AWS nova documentation change
Summary
Added AWS workshops links, GitHub resources, and updated model catalog entries including new Amazon Nova Premier model and extended video duration for Nova Reel
Security assessment
Changes focus on adding educational resources and updating model specifications without mentioning security controls, vulnerabilities, or security best practices. The Nova Reel duration extension (6s → 2m) and model ID format changes (removed 'us.' prefix) are feature updates rather than security-related modifications.
Diff
diff --git a/nova/latest/userguide/additional-resources.md b/nova/latest/userguide/additional-resources.md index 01a6fcb57..c2fa0963e 100644 --- a//nova/latest/userguide/additional-resources.md +++ b//nova/latest/userguide/additional-resources.md @@ -7 +7,25 @@ -The following resources will help you when using Amazon Nova. +The following AWS Workshops are available for Amazon Nova: + + * [Unleashing Creativity: Mastering Nova Canvas and Nova Reel for creative success](https://catalog.us-east-1.prod.workshops.aws/workshops/66a0984a-ad2b-481f-a1cf-e7896ea9595b/en-US) + + * [Amazon Nova multimodal understanding workshop](https://catalog.us-east-1.prod.workshops.aws/workshops/012d9c20-25dc-4065-bdb6-50e935e8bd9f) + + * [Amazon Nova Sonic (speech-to-speech) Workshop](https://catalog.us-east-1.prod.workshops.aws/workshops/5238419f-1337-4e0f-8cd7-02239486c40d/) + + + + +The following GitHub resources are available for Amazon Nova: + + * [Multimodal generation examples](https://github.com/aws-samples/amazon-nova-samples/tree/main/multimodal-generation) + + * [Multimodal understanding examples](https://github.com/aws-samples/amazon-nova-samples/tree/main/multimodal-understanding) + + * [Speech to speech examples](https://github.com/aws-samples/amazon-nova-samples/tree/main/speech-to-speech) + + * [Amazon Nova samples repository](https://github.com/aws-samples/amazon-nova-samples/tree/main) + + + + +The following documentation resources will help you when using Amazon Nova. @@ -32,10 +56,11 @@ AWS Foundation Model Catalog Model | Model ID | Description | Status | Release d -Amazon Nova Pro | us.amazon.nova-pro-v1:0 | Amazon Nova Pro is designed for highly complex use cases requiring advanced reasoning, creativity, and code generation. The model supports image, video, and text inputs and outputs text. | Active | 12/2/2024 | 300k | Text, Image, Video | Text -Amazon Nova Lite | us.amazon.nova-lite-v1:0 | Amazon Nova Lite balances intelligence, latency, and cost-effectiveness. It's optimized for complex scenarios where low latency (minimal delay) is crucial, such as interactive agents that need to orchestrate multiple tool calls simultaneously. The model supports image, video, and text inputs and outputs text. | Active | 12/2/2024 | 300k | Text, Image, Video | Text -Amazon Nova Micro | us.amazon.nova-micro-v1:0 | Amazon Nova Micro is the fastest and most affordable option, optimized for large-scale, latency-sensitive deployments like conversational interfaces, chats, and high-volume tasks, such as classification, routing, entity extraction, and document summarization. | Active | 12/2/2024 | 128k | Text | Text -Amazon Nova Canvas | us.amazon.nova-canvas-v1:0 | Amazon Nova Canvas allows users to leverage reference images to guide image generation, where the output image aligns with the layout and composition of the reference image while still following the textual prompt. Users can create images that match their text-based descriptions by simply inputting natural language prompts. Furthermore, they can upload and edit existing images, including applying text-based prompts without the need for a mask, or editing specific parts of an image using an image or text mask. The model also supports outpainting, which extends the boundaries of an image, and inpainting, which fills in missing areas. It offers the ability to generate variations of an image based on an optional text prompt, as well as instant customization options that allow users to transfer styles using reference images or combine styles from multiple references, all without requiring any fine-tuning. | Active | 12/2/2024 | | Text, Image | Image -Amazon Nova Reel | us.amazon.nova-reel-v1:1 | Amazon Nova Reel allows users to generate videos from a natural language text prompt and an included reference image. The model allows you to generate realistic, studio-quality videos by using text- and image-based prompts. The model supports text-to-video generation and text-and-image to-video generation. Videos are generated at 1280x720 resolution, 24 frames per second, and with a duration of 6 seconds. | Active | 12/2/2024 | | Text, Image | Video -Titan image generator V2 | us.amazon.titan-image-generator-v2:0 | Titan Image Generator v2 supports all the existing features of Titan Image Generator v1 and adds several new capabilities. It allows users to leverage reference images to guide image generation, where the output image aligns with the layout and composition of the reference image while still following the textual prompt. It also includes an automatic background removal feature, which can remove backgrounds from images containing multiple objects without any user input. The model provides precise control over the color palette of generated images, allowing users to preserve a brand's visual identity without the requirement for additional fine-tuning. Additionally, the subject consistency feature enables users to fine-tune the model with reference images to preserve the chosen subject (e.g., pet, shoe, or handbag) in generated images. This comprehensive suite of features empowers users to unleash their creative potential and bring their imaginative visions to life. | Active | 8/6/2024 | Text: 512 char Image: 5mb | Text, Image | Image -Titan Text Premier | us.amazon.titan-text-premier-v1:0 | Premier is a large language model for text generation. It is useful for a wide range of tasks including open-ended and context-based question answering, code generation, and summarization. This model is integrated with Amazon Bedrock Knowledge Base and Amazon Bedrock Agents. The model also supports Custom Finetuning in preview. | Active | 5/7/2024 | 32k | Text | Text -Titan image generator V1 | us.amazon.titan-image-generator-v1 | Amazon Titan Image Generator v1 enables users to generate and edit images in versatile ways. Users can create images that match their text-based descriptions by simply inputting natural language prompts. Furthermore, they can upload and edit existing images, including applying text-based prompts without the need for a mask, or editing specific parts of an image using an image mask. The model also supports outpainting, which extends the boundaries of an image, and inpainting, which fills in missing areas. It offers the ability to generate variations of an image based on an optional text prompt, as well as instant customization options that allow users to transfer styles using reference images or combine styles from multiple references, all without requiring any fine-tuning. | Active | 11/29/2023 | Text: 512 char Image: 5mb | Text, Image | Image -Titan Text Express | us.amazon.titan-text-express-v1 | Express is a large language model for text generation. It is useful for a wide range of advanced, general language tasks such as open-ended text generation and conversational chat, as well as support within Retrieval Augmented Generation (RAG). At launch, the model is optimized for English, with multilingual support for more than 30 additional languages available in preview. | Active | 11/29/2023 | 8k | Text | Text -Titan Text Lite | us.amazon.titan-text-lite-v1 | Lite is a light weight efficient model, ideal for fine-tuning of English-language tasks, including like summarizations and copy writing, where customers want a smaller, more cost-effective model that is also highly customizable. | Active | 11/29/2023 | 4k | Text | Text +Amazon Nova Premier | amazon.nova-pro-v1:0 | Amazon Nova Premier is our most capable multimodal model for complex tasks and the best teacher for distilling custom models for cost-effective applications. | Active | 4/30/2025 | 1M | Text, Image, Video | Text +Amazon Nova Pro | amazon.nova-pro-v1:0 | Amazon Nova Pro is designed for highly complex use cases requiring advanced processing, creativity, and code generation. The model supports image, video, and text inputs and outputs text. | Active | 12/2/2024 | 300k | Text, Image, Video | Text +Amazon Nova Lite | amazon.nova-lite-v1:0 | Amazon Nova Lite balances intelligence, latency, and cost-effectiveness. It's optimized for complex scenarios where low latency (minimal delay) is crucial, such as interactive agents that need to orchestrate multiple tool calls simultaneously. The model supports image, video, and text inputs and outputs text. | Active | 12/2/2024 | 300k | Text, Image, Video | Text +Amazon Nova Micro | amazon.nova-micro-v1:0 | Amazon Nova Micro is the fastest and most affordable option, optimized for large-scale, latency-sensitive deployments like conversational interfaces, chats, and high-volume tasks, such as classification, routing, entity extraction, and document summarization. | Active | 12/2/2024 | 128k | Text | Text +Amazon Nova Canvas | amazon.nova-canvas-v1:0 | Amazon Nova Canvas allows users to