Using Stable Diffusion

I chose Stable Diffusion because I have never tried text to image before and Stable diffusion lets you install their models and select appropriate model weights based on your requirements. I tried to give a lot of prompts and these were some output that I received with their corresponding prompts:

• “Create an animated form of futuristic world with underwater creatures and clear sky” prompt, Stable Diffusion, 29 Mar. 2024, stablediffusionweb.ca/.

The images below were created using the online version and the above was created using the local model and weights.

• “Ronaldo and Messi playing in the same team” prompt, Stable Diffusion, 29 Mar. 2024, stablediffusionweb.ca/.

• “Climbing Mount Everest in shorts” prompt, Stable Diffusion, 29 Mar. 2024, stablediffusionweb.ca/.

• “Playing with snow in a desert” prompt, Stable Diffusion, 29 Mar. 2024, stablediffusionweb.ca/.

---

SECTIONS analysis on Stable Diffusion

Students

Students are the users using the Stable Diffusion to create unique images using their prompts. This technology is free for initial use or to introduce users to the technology and after that, users need to pay for every token used which basically means the number of words used in the prompt, roughly 1 token is almost 1 word. Major barriers that could be created are lack of understanding of the media, as we learnt this could be good form of off-loading tasks to technology but users need to make sure it is not letting them skip an important aspect of knowledge over a subject.

Ease of Use

The interface as of today has been refined and extracted out to a point where it becomes really easy to use. Stable diffusion was initially only available in form of models as I mentioned above, you would need to install those models and model weights which is the data the model would need to output any content. As the technology became more widespread, people started created their own layers and now there are multiple online platforms that would just take it in a prompt online and return the result by running the models on a cloud server. So, it becomes pretty easy to use and easily available.

Cost

The cost is not very tremendous for stable diffusion and has definitely become much better than before, it costs $7 per month when billed yearly which gives the user 2000 fast generated images and after that the render time becomes much slower. There is also another plan for $14 per month when billed yearly which gives the user 4000 fast generated images and after that the render time becomes much slower. These prices are specific to Stable Diffusion and not any other Generative AI platform, every platform has their own pricing based on their use case.

Teaching

I believe that Stable Diffusion is an amazing fit for teachers and teaching. This helps explain topic through visual indicators which we know helps enhance the content exponentially. It can be used to express a message in form of dynamic outputs to keep the students engaged and interested in the core topics.

Interaction

In the case of Stable Diffusion, the interaction between students could potentially be boosted by sparking up their interest in the output as we have seen above could be really eye catching and help students start conversation about these content outputs. The student – content interaction will not be much as the content output from Stable diffusion is generally a form of image which is not interactive and hence the direct interaction is not high. Whereas, student – teacher interaction will definitely be boosted similar to student-student interaction where these images could end up being catalyst for conversations.

Organization

When it comes to control for organizations to tailor the experience, there are different parameters that could be modified in order to create different outputs but when it comes to tailoring actual code for models, the information and knowledge needed in order to that is very scarce. The resources required to created a stable diffusion for an institution, it is not viable for most of the organizations. Even though, there could be some tweaks here or there but building an customized experience might not be that straightforward.

Networking

This technology provides a unique opportunity in connecting multiple fields by having a common ground which is Stable diffusion as a platform. People working health could benefit from talking to people working in education as the input in form of prompts is being inputted by both the user groups in a similar manner just having different domain knowledge insights. These groups could benefit from talking and exchanging some bites of information they picked up to get better output when writing prompts as an example.

Security

Security is still a big topic of controversy or a topic of concern even. These learning models are not transparent with the data they use to train their models which imposes a security concern when users which in this case could be teachers or students enter their information which could be sensitive it is not clear if that information is stored to train their models. For stable diffusion as I mentioned above, we have models which could be installed locally on user’s machine in which case there is no connection to the internet and you in a form own the data and the trained model which is slightly better still without any solid outlines on this.

Reflection Questions

Q1) What tools did you find useful in your explorations this week and how did you use them? Which ones were not useful?

I found several tools particularly useful for enhancing my understanding and utilization of Stable Diffusion. Firstly, the intuitive user interface of Stable Diffusion facilitated seamless interaction on the web app. The controls allowed me to input text prompts and generate corresponding images effortlessly. Additionally, the built-in customization options, such as image resolution and style parameters, provided flexibility in tailoring the generated images to specific preferences. Its documentation and online tutorials served as valuable resources as well.

However, there were some limitations encountered during my exploration of Stable Diffusion. Despite its user-friendly interface, the software occasionally experienced stability issues or hallucination, resulting in unexpected outputs. Additionally, the quality and diversity of the generated images varied depending on the input text and model settings, indicating room for improvement in fine-tuning the model. The examples could be seen above where I have prompts and corresponding output images.

