Table of Contents
AI content generation.
AI content generation is grounded in recent advances in deep learning, particularly in developing transformer architectures, generative diffusion models, and multimodal learning systems. These technologies have enabled machines to understand human language and imagery and generate increasingly creative multimedia content.
The transformer architecture introduced by Vaswani et al. in 2017 is at the core of modern AI content creation. Transformers revolutionized natural language processing by replacing recurrent mechanisms with self-attention, allowing models to capture long-range dependencies in text and scale to billions of parameters. This architecture underlies large language models (LLMs) such as GPT, T5, and others, capable of generating high-quality written content across domains.
In parallel, diffusion models have emerged as a dominant framework for generating visual and audiovisual content. These models work by learning to reverse the process of adding noise to data, gradually generating high-resolution images, animations, or video sequences from random noise guided by text or other input modalities. Diffusion models produce more stable and controllable results, with better alignment to prompts.
Modern systems rely on multimodal encoders to enable cross-modal content generation, such as generating images from text or videos from audio. As AI content generation becomes more powerful, marketers must learn how to use these tools to create engaging content.
Content Creation Tools
Images
Midjourney
Midjourney is a high-performing AI art generator hosted on Discord…
Midjourney is an AI research lab based in California. In 2022, it launched the Midjourney application inside of Discord. The free tool was available to anyone. Midjourney quickly became popular, reaching 16 million members by October 2023. Due to its fast-growing user base, Midjourney canceled its free usage options, and now it can only be accessed via a subscription or APIs. Midjourney is one of the highest-performing realistic text-to-image generators on the market. Known for its versatile and high-quality outputs, the company became one of the leaders in AI image generation.
Stability.ai
Stable Diffusion is one of the most widely used open-source image models…
Stability.ai is a UK-based AI company founded in 2019. It created Stable Diffusion, an open-source text-to-image generator that helped democratize access to AI art creation. Unlike proprietary tools, Stability.ai’s models are freely available and can be customized by developers. The models are hosted on platforms like Hugging Face and can also be accessed through paid tools such as DreamStudio or via Python APIs. Its open philosophy and community-driven model training distinguish it from commercial competitors.
Google Imagen
Imagen is a photorealistic model developed by Google for enterprise users…
Imagen is a high-performance image generation model created by Google Research in 2022. It uses large transformer-based language models and diffusion techniques to create highly realistic images from text prompts. Unlike Midjourney or Stability.ai, Imagen is not publicly available for casual use, but it can be accessed through Google Cloud’s Vertex AI platform by businesses and developers. Google highlights Imagen for its ability to understand nuanced text inputs and produce clean, high-fidelity visuals suitable for commercial and research applications.
Microsoft Image Creator
Bing Image Creator is Microsoft’s tool based on OpenAI’s DALL·E model…
Microsoft Image Creator was launched in March 2023 and is integrated into Bing and Microsoft Edge. It uses OpenAI’s DALL·E model to create images from natural language prompts. Users can access it for free through their Microsoft account and generate a limited number of images per day. It is part of Microsoft’s broader integration of AI into Office tools and the Azure ecosystem, offering seamless generation for presentations, documents, and visual design directly inside their apps.
DALL·E 3
DALL·E 3 is OpenAI’s latest version of its text-to-image model, available in ChatGPT…
DALL·E 3 was released by OpenAI in October 2023. It builds on the earlier DALL·E and DALL·E 2 models by significantly improving the alignment between prompts and generated images. Users can access it via ChatGPT Plus (through GPT-4) or through OpenAI’s API. It also features native inpainting and outpainting tools, and advanced prompt-following abilities. DALL·E 3 is frequently used in marketing, illustration, and prototyping, and it’s praised for generating legible text within images and obeying instructions more precisely than its predecessors.
Adobe Firefly
Firefly is Adobe’s creative AI tool integrated into Photoshop and Illustrator…
Adobe Firefly was introduced in 2023 as part of Adobe’s Creative Cloud. It is designed to assist creative professionals by generating commercial-use-safe images, text effects, and templates. Trained on Adobe Stock and public domain content, it avoids the legal gray areas surrounding generative AI. Firefly is embedded in tools like Photoshop and Illustrator and accessible to all users with a Creative Cloud license. It emphasizes editable outputs, making it ideal for post-generation refinement in professional design workflows.
Video
Veed.io
Veed.io is a browser-based AI video editor with voice cloning, avatars, and auto-subtitles…
Veed.io is an online video editing platform designed to make video creation simple and accessible. It works directly in the browser and supports editing tasks like trimming, cropping, adding overlays, transitions, subtitles, music, and more. Its AI features include voice cloning, avatar insertion, background removal, and automatic subtitle generation, making it a top pick for creators and marketers.
Adobe Express
Adobe Express lets you create and edit videos directly in your browser…
Adobe Express is Adobe’s web-based video tool for fast, creative video production. Users can crop, trim, split scenes, apply effects, and add music, icons, and text overlays. It’s ideal for social media, with built-in templates and sharing tools. Students at BU can get free access via their Adobe account.
Runway
Runway is a creative video tool with motion control, AI avatars, and Gen-3 Alpha…
Runway is an AI research company offering video editing and generation powered by its Gen-3 Alpha foundation model. Features include Motion Brush, Director Mode, camera motion tools, and text-to-video generation. The tool is popular for commercial and artistic use and integrates well into editing pipelines.Runway offers free credits to users to help you get started.
CogVideo
CogVideo creates dynamic video from text, developed by Tsinghua University…
CogVideo is a Chinese text-to-video model developed by Tsinghua University. It transforms detailed prompts into motion videos. One CogVideo-generated short won a Cannes Jury Award.
Try out the Cog Model on Hugging Face.
LTX Studio
LTX Studio is an AI-powered video storytelling platform for cinematic content creation…
LTX Studio is an advanced AI tool developed by Runway’s former head of research. It allows users to script, cast, style, and direct entire cinematic videos using artificial intelligence. With features like scene planning, visual character design, and shot layout generation, LTX is designed for storytellers, marketers, and creative teams looking to automate production workflows and bring complex narrative ideas to life visually.
OpenAI Sora
Sora is OpenAI’s powerful text-to-video generator creating realistic videos from text prompts…
Sora is OpenAI’s text-to-video model that generates videos up to 20 seconds long from text prompts or by extending existing content. Released in December 2024, it’s available to ChatGPT Plus and Pro users and offers features like storyboarding, Re-mix for creative adjustments, and different resolution options. Videos can be created in widescreen, vertical, or square aspect ratios, and the platform includes built-in safeguards and watermarking for transparency.
Writing.
Perplexity AI
Perplexity AI is a powerful research assistant with real-time web search capabilities…
Perplexity AI combines search engine functionality with AI, providing real-time information retrieval with proper citations. It excels at research-based tasks, offering accurate information sourced directly from the web with excellent thread continuity. The platform maintains consistent context throughout conversations and features a user-friendly interface with quick access to source links. Advanced features include a “Collections” system for organizing research, different interface modes for academic and creative writing, and support for multiple AI models including GPT-4, Claude 3, and Sonar.
Jasper AI
Jasper AI specializes in marketing content creation with brand voice customization…
Jasper AI is a content creation platform designed primarily for marketing teams and content creators. It features over 50 pre-built templates for different content types, tone customization to maintain brand voice consistency, and collaborative tools for team workflows. Its “Boss Mode” allows users to write up to five times faster through direct AI commands. While particularly strong for marketing copy, social media content, and email campaigns, Jasper may produce generic content without proper training and requires fact-checking for data accuracy. The platform integrates with tools like Grammarly and Copyscape for quality assurance.
Claude
Claude is Anthropic’s AI assistant excelling in ethical, clear writing with new reasoning abilities…
Claude is Anthropic’s AI assistant known for clarity, ethical guardrails, and context-aware responses. The latest Claude 3.7 Sonnet model, released in February 2025, introduces hybrid reasoning capabilities, allowing users to choose between standard quick responses or an extended thinking mode that improves performance on complex tasks. Claude particularly excels at writing tasks requiring style adjustments and tone modifications, making it ideal for creative writing, dialogue, and style refinement. Recent additions include a built-in analysis tool enabling Claude to write and execute JavaScript code for data processing, the ability to customize Claude’s response style, and strong document comprehension capabilities.
Writesonic
Writesonic creates factually accurate, SEO-optimized articles with Chatsonic AI…
Writesonic specializes in creating factually accurate, search-optimized articles through its AI writing platform. Its Chatsonic feature provides a conversational AI interface with real-time web search capabilities similar to Perplexity but with additional content creation tools. The platform excels at generating marketing copy, blog posts, and product descriptions with SEO optimization built in. Writesonic also offers fact-checking capabilities for accurate content creation and integrates multiple AI models in one interface, allowing users to switch between different engines for various tasks. Its affordable pricing structure starts with a free plan for limited usage.
Copy.ai
Copy.ai specializes in marketing copy generation across various channels…
Copy.ai focuses on generating high-quality marketing copy across various channels including ads, emails, and social media. The platform excels at creating shorter written content like ad campaigns, product descriptions, and email marketing materials rather than long-form articles. With an intuitive interface and numerous templates for different content types, Copy.ai makes it easy for marketing teams to quickly create variations of their messaging. The service offers a free plan with limited access and paid plans starting around $36/month, making it accessible for small businesses and individual marketers looking to streamline their copywriting process.
