This is the second part of my ChatGPT conversations and composition of my AI Video project. For more early conception ideas refer to “Rylan Eisenhauer Blog Post #4 (Chat GPT Video Chat)”. This post is about the specifics in narrowing down the shots I want to create for the project using ChatGPT to edit and narrow down my ideas. Below is a screenshot of my finalized list of shots and expressed emotions that I am aiming for, and below that is the entire conversation I had with ChatGPT to edit and narrow down my ideas:

Since the video work I am creating consists of sad and slow shots, I should only have about 7-8 shots as I think the drawing out of scenes and panning shots can help extenuate the feeling of things being slow and gloomy. Too many fast and whippy shots can ruin the effect I am going for as well as give the audience “too much” information when things should feel a bit ambiguous so that many can relate their experience to my video.

I was recommended to try and practice using RunwayML a little bit in order to experiment with AI creating video. I knew exactly what I wanted to test as I have had a still graphic of a lens flare that I wanted to give some motion. I gave RunwayML the image with the prompt:

“the yellow/orange flare in the middle does not move from the middle, but the rays that it shines slowly shine outwards without covering the red background. The video should end looking how it started as if it loops.”

Here is the still image as well as the video it gave to me as a result of the prompt, it was almost exactly what I was looking for besides the loop part:

This is exactly as I was looking for and I am glad it seems I understand that being specific with prompting is important. I will ensure to keep this strongly in mind when making my AI video and ensure that there is a strong sense of consistency in the videos as well as characters (such as the female AI character) looks consistent and natural.

-Rylan Eisenhauer

When first starting my dialogue with ChatGPT I realized how important wording my prompts was. My first ask was involved saying how I was gonna use AI to create video but ChatGPT read that as “give me ideas that would make videos about AI.”

I ended up using the prompt “give me some ideas for some short film projects/ story ideas” which definitely helped get more on the right track with creative endeavors. ChatGPT gave me 10 ideas. The 3 I liked most were “Fading Memories,” “The Last Passenger,” and “Echoes of the Past.” I decided to expand upon “Fading Memories” as it seemed a route that would work well with AI being almost a dreamlike state where what is generated is allowed to be a bit odd because it may not be remembered correctly.

I expanded on this idea with the prompt “Hey I like that “Fading Memories” idea! I want to do a 30-60 second short film montage with me having dialogue over assortment of hazy memories. what types of shots should I consider for this project?” to which it gave many ideas that I liked with having a mixture of shorts both of the past memories being hazy and close up dramatic slow shots to create a similarity and contrast of sad feelings between both shot types.

Thus I have landed on the idea to make a dramatic 30-60 second short film of happy memories slowly fading as they have happened so long ago. I will most likely make it about a love relationship that has been lost to time and being separated has made the emotion of the memories feel bittersweet. I want to have myself do the dialogue, record myself as the character in the non memories section and then use AI for all of the hazy dream sections.

To compare what I am envisioning to other works of film and quality type, the lighting of the shots of the man alone with be very dark and the AI memories will be black and white to show a positive yet slightly forgetfulness. The set for the alone man will be places like sitting on the bed, looking in the mirror, and other dramatic dark locations with the lights off meanwhile the shots of AI will be more outside and open with sunlight or good indoor lighting.

The AI creations will be similar to the montage we see at the beginning of Up (except not cartoon looking and using black and white instead) I see why they have the color in Up as Carl’s memory is fine and stable, but for my effect I need things to not have all of the details like a part of you is trying to keep it and the other wants to throw it away.

(But black and white with hazy effects)

Another point to draw from is the film “A Man Called Otto” which I believe shows both how I want to shot the in real life shots similar to Otto in his home being dramatized with different close ups and establishing shots, but also how the hazy memories are done in the montage style(except black and white instead of yellow) The yellow of these shots show pure untainted happiness about those memories meanwhile I believe the black and white effect will help show the sadness that has been added to the memories.

