为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…

Custom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)

Official PyTorch codes for the paper: "ViCo: Detail-Preserving Visual Condition for Personalized Text-to-Image Generation"

SSD-1B, an open-source text-to-image model, outperforming previous versions by being 50% smaller and 60% faster than SDXL.

Implementation of Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

A realtime sketch to image demo using LCM and the gradio library.

A Compressed Stable Diffusion for Efficient Text-to-Image Generation [ECCV'24]

Faster Whisper transcription with CTranslate2

Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference

Latent Consistency Model for AUTOMATIC1111 Stable Diffusion WebUI

BlueLM(蓝心大模型): Open large language models developed by vivo AI Lab

Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures.