aiXia121's repositories
AnyText
Official implementation code of the paper <AnyText: Multilingual Visual Text Generation And Editing>
Awesome-Chinese-LLM
整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。
comfy-flow-api
对ComfyUI的API进行的一层封装，并提供了微信小程序授权的API
comfy_mtb
Animation oriented nodes pack for ComfyUI
comfyui-deploy
An open source `vercel` like deployment platform for Comfy UI
ComfyUI-Depth-Anything-Tensorrt
ComfyUI Depth Anything Tensorrt Custom Node (up to 5x faster), licensed under CC BY-NC-SA 4.0
ComfyUI_LayerStyle
A set of nodes for ComfyUI that can composite layer and mask to achieve Photoshop like functionality.
cutword
一个简单快速的分词、命名实体识别工具
DecryptPrompt
总结Prompt&LLM论文，开源数据&模型，AIGC应用
DeepLabCut
Official implementation of DeepLabCut: Markerless pose estimation of user-defined features with deep learning for all animals incl. humans
EasyNLP
EasyNLP: A Comprehensive and Easy-to-use NLP Toolkit
facefusion
Next generation face swapper and enhancer
FollowYourClick
[arXiv 2024] Follow-Your-Click: This repo is the official implementation of "Follow-Your-Click: Open-domain Regional Image Animation via Short Prompts"
Fooocus
Focus on prompting and generating
generative-models
Generative Models by Stability AI
HanLP
中文分词 词性标注 命名实体识别 依存句法分析 成分句法分析 语义依存分析 语义角色标注 指代消解 风格转换 语义相似度 新词发现 关键词短语提取 自动摘要 文本分类聚类 拼音简繁转换 自然语言处理
HivisionIDPhotos
⚡️HivisionIDPhotos: a lightweight and efficient AI ID photos tools. 一个轻量级的AI证件照制作算法。
IC-Light
More relighting!
magi
Generate a transcript for your favourite Manga: Detect manga characters, text blocks and panels. Order panels. Cluster characters. Match texts to their speakers. Perform OCR.
MINI_LLM
This is a repository used by individuals to experiment and reproduce the pre-training process of LLM.
MiniGemini
Official implementation for Mini-Gemini
MusePose
MusePose: a Pose-Driven Image-to-Video Framework for Virtual Human Generation
OOTDiffusion
Official implementation of OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on
Open-Sora
Open-Sora: Democratizing Efficient Video Production for All
Prompt-Engineering-Guide
🐙 Guides, papers, lecture, notebooks and resources for prompt engineering
pytorch-fid
Compute FID scores with PyTorch.
Qwen1.5
Qwen1.5 is the improved version of Qwen, the large language model series developed by Qwen team, Alibaba Cloud.