Tencent mixed yuan Wensheng graph large model open source training code, released LoRA and ControlNet p...

Tencent mixed Yuan large model

DIYuan | 2024-06-21 15:45

【數(shù)據(jù)猿導(dǎo)讀】 Tencent mixed yuan Wensheng graph large model open source training code, released LoRA and ControlNet plug-ins

June 21 news, Tencent mixed Yuan Wensheng Diagram large model (hereinafter referred to as mixed yuan DiT model) announced a comprehensive open source training code, while the external open source mixed yuan DiT LoRA small-scale data set training program and controllable plug-in ControlNet. Among them, LoRA model is a technology used to fine-tune large-scale language models. In Vincennes diagram model, users can use a small amount of data to train models with specific painting style, IP or character characteristics without modifying the original model or increasing the size of the model. ControlNet is a controlled generation algorithm for Vincennes that allows users to better control the generation of images by adding additional conditions. The release of the two model plug-ins means that enterprises and individual developers around the world can fine-tune code based on mixed DiT training or modify and optimize code based on mixed DiT, build their own applications based on this, and promote rapid iteration and innovation of technology.

來源：DIYuan

收藏分享

聲明：數(shù)據(jù)猿尊重媒體行業(yè)規(guī)范，相關(guān)內(nèi)容都會(huì)注明來源與作者；轉(zhuǎn)載我們原創(chuàng)內(nèi)容時(shí)，也請務(wù)必注明“來源：數(shù)據(jù)猿”與作者名稱，否則將會(huì)受到數(shù)據(jù)猿追責(zé)。