(But black and white)

(Darker lighting but similar vibes of this)

-Rylan Eisenhauer

Here are my loop videos for the Loops Assignment. each one repeats 3 times

Continuity Loop (7 secs)x3:

Infinite Loop (8.6 secs)x3:

Montage Loop (6.3 secs)x3: (No Sound)

-Rylan Eisenhauer

The breaking space style I went for was using the Metric montage style with every video being exactly 3 seconds long. the Metric style ensures that editing follows a specific number of frames, duration of shot. This gives the montage a light rhythmic visualization while the near silent ambience of the room helps create the calm and relaxed vibe.

The calm and relaxing vibe I aimed towards was filming all of the different features and décor that is within my recording room. There is no sound besides light whirring of fans and brushing up against its elements to convey the importance of the items creating their own visual experience of the room. The room has many objects from posters, plushies, and gaming equipment to showcase the variety of interests while also showing the liveliness of the room also depends on the energy its given. When the main overhead light is off but the LED’s are on, you get a sense of motion and living from all of the motionless objects.

Right off the bat, McCloud gives the reader strong examples of how our focus on the frame and the properties it holds helps the viewer fill in blanks and create a sense of time when reading multiple parts of dialogue in a single frame. Time doesn’t stay consistent specifically based on singular properties of a frame. Rather, it is comprised of the sizing of the frame, how much dialogue, what is being captured in the frame, and even the detailing often having the audience spend more time looking at the quality of the art to imply impact.

Take for example the first example McCloud gives that involves a wide spread of characters speaking but there is a series of events and timing that helps create a sense of flow. Starting on the left the man takes a picture, the guy who gets his picture taken reacts, due to that reaction a women discourages the picture taker, then another women responds to her saying that he is fine doing so, then a man responds to the fact that he is being encouraged and encourages other behavior, and lastly the man on the right acknowledges his remarks and encourages as well.

When first looking at this scene, my first initial thought is that all of these pieces of dialogue happen at the same time, because visually they ARE being presented at the same time. But it’s because of the content of what they are saying and who they are speaking to that creates a order of operations rather than a chaotic “everyone is speaking at the same time.” So now we have gotten a sense of space where everyone is and established interactions with one another as a quick judge of character. What was done in one frame is a shot that would most likely last around 15-20 seconds panning from character to character as the audience focuses on the next person.

The best connection that McCloud makes is how the rope being stranded from one dialogue bubble to the next. We can see that the flow of the events have to happen in a certain order otherwise the dialogue they provide wouldn’t match up with a different character such as one character saying “Oh Henry, put that camera away will you?” and the next saying “hmmmm, you sure you want to move there Jed?” It just doesn’t make sense!

The other point McCloud made that stuck out to me is the frame shaping and its placement with the other frames. We in our culture read from left to right top to bottom so following this flow is pretty important, but that doesn’t mean we are completely restricted to this or how these frame are expressed individually or in a sequence. Some frames use 2 frames overlayed to often emphasis a certain aspect of a frame such as a zoom in or extra dialogue that happens within the same scene. These overlay frames can be place almost anywhere overtop as long as the writer can express what is happening in the background frame in relation to the one overtop.

Last point I want to talk about is panel sizing and framing within the shot size. Frame sizing often implies stronger importance on frames that are bigger when there are more details or aspects that the author wants the reader to pick up on. This is best explained in the “I guess” comic McCloud refers to, as it helps us create a sense of time between first dialogue and the next. Looking at the 2 examples below:


The first example shows a moment of thought, its brief but still exists within the timeline. But look at the size and framing of the second example, it shows deeper more well thought out thinking, they even make him a bit smaller in the scene so that both himself and the shot have gained new perspective. Not to mention that the frame zooming back in also creates a sense of impact to admitting the “I guess” to show that he put more thought into it verses the first example.

-Rylan Eisenhauer

consider the framed panel in a comic as a cinema shot.  Wider or longer panels are like shots with longer durations (“long takes”).  Smaller panels are like shots of shorter durations.  Discuss some aspect of McCloud’s visual essay that makes you think of the possibilities of time manipulation in digital cinema or of a certain movie scene that plays with time.

