Chenxi

insanely-fast-whisper. Incredibly fast Whisper-large-v3

cog-RMBG. Fork of https://huggingface.co/briaai/RMBG-1.4

bark. 🔊 Text-Prompted Generative Audio Model

SUPIR. SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild

Kandinsky-2. Kandinsky 2 — multilingual text2image latent diffusion model

cog-whisper. Roff

cog-sd-txt2imghd. Stable-diffusion with Real-ESRGAN for upsampling

video-retalking. [SIGGRAPH Asia 2022] VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild

cog-themed-diffusion. Python

SadTalker. （CVPR 2023）SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

rembg. Rembg is a tool to remove images background.

rudalle-sr. A Cog implementation of the Real-ESRGAN super-resolution model from ruDALL-E.

OpenVoice. Instant voice cloning by MyShell.

i2vgen-xl. Official repo for VGen: a holistic video generation ecosystem for video generation building on diffusion models

Semantic-Segment-Anything. Automated dense category annotation engine that serves as the initial semantic labeling for the Segment Anything dataset (SA-1B).

Grounded-Segment-Anything. Marrying Grounding DINO with Segment Anything & Stable Diffusion & Tag2Text & BLIP & Whisper & ChatBot - Automatically Detect , Segment and Generate Anything with Image, Text, and Audio Inputs

cog-deforum-stable-diffusion. Python

cog-damo-text2video. Python

VideoCrafter. VideoCrafter1: Open Diffusion Models for High-Quality Video Generation

civitai2cog. Python

cog-Real-ESRGAN. Python

seamless_communication. Foundational Models for State-of-the-Art Speech and Text Translation

AudioSep. Official implementation of "Separate Anything You Describe"

CogVLM. a state-of-the-art-level open visual language model | 多模态预训练模型

fake-news-detection. AAAI ICWSM-2022 Evaluation of Fake News Detection with Knowledge-Enhanced Language Models

replicate-sd-textual-inversion. Python

ControlVideo. Official pytorch implementation of "ControlVideo: Training-free Controllable Text-to-Video Generation"

cog-pix2struct. Python

cog-point-e. OpenAI Point-E as a Cog model

Omost. Your image is almost there!

CosyVoice. Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

clip-guided-diffusion-pokemon. A Cog implementation of generating pixel artwork from a prompt using a diffusion model trained on pokemon sprites.

Lotus. Official Implementation of Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction

Sana. SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

demucs. Code for the paper Hybrid Spectrogram and Waveform Source Separation

AniPortrait. AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation

UnIVAL. Official implementation of UnIVAL: Unified Model for Image, Video, Audio and Language Tasks.

MeloTTS. High-quality multi-lingual text-to-speech library by MyShell.ai. Support English, Spanish, French, Chinese, Japanese and Korean.

ZoeDepth. Metric depth estimation from a single image

face-alignment-cog. Python

PixArt-sigma. PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

OminiControl. A minimal and universal controller for FLUX.1.

DeepSeek-VL2. DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

pix2pix-zero. Python

Prompt-Free-Diffusion. Prompt-Free Diffusion: Taking "Text" out of Text-to-Image Diffusion Models

CogVideo. Text-to-video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

Cutie. [arXiv 2023] Putting the Object Back Into Video Object Segmentation

cog-sd-textual-inversion. Python

InternLM-XComposer. Python

ml-depth-pro. Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.

cog-I2VGen-XL. Python

clip-guided-diffusion. A Cog implementation of CLIP Guided Diffusion

T2I-Adapter. T2I-Adapter

cog-ledits. Python