mr-harry Goto Github PK

2d_audio_driven_digital_human

第十四届全国大学生服务外包创新创业大赛企业类命题A15-2d虚拟人语音驱动算法

4k4d

4K4D: Real-Time 4D View Synthesis at 4K Resolution

ai-

AI视频创作，开发使用python支持多国语音配音，ffmpeg+openai-whisper+tts，项目仅作参考,技术探讨研究，拒绝非法使用

animateanyone

Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation

animesr

Codes for "AnimeSR: Learning Real-World Super-Resolution Models for Animation Videos"

awesome-video-diffusion-models

[Arxiv] A Survey on Video Diffusion Models

boxdiff-xl

Extend BoxDiff to SDXL (SDXL-based layout-to-image generation)

chinese-llama-alpaca-2

中文LLaMA-2 & Alpaca-2大模型二期项目 + 16K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs, including 16K long context models)

cogvideo

Text-to-video generation. The repo for ICLR2023 paper "CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers"

cogvlm

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

dynamicrafter

DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors

emo

facefusion

Next generation face swapper and enhancer

focus-on-your-instruction

Focus on Your Instruction: Fine-grained and Multi-instruction Image Editing by Attention Modulation

generative-models

Generative Models by Stability AI

ic-light

More relighting!

instantid

InstantID : Zero-shot Identity-Preserving Generation in Seconds 🔥

interactdiffusion

[CVPR 2024] Official repo for "InteractDiffusion: Interaction-Control for Text-to-Image Diffusion Model".

latte

The official implementation of Latte: Latent Diffusion Transformer for Video Generation.

lgm

LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation.

lumina-t2x

Lumina-T2X is a unified framework for Text to Any Modality Generation

lwm

mamba

A simple and efficient Mamba implementation in PyTorch and MLX.

mambatransformer

Integrating Mamba/SSMs with Transformer for Enhanced Long Context and High-Quality Sequence Modeling

minidocx

minisora

The Mini Sora project aims to explore the implementation path and future development direction of Sora.

mnbvc

MNBVC(Massive Never-ending BT Vast Chinese corpus)超大规模中文语料集。对标chatGPT训练的40T数据。MNBVC数据集不但包括主流文化，也包括各个小众文化甚至火星文的数据。MNBVC数据集包括新闻、作文、小说、书籍、杂志、论文、台词、帖子、wiki、古诗、歌词、商品介绍、笑话、糗事、聊天记录等一切形式的纯文本中文数据。

motionctrl

oneto3d

OneTo3D: One Image to Editable Dynamic 3D Model and Video Generation

open-sora

Open-Sora: Democratizing Efficient Video Production for All