Brumes d’automne (Autumn Mists) is another strong example of the artistic creativity that comes from “silent films” tasking to present a story or in this films case, ideas and thought processes. The usage of music is key as it helps bring out tone and direction that the film is working to express visually. Not to mention being made in 1928 during black and white filming also creates a sense of tone that may have been natural and fit in with other black and white film, but has since adopted its own unique sense of artistic expression different from how film is presented today.

An aspect of Brumes d’automne that I noticed early on is how the character expresses emotion very reservedly and most of the emotional impact is shown through her eyes. In moments of putting the papers into the fire, you can see small shivers that she has as the papers burn. Perhaps these papers hold or held value at one point and she has a desire to let go in order to move forward? Or possibly the papers were love notes from a old relationship that she feels pain remembering.

Another detail I noticed while watching was the use of focus to almost show the audience memory in how well she can and cant remember details based upon how clearly the imagery is, or perhaps the glossiness of her eyes indicate the tears, maybe the visuals are based upon how sad specific details may make her cry more. It shows its intention as non of the shots of the women are blurry and we have an assortment of very clear images that keep showing up (the tree branch over the water, the mud water tire marks, and shots of water dropping on what appears to be a lake.) meanwhile new additional pieces like the silhouette of the person, and specific locations can change its clarity like tears are forming or memory is failing.

The editing is unique but almost seems sporadic. As if someone is trying to tell a dream they had and in the time you try to make sense of what you just heard, even more information has come to process. The cuts between shows flow often through the relation of certain elements such as the fire burring then cutting to the smoke coming out the top and then having more shots be done outside. I get the feeling that she is thinking on the past or going through a mixture of emotions leading her overall expression to at times feel blank almost letting her eyes solely convey how she feels.

I believe that the montage work does work for the sense that is doesn’t have sound besides music and creates its sense of tone by almost having a rush of different imagery reflect on our minds racing thoughts on locations and feelings. Although as much as it evokes its purpose, the style doesn’t really evoke anything from me. The lack of an exact story doesn’t make me feel very invested in the woman or in the shots it is showing because of the imagery changing so quickly it seems like the film doesn’t care if I am “caught up” or not. It makes me just keep asking “why are there so many shots of water, ponds, rain, and even a beach?” leading me to create my own sense of story such as the woman having a love interest that she lost to the ocean and her sorrow is so strong she wants to rid of the pain by forgetting the memories of him while having regrets doing so.

I can see the vision that Kirsanoff was going for and can see the benefit it holds towards a specific feeling to evoke with your audience. but because the film is so “long” (for what is being conveyed) it almost was leaving me confused as to if the points I was drawing from it were correct, like the movie was showing me more because I might have drawn an incorrect conclusion so it keeps showing more to potentially clear that up. But for me it kind of makes it seem like the movie is trying to hold my hand explaining it carefully and cautiously, but its in words I can’t fully understand. So visual queues and music work helps try to put my brain into the right mindset to possibly make my own connections to what the woman is feeling. Maybe I myself was losing my density and unity as a result being shown so much imagery and scenic shots working to evoke those feelings.

-Rylan Eisenhauer

This was shot on Sunday after sitting in my recording room brainstorming ideas when I realized I left my headphones in another room. I was struck with the idea of making continuous space by shooting multiple shots on the same camera direction but in different spots to create the illusion of my arm stretching to grab something while my body sits in a chair.

The music was an intentional addition as the audio of me breathing and making other sounds would break the illusion as you could hear the rest of my body being closer to the camera than I would like it to seem. The grabbing of incorrect items in different spaces I believe helps add to the effect that I am blindly letting my arm move through space while making educated guesses due to having no visual queues. I had a lot of fun trying to ensure my arm moved as straight forward and back as possible so that the stretch  illusion would work best rather than it seeming like I have a bunch of joints all extending outward.