在亚马逊基岩中使用Amazon Nova建立一致的故事板 - 第2部分

在这篇文章中,我们拍摄了由Amazon Web Services(AWS)FuzzyPixel制作的动画短片Picchu,通过提取关键角色框架来准备培训数据,并为主要角色Mayu和她的母亲进行微调模型,因此我们可以快速为新的序列产生诸如以下图像的新序列的故事板概念。

来源:亚马逊云科技 _机器学习
尽管仔细的提示手工制作可以产生良好的结果,但是实现专业级的视觉一致性通常需要调整基础模型本身。在此两部分系列的第1部分中涵盖的迅速工程和角色开发方法的基础上,我们通过微调亚马逊Nova Canvas Foundation Model(FM)来推动特定角色的一致性水平。 Through fine-tuning techniques, creators can instruct the model to maintain precise control over character appearances, expressions, and stylistic elements across multiple scenes.In this post, we take an animated short film, Picchu, produced by FuzzyPixel from Amazon Web Services (AWS), prepare training data by extracting key character frames, and fine-tune a character-consistent model for the main character Mayu and her mother, so we can quickly generate storyboard concepts for new续集像以下图像一样。解决概述以实现自动工作流程,我们提出了以下全面的解决方案体系结构,该架构使用AWS服务进行端到端实现。工作流程由以下步骤组成:用户将视频资产上传到亚马逊简单存储服务(Amazon Simple Storage Service selects those containing the character, and then center-crops them to produce the final character images.Amazon ECS invokes an Amazon Nova model (Amazon Nova Pro) from Amazon Bedrock to create captions from the images.Amazon ECS writes the image captions and metadata to the S3 bucket.The user uses a notebook environment in Amazon SageMaker AI to invoke the model training job.The user fine-tunes a custom Amazon Nova帆布模型通过调用Amazon Bedrock create_model_customization_job和create_model_provisioned_throughput api调用来创建可用于推断的自定义模型。此工作流程在两个不同的阶段结构。初始阶段,步骤