leverage reference images to guide image generation, where the output image aligns with the layout and composition of the reference image while still following the textual prompt. Users can create images that match their text-based descriptions by simply inputting natural language prompts. Furthermore, they can upload and edit existing images, including applying text-based prompts without the need for a mask, or editing specific parts of an image using an image or text mask. The model also supports outpainting, which extends the boundaries of an image, and inpainting, which fills in missing areas. It offers the ability to generate variations of an image based on an optional text prompt, as well as instant customization options that allow users to transfer styles using reference images or combine styles from multiple references, all without requiring any fine-tuning. | Active | 12/2/2024 | | Text, Image | Image +Amazon Nova Reel | amazon.nova-reel-v1:1 | Amazon Nova Reel allows users to generate videos from a natural language text prompt and an included reference image. The model allows you to generate realistic, studio-quality videos by using text- and image-based prompts. The model supports text-to-video generation and text-and-image to-video generation. Videos are generated at 1280x720 resolution, 24 frames per second, and with a duration of up to 2 minutes. | Active | 12/2/2024 | | Text, Image | Video +Titan image generator V2 | amazon.titan-image-generator-v2:0 | Titan Image Generator v2 supports all the existing features of Titan Image Generator v1 and adds several new capabilities. It allows users to leverage reference images to guide image generation, where the output image aligns with the layout and composition of the reference image while still following the textual prompt. It also includes an automatic background removal feature, which can remove backgrounds from images containing multiple objects without any user input. The model provides precise control over the color palette of generated images, allowing users to preserve a brand's visual identity without the requirement for additional fine-tuning. Additionally, the subject consistency feature enables users to fine-tune the model with reference images to preserve the chosen subject (e.g., pet, shoe, or handbag) in generated images. This comprehensive suite of features empowers users to unleash their creative potential and bring their imaginative visions to life. | Active | 8/6/2024 | Text: 512 char Image: 5mb | Text, Image | Image +Titan Text Premier | amazon.titan-text-premier-v1:0 | Premier is a large language model for text generation. It is useful for a wide range of tasks including open-ended and context-based question answering, code generation, and summarization. This model is integrated with Amazon Bedrock Knowledge Base and Amazon Bedrock Agents. The model also supports Custom Finetuning in preview. | Active | 5/7/2024 | 32k | Text | Text +Titan image generator V1 | amazon.titan-image-generator-v1 | Amazon Titan Image Generator v1 enables users to generate and edit images in versatile ways. Users can create images that match their text-based descriptions by simply inputting natural language prompts. Furthermore, they can upload and edit existing images, including applying text-based prompts without the need for a mask, or editing specific parts of an image using an image mask. The model also supports outpainting, which extends the boundaries of an image, and inpainting, which fills in missing areas. It offers the ability to generate variations of an image based on an optional text prompt, as well as instant customization options that allow users to transfer styles using reference images or combine styles from multiple references, all without requiring any fine-tuning. | Active | 11/29/2023 | Text: 512 char Image: 5mb | Text, Image | Image +Titan Text Express | amazon.titan-text-express-v1 | Express is a large language model for text generation. It is useful for a wide range of advanced, general language tasks such as open-ended text generation and conversational chat, as well as support within Retrieval Augmented Generation (RAG). At launch, the model is optimized for English, with multilingual support for more than 30 additional languages available in preview. | Active | 11/29/2023 | 8k | Text | Text +Titan Text Lite | amazon.titan-text-lite-v1 | Lite is a light weight efficient model, ideal for fine-tuning of English-language tasks, including like summarizations and copy writing, where customers want a smaller, more cost-effective model that is also highly customizable. | Active | 11/29/2023 | 4k | Text | Text