Posts

Showing posts from June, 2025

Manipulated

Image
  Manipulated 4:30 This was written with Meta AI with Llama 4 and Chat AI 1.62 assistance. It's another installment in the  AI theme. This is probably the most sinister I will portray AI. I'm actually very pro AI and excited by the future prospects.  I added a subscription to Chat AI because I was temporarily reduced in usage on Meta. I'm not entirely happy with it, but it does provide a different angle of approach at times from Meta that is refreshing. I have found that chatting about topics can develop a route to a story idea. Having both is good for this.  This film required adding a subscription to Leonardo AI. I'm mixed on the need for this, but I'm very impressed with the Motion 2.0 generator. It has been very useful for helping establish a set. Also, it has  the best crane to eagle eye's view as well. I've been able to generate views that the other video generators cannot. I rushed through this one. I don't feel like it's as polished as the la...

Path Unfolding Ep 2

Image
 Watch on YouTube: Path Unfolding Ep  2 Tea of Sorrow 5:39 This was written with assistance by Meta AI with Llama 4 and Eskitor. I decided to make this samurai (Kei) have a continuing series of events.  The challenge for this film was to clean it all up. I feel now I've learned the ins and outs of the open source film editor OpenShot. I see where my video distortions from framerate changes are generated. My aspect ratios and color grading flaws. I decided to try to focus on the technical aspects of making films.  It's not perfect, but it's definitely much better than the previous films. Some flaws are noticeable in the color grading of some of my composites, but I've managed to clean up most of it. This one took many generations of Japanese style music to get the components that I needed to weave into a music track. I found the ardianfe/music-gen-fn-200e generator to be my primary source. I took the Japanese flute and drum jingle from the first samurai film and used ...

Desperate Ride

Image
  Desperate Ride 4:21 This one was written with assistance by Meta AI with Llama 4. It was inspired by my recent visit to the Tallgrass Prairie Reserve in Kansas, USA. I wanted to create a film that captures a broad sense of space and has a lot of moving elements too. This was the perfect story for this. The major challenge here was the gag that has the rider falling from horse and on to the back of a buffallo. It utilized failed prompts for images that were created with layered elements in GIMP and