Q2) Where do you think these tools will be in their evolution in 2-3 years’ time?

In 2-3 years’ time, I think that Stable Diffusion will undergo evolution and even more refinement, driven by advancements in machine learning. Here are some potential developments:

• Improvement in realistic images
• More control over customization
• Faster Speeds for processing
• Cheaper rates to process the prompts

H5P Interactive Learning Object

For the learning object, I chose to create a football trivia quiz consisting for multiple choice questions and true/false questions. This is an interactive method to learn and educate people about football in a more fun way by keeping them engaged in the learning process:

Lesson Planning template

I chose football as a topic to be learnt for the lesson planning template. I have always been interested in football from the childhood and thought it would be a unique topic to plan as a lesson. I have attached the template below:

Reflection Questions:

Q1) How have you found the balance of passive and active learning in this course for your learning? How does it compare to your experience in other courses?

In this course, the balance between passive and active learning has been quite different from other courses. We’ve engaged in various activities that encouraged active participation, such as group discussions, problem-solving tasks, and multimedia interactions. These activities have enabled us to apply concepts in real-world scenarios which is mentioned in Merrill’s first principle as well!

The course also incorporates passive learning elements, particularly in the form of reading materials and watching instructional videos. These passive components serve as foundational knowledge and terminology scaffolding, preparing us for more active engagement with the content. Just like the text mentions, passive learning can be valuable for laying the groundwork before diving into more interactive activities.

As compared to other courses, I feel like since we were learning about multimedia and concepts regarding educational techniques consciously it was easier to cover principles of active learning and passive learning in a balance but when we are studying engineering subjects, it is easier to skip these concepts due to the complexity of the concepts and time frame in which we need to complete them. Even though that is the case, after having a better view on active learning it can definitely help us in learning as we go forward now!

Q2) Can you describe (step by step) an example of scaffolding in a learning experience that you’ve designed or experienced?

Something recent that I worked on where the learning experience was unique and interesting was creating the story flow using Twine. I would categorize that experience as:

• Introduction to the Twine: I started off with getting to know about Twine as platform and ways to describe a story. As a prerequisite, I did some research about story telling and it amazed me how much integrated story telling is in activities around us like speeches, song lyrics and even standup comedy are some very silent forms of storytelling.
• Followed multiple tutorials: After being a little familiar with the concept and idea of Twine, I went on to learn some basic workflows of functionalities offered by Twine as a platform.
• Started implementation: Having read the module, it gave me a different perspective on the implementation strategy for story writing. In adjacency with Merrill’s principle of engaging learners in solving authentic problems, I figured that the story needs to be engaging in a manner that keeps the users hooked.
• Reflecting back: Another principle that I found really helpful was to Encourage students to reflect on their progress and make revisions based on feedback, Merrill’s principle of feedback and reinforcement. This principle made me have a retrospective on the task of creating a story which made me realize the decisions I took while building that story block by block which in turn helped me to make a few changes later on.

Video – Video link here

Script –

Hey, Today we will be talking about the AI Collar Pin: the next frontier in wearable AI technology. This innovative device seamlessly combines hardware and software to revolutionize the way we interact with our environment.

[Change environment]

At its core, the AI Collar Pin is designed for multifunctionality. Imagine having the power of AI at your fingertips, quite literally. Let’s delve into what makes this device so remarkable.

[ Have the first clip of showing the clip in the middle of the sentence ]

First, let’s talk hardware. The AI Collar Pin is sleek and elegant, designed to be worn comfortably on your clothing. Despite its compact size, it packs a punch with a range of sensors and components.

Equipped with advanced navigation sensors, the AI Collar Pin provides unparalleled protection and assistance in navigating your surroundings. 

Whether you’re exploring a new city or simply walking to class, you can trust the AI Collar Pin to guide you safely.

How does it do that? Let’s have a look at that using this demonstration,

[Demonstration]

In conclusion, the AI Collar Pin is not just a piece of technology—it’s a game-changer. With its combination of hardware and software features, it redefines what’s possible with wearable AI. Humane has already released an instance of this so do check them out if you are interested to learn more, Thank you!

[Fade away or move up]

Storyboards –

These storyboards are features that the AI Collar pin can perform including projection for looking at the lectures. Navigation also utilizes projection as a part of functionality, these storyboards reflects watching lecture videos as another utility of it!

The AI Collar Pin also has Bluetooth and internet connection for better response and connectivity!

