据悉,阿里云通义实验室正式开源Z-Image基座模型。该模型参数量为60亿(6B),属非蒸馏原生架构,完整保留权重分布,原生支持CFG(Classifier-Free Guidance)引导机制,可直接作为LoRA、ControlNet等图像生成微调任务的训练底座。此举旨在降低高质量图像生成模型的研发与定制门槛,推动电商等垂直场景的AIGC应用落地。
特别声明:以上内容(如有图片或视频亦包括在内)为自媒体平台“网易号”用户上传并发布,本平台仅提供信息存储服务。
Notice: The content above (including the pictures and videos if any) is uploaded and posted by a user of NetEase Hao, which is a social media platform and only provides information storage services.