Store

Code for the paper "Language Models are Unsupervised Multitask Learners"

VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models

moondream1 is a tiny (1.6B parameter) vision language model trained by @vikhyatk that performs on par with models twice its size. It is trained on the LLaVa training dataset, and initialized with SigLIP as the vision tower and Phi-1.5 as the text encoder. https://huggingface.co/spaces/vikhyatk/moondream1

Wav2Lip UHQ extension for Automatic1111

Unofficial Re-Trained AnimateAnyone (Image + DWPose Video → Animated Video of Image)

nsfw protection bypass for the Next generation face swapper and enhancer

PhotoMaker

Contribute to candywrap/Moore-AnimateAnyone-for-windows development by creating an account on GitHub.

Convert your videos to densepose and use it on MagicAnimate

Useful tool to track location or mobile number

Massively Multilingual Speech (MMS): Persian Text-to-Speech

Efficiently separate audio tracks with Spleeter

Focus on prompting and generating

[ICLR 2024 Oral] Generative Gaussian Splatting for Efficient 3D Content Creation

Next generation face swapper and enhancer

Contribute to MuriloTroll/Uncensored_Facefusion development by creating an account on GitHub.

A colab gradio web UI for running Large Language Models

Unlock the new experience of Housing App Android Setup with Automation using Pinokio

Contribute to sunilkumardash9/voice-clone-and-lip-sync development by creating an account on GitHub.

"Effective Whole-body Pose Estimation with Two-stages Distillation" (ICCV 2023, CV4Metaverse Workshop)