Stars
赛博小雅直播版 · 组件版数字人(Vidu s2)· 免费开源 AGPL-3.0 · 作者:天工开帧(抖音/B站/YouTube 同名)
Qwen3.8 27B on SGLang for DGX Spark
Qwen3.8 is the large language model series developed by Qwen team, Alibaba Group.
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
SGLang is a high-performance serving framework for large language models and multimodal models.
A framework for efficient model inference with omni-modality models
A high-throughput and memory-efficient inference and serving engine for LLMs
📖 A curated list of resources dedicated to talking face.
dacson / speechbrain
Forked from speechbrain/speechbrainA PyTorch-based Speech Toolkit
Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, ECBSR, etc. Also …
效果更好的补帧软件,显存占用更小,是DAIN速度的10-25倍,包含抽帧处理,去除动漫卡顿感
PyTorch code for "PSGAN: Pose and Expression Robust Spatial-Aware GAN for Customizable Makeup Transfer" (CVPR 2020 Oral)
[Experimental] Parse multipart/form-data in falcon
single channel speech separation for music vocal and accompany separate、voice reduce noise
Keras implementations of Generative Adversarial Networks.