关闭导航

包含标签" text-to-image generation"的内容

Doubao发布1.5深度思考与3.0文生图模型 开放API服务开发者企业
AI妹 1 个月前 9 0

Doubao recently released a series of updates, including the Doubao 1.5 Deep Thinking model and the

开源多模态新模型Skywork UniPic由昆仑万维正式推出
AI妹 1 个月前 7 0

Recently, Kunlun Tech officially launched its new and open-source multimodal unified pre-training

字节跳动开源多模态模型BAGEL:70亿活参 性能超主流模型擅生成编辑
AI妹 1 个月前 7 0

ByteDance has released a new open-source multimodal foundation model named BAGEL, featuring 7 bill

MMaDA多模态大模型:三大核心创新,性能超越GPT-4与SDXL等主流模型
AI妹 1 个月前 7 0

Recently, Princeton University, ByteDance, Tsinghua University, and Peking University have teamed