Overview
Zhizi Engine researches and develops multimodal large models and released Yuanchengxiang ChatImg, its first application-level multimodal ChatGPT product. With tens of billions of parameters, it mainly trains on image–text pairs and VQA data, jointly learning image–text matching, retrieval, image captioning and text description generation. From images or text, it can chat, tell stories and write advertisements.
Connected profiles
Explore
More Video generation products
Sources · 0Sources & provenance
English text is maintained separately from the original record. Consult the original source before citing a fact.
No source links are available for this profile.
Original source text
Names may use phonetic renderings when no English name is supplied. The original wording is retained below.
智子引擎是一家多模态大模型研究和开发商,发布了第一款应用级多模态ChatGPT产品“元乘象 ChatImg”。“元乘象ChatImg”的参数量在百亿级别,主要使用了图文对数据和VQA数据作为训练集,同时进行图文匹配、图文检索、图像描述生成、文本描述生成等多种任务的训练。根据用户输入的图片或文字,“元乘象ChatImg”可以进行智能聊天、讲故事、写广告等。