Social Media Content.
Buffer AI Assistant
Buffer AI Assistant helps create and repurpose social media content across platforms…
Buffer AI Assistant is designed specifically for social media content creation, helping you generate new posts, repurpose existing content, and spark fresh ideas for any platform. The tool understands platform-specific requirements (like character limits for X/Twitter) and helps maintain consistent brand voice across all channels. Buffer’s AI Assistant integrates directly with its scheduling platform, creating a seamless workflow from content generation to publishing. Users can transform content between platforms—for example, turning a LinkedIn post into a Twitter thread—and can generate multiple variations of posts to test different approaches.
Hootsuite
OwlyWriter AI generates captions, hashtags, and content ideas for social media platforms…
Hootsuite’s OwlyWriter AI is more than just a caption generator—it’s a comprehensive content creation tool designed to save time on social media management. The AI can generate captions from scratch, from a URL, or based on upcoming holidays and events. It also creates multiple ad copy variations for testing, suggests relevant hashtags based on your post’s content and images, and integrates with Canva for visual content creation. The tool works within Hootsuite’s ecosystem, allowing for scheduling and performance tracking, making it ideal for marketers looking for an all-in-one solution.
SocialBee AI Generator
SocialBee AI Generator creates captions and images with DALL-E 3 integration…
SocialBee’s AI Post Generator offers a comprehensive solution for social media content creation, generating both captions and images. The tool creates engaging content based on your inputs while maintaining your brand voice, and includes AI-generated graphics powered by DALL-E 3 integration. SocialBee’s AI assists with overcoming writer’s block by providing a continuous stream of post ideas, and can automatically incorporate relevant emojis and hashtags into posts. The platform also specializes in creating content variations to keep your feed fresh and can transform links into ready-to-publish social media posts with just a few clicks.
Meta Advantage+
Meta Advantage+ creates personalized ads and AI-generated content for Meta platforms…
Meta Advantage+ is an AI-powered platform that automatically creates multiple ad variations from minimal media assets. Beyond advertising, Meta has integrated AI content creation capabilities through Meta AI, which helps users quickly create posts and images across Facebook and Instagram. The Meta AI assistant can generate visuals to share with your network and assist in writing posts with appropriate tone and style. Meta also provides a free AI studio where users can create AI characters for engaging with their audience or auto-responding to common inquiries, streamlining content creation and audience interaction on Meta’s family of platforms.
TikTok Symphony
TikTok Symphony generates video scripts and content specifically for TikTok…
TikTok Symphony is TikTok’s native AI content creation system designed specifically for its platform. The Symphony Assistant helps creators generate ideas and scripts for videos, provides platform insights, and highlights current trends to help creators stay relevant. The Creative Studio takes content creation further by enabling users to generate videos from just a few product or page links with editing capabilities. Symphony offers translation and dubbing features to adapt content for diverse global audiences, and is developing a feature to allow creators to use custom digital avatars as narrators, while currently offering a database of AI-generated avatars based on real creators.
HubSpot AI Generator
HubSpot AI Generator creates social media content and helps you schedule posts.
HubSpot’s AI Social Media Generator is part of HubSpot’s comprehensive marketing suite, helping users create social media posts quickly. It features automated social copy generation that can repurpose basic post ideas into trivia, polls, and question-based captions to enhance engagement. The tool supports multiple social media channels, creating appropriate content for Instagram, Twitter, Facebook, and LinkedIn. HubSpot’s caption generator is integrated with its reporting dashboard, allowing users to create, publish, and track post performance in one place. Users can identify top-performing content, analyze audience trends, and optimize posting times, though the tool offers fewer customization options than some specialized alternatives.
Automated Content Creation
You can automate content creation on any platform, like social media channels, applications, or your website, using APIS from your platform and the multimodal AI models you want to use. Every central cloud AI player, such as Azure, Google Cloud, and Amazon, has a cloud run function option that allows you to run code directly in a container with minimal configuration, enabling immediate execution. This is called Cloud Run in Google Cloud, which lets you run containerized applications with automatic scaling. In Amazon Web Services (AWS), it’s called AWS Lambda, offering serverless code execution without managing infrastructure. In Microsoft Azure, it’s known as Azure functions.
We will use these functions to run some python code to create an application for automatic blog post creation.
Step1: Enable WordPress API.
- Log in to WordPress as an administrator.
- Navigate to Users > Your Profile.
- Scroll down to the Application Passwords section.
- Create a new application password by providing a name.
- Copy the generated password, as it will be used in your Google Cloud Run function for API authentication.
