineered implementation of the ChatGPT official website interface. Supports the GPT-Image-2 model and text models, is compatible with the OpenAI API protocol, supports online batch image generation/image editing, account pool management, and reverse engineering of editable PPT/PSD files, supports importing CPA and sub2api account pools, and supports integration with software such as Cherry Studio and New Api

TranslatedAnti-getting-lost | 禁漫天堂 (JMComic, "Forbidden Manga Paradise") APK | 禁漫 (JMComic) app Android installation package | jm天堂 (JM Paradise) | 回家 (Going Home) | GitHub Actions | JMComic3 | JMComic2

[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.