Reflection Questions:

Q1) What is the learning purpose of your video?

The learning purpose of the video is to educate people about how Artificial Intelligence can be intertwined with a hardware piece to bring another form of technology to life. The video will showcase real-world applications of AI-enabled hardware which could also act as a seed of interest for the viewers and motivate them to develop a related product themselves. Since this space is relatively new, education becomes really important, hence the purpose of this video.

Q2) Why is video a good medium for this learning purpose?

I feel like after going over the Mayer’s principles, I have realized that education and communication has a lot of depth. Video becomes a good medium for this learning purpose because it leverages Mayer’s principles of multimedia learning to enhance understanding and engagement. Through the integration of narration and demonstrations, it facilitates active processing by providing learners with multiple channels for processing information simultaneously. The use of real-world demonstration aligns with the coherence principle, ensuring that content remains focused and relevant.

Q3) Which of the principles we’ve covered this term (e.g., Mayer/Universal Design for Learning/Cognitive Load Theory) did you incorporate into your design and why?

While writing the script and storyboards, I incorporated principles from Mayer’s Cognitive Theory of Multimedia Learning to optimize the learning experience.

1. Limited Capacity (Cognitive Load Theory): I ensured that the video content didn’t overwhelm viewers’ working memory by presenting information in manageable chunks. By avoiding information overload, learners could focus more effectively on the integration of AI with hardware.
2. Active Processing: Throughout the video, I encouraged active engagement by prompting viewers to mentally filter, select, and organize information. By fostering this active processing, learners were better equipped to construct meaningful mental representations of the content.

Also, I added a real-world example that helps the viewers deviate from the video explanation which recollects their focus to something different than just a visual speech.

Q4) What was challenging about capturing your own video?

I would say the major thing which was challenging was recording myself speaking to a camera since I have not had a lot of experience with that and it was pretty awkward. Other parts were still interesting yet challenging like writing a script and storyboards but I was able to overcome those over time but recording and watching my own self was the most challenging part of the assignment.

Q5) What did you find easiest?

The easiest and most fun part was going out with my friends and creating a working demonstration of the topic and product being discussed which as an AI Collar Pin. I was all ready to direct and edit it later on to be a central part of my video presentation and hope that viewers would also like it. Also enjoyed scriptwriting after understanding how we want to get it written down. Initially it was a bit difficult but got comfortable with it after a little while.

Q6) How would you approach capturing video differently next time?

Next time, I would try to focus more on adding a couple more visual indicators which I was thinking of but could not implement which refers to animations of some sort that could intrigue the viewers a little more to be hooked on to the content. Also, a smoother timeline for the story could have been better but I also believe that could be done over time through experience only.

Module Summary

In this week’s module, we discovered the importance of story telling and how it can have major impacts in all areas of life, especially teaching. We went over the rich tradition of story telling which helps transmit information over to the next generations. Followed by the relevance of video creation and how story telling becomes much easier via video format. There are also some things we need to keep in mind while creating content in form of videos to convey an insightful and convincing story which includes:

• Focusing on Learning Outcomes
• Keeping the content short
• Adding visual elements
• Using a conventional tone

These were some points which we learnt from Mayer’s various principles which help us carve out a better story overall!

Importance of Scriptwriting

As a student without any theatre background, writing down a story in form of a script before executing it was not a very obvious concept. After watching the attached videos in Module 3 and researching more about it, I realized how important it can be to pre-process the creation of a video to save time and resources later on if we realize that the final product is not satisfactory.

While working on the story for Twine in this module which is attached below, I practiced this by creating a rough script in a clear, informal language with a structure as suggested in the Module. Storyboards also end up being helpful when working on stories as it helps us visualize the concept we want in our end product. I would definitely try to integrate a storyboard as a part of pre-planning phase for the Assignment 2 Video!

Twine Story

I tried spending some days to learn more about Twine as a platform. “Non-linear branched narratives” means that we do not have linear story path, instead we can have multiple options as a part of different pages which makes the story interactive and also dynamic since the story takes a different turn on every decision made by the user. We can visualize it as a tree which branches out into multiple other branches, in a similar manner a branched narrative story unfolds into multiple options.

This is the link to the hosted story: https://saksham1009.github.io/EDCI337/

The story I chose to display was of a kid visiting a football match in a stadium for the first time which was the final match for FIFA World Cup. The story unfolded itself where in the kid gets a chance to get onto the field to play at different positions and also got to experience the match through his seat. Now, I would not want to spoil all the plot but after my Assignment 1’s feedback I made sure to include the things that I learnt from the Module and my own research into the implementation which majorly impacted the quality of text written in the story. I kept in mind the concepts mentioned above which would make the story realistic and relatable!