You will use this application password along with your WordPress REST API URL to post content programmatically. Your url will look like this: https://yoursite.com/wp-json/wp/v2/. Replace yoursite.com, with the domain name of your website.
Step 2: Start a new project on your Cloud platform.
Visit the Google Cloud Console and sign in with your Google account.
Create a New Project:
- Click on the project dropdown at the top of the page.
- Select an existing project or click New Project to create one.
- Provide a project name and billing account.
Step 3: Enable the APIS on Google Cloud
In the left-hand menu, click APIs & Services > Library. In the API Library, type the API name you want to enable in the search bar. You need to activate the Cloud Run API (to manage and deploy your containerized app), Cloud Build API (to build the app into a container), Artifact Registry API (to store container images), Gemini for Google Cloud API (for generating AI-based content), Cloud Logging API (to monitor and debug the app), and IAM API (to manage permissions and access control). Once these APIs are enabled, you can use them within your project to automate tasks and run your application.
Step 4: Create an API Key in Google AI Studio
Go to aistudio.google.com and click on “Generate a New API Key.” Select the Google project you just created and generate the key. Copy the key to use it in your Google Cloud project.
Step 5: Create a service account
We must create a service account in Google IAM & Admin to ensure your cloud function runs. Locate IAM & Admin in the left-hand menu of the Google Cloud Console. Under IAM & Admin, click on Service Accounts. This will open the section to view existing service accounts or create a new one.
Once you click on Create New, you will see the following screen. Add a name and a description. Afterward, the wizard will ask you to assign a role. For Google Cloud Run, the most appropriate role to assign to the service account is Cloud Run Admin. This role allows the service account to fully manage Cloud Run services, including creating, updating, and deleting services. Grant this service account access to the project section; click the Select a role dropdown. Search for Cloud Run Admin or find it under By product or service > Cloud Run. Select Cloud Run Admin.
Step 6: Go to Cloud Run and Deploy your code.
First, access the Google Cloud Console and navigate to Cloud Run. Once there, click Create Service to begin. Choose the option inline editor, choose the region us-east1 , and the runtime Python 3.12
After you click Create, you must add your Python code to the editor. Click on edit and delete the code that is already there. The essential files you’ll need are your main.py (which contains your Python application logic) and requirements.txt (which lists the necessary dependencies). The main.py file includes the code to interact with APIs or perform the required tasks, and the requirements.txt file will list libraries like Flask, requests, and any others your application requires.
In this notebook, you will find the code you need to copy and paste to the main.py file:
https://colab.research.google.com/drive/1-uy92SeXB4d6PLRUZ4Bu12CwXy8sdJGY
in the requirements.txt file add the following dependencies:
functions-framework==3.*
requests
Flask
Pillow
google-generativeai>=0.3.0
These dependencies are needed because your code uses Flask to create a web service that handles incoming requests, requests to communicate with external APIs like WordPress and Gemini, Pillow to process any images involved, google-generative to generate content using AI, and functions-framework to ensure the app runs smoothly in Google Cloud Run without manual server management.
During deployment, Cloud Run will automatically build your application from these files and prepare it for use. You’ll also be asked to configure the entry point—in this case, it will likely be the main function within your Python file, which Cloud Run invokes when the service is accessed.
Next, configure any environment variables your application needs, such as API keys or credentials. Your application will interact with external services like the Gemini API and WordPress, so you should add environment variables such as GEMINI_API_KEY, WORDPRESS_USERNAME, and WORDPRESS_APP_PASSWORD. We already copied the GEMINI_API_KEY in step 4. You can find the WORDPRESS_USERNAME, and WORDPRESS_APP_PASSWORD by going to the dashboard of your website, go to users, and get the username and password associated with your username.
Once you’ve finished configuring the settings, click Create. Google Cloud Run will then build and deploy your application, making it accessible at a unique URL. This URL will allow you to interact with your deployed Python service via HTTP requests. Cloud Run will automatically handle scaling and performance based on demand.
Step 7: Go to WordPress and Create the PHP code to display the blog post generator.
Go to your website and install a plugin called Snippets.
This plugin will allow you to add code snippets to your website. Once this is installed, you can add a new php snippet. You will find this code in the notebook:
https://colab.research.google.com/drive/1R4Q5_9x-MVSgajNhfB26YVMi5i677zm_#scrollTo=mvgKVwNLAWCQ
The php code will create a form we can insert in any page using a shortcode [docs_ai_post_generator].AI Post Generator
Milestone IV
Create a short, engaging video to promote your selected products. The video should be tailored to your target audience, and the visuals must be consistent with your brand.
Create a social media post on your chosen platform. Ensure the content aligns with the brand style and message you represent.
You can either post the links on your website or send them to me directly.