Reflection Question – What storytelling techniques have you used instinctively and which ones require more work for you? Which techniques will you focus on moving forward?

I tried implementing all the techniques mentioned above in some capacity including keeping it short, focusing on learning outcomes, using a conventional tone, including active learning, keeping text and images together and building in accessibility.

Even though these factors mentioned above were part of my execution, the factor that I intentionally worked on to use and will take forward with me is creating a story with an emotional pull as mentioned in the “Storytelling” section in Module 3. Describing sentences that visualizes the scenario and takes the reader into the story seemed really relevant and interesting to me. I have consciously tried to make sentences include describing words to make the story immersive. For example, a line from the story in Twine which I wrote was “You smell the aroma of grass spread across the stadium” which according to me makes the experience of reading a story almost virtually real.

Do Remember to checkout the story from the link given above:)

These are the links to my blogs:

• Introduction
• Module 1
• Module 2

These are the links to my group mates’ blogs where I have commented:

• Nima – Module 1
• Nima – Module 2
• Nour’s Module 1
• Nour’s Module 2

Overview

In this blog, we would be going over the learnings from this weeks Module 2, WAVE accessibility report and a piece of infographic content.
We’ll take a look at how inclusive design and infographics can help boosting learning efficiency and also makes it accessible for everyone.

WAVE Accessibility report

The image above describes different metrics like Errors, Contrast Errors, Alerts, Features, Structural Elements and ARIA about the last blogpost Module 1.

After reviewing the WAVE report, there are multiple areas where I think I could improve to create a better blog overall. After digging deeper into the concepts from Module 2, I feel like I am more informed about creating and structuring the topics so that it is easier to understand and more engaging as well.

Journey Map illustration using infographics

This is a Journey Map created using Canvas which was created for a Software Engineering course to evaluate what a user for a specific problem which in this case is Communication goes through on a daily basis. This describes the different actions and scenarios that a user has to take and experience in an organized manner.

Looking backwards, integration of infographics is an essential part of the education. The project would not have been complete or would be really difficult to understand these metrics if a chart or visual representation like above was not included.

Reflecting back on Module 2 – Reflection Question

Q: Graphic design is inherently visual – what additions or modifications could you make to ensure that learners with visual impairments have access to the same information in an infographic in an online setting?

Including graphically represented information has become a key part of educational content as discussed above. While being visual is a key feature of graphical designs there are many more aspects which could be added or modified to enhance the experience even more.

• Alt Text: Including description for all the images in case the image is not visible on the webpage. Also, for accessibility purposed it is always beneficial to have an alternate text which describes the image show up under the image. (I have added it under the infographic illustration added above)
• Color: To make the illustration stand out and catch the reader’s attention, we should have contrasting colours which could also act as functional part of the image. An example for that would be having different colours show different percentages while making calorific charts.
• Interactive Elements: Engaging users can be really helpful especially when the content is dense or new to the readers. Having parts of the graphical design which can be moved around or interacted with by the user can end up making the content more fun and easier to be hooked onto.
  

By implementing these additions and modifications, we can ensure that learners with impairments and those who require accessibility inputs have equal access to the information presented in an infographic, promoting inclusivity and accessibility in online learning environments.

Discovering more about Loom

In this Module, I created a screencasting on QuickTime of a quick walk around Loom. In the walkthrough, I went over how and why to use Loom. What are the features that it offers and how it can help make life easier for people on different types of operating systems to view the original file without changing extensions.

Mayer’s Principles

There were certain aspects of Mayer’s principles that I tried to maximize the Intrinsic Cognitive Load by segregating the topic description into high level features and then summing them up later to explain the logic better. I try to break down the reasons behind the popularity and utility to give better context as well.

Overall, if someone goes over this tutorial video, they would be able to navigate and make proper use of functionalities that Loom offers as a service and communicate better via videos.

Reflecting

I think Active Processing was something that really caught my attention as I have seen some examples where that was a problem in my own experiences. Active Processing becomes a huge part especially when the amount of information being consumed increases. To tackle this, I believe having video content and other presentations really help as we did above!

Hello Hello,

My name is Saksham Dua and I am international student taking Computer Science at University of Victoria. I’m originally from India but I have been in Victoria for more than 2 years now. I’m in the third year of my computer science degree and have about 3 terms left before graduation.

I love to play football(soccer), go on long drives and play cricket in my spare time. I also love watching movies and shows, recently I have been hooked on to Suits (I know I am a bit late to the wave). Also love to cook Indian food and try different restaurants around Victoria.

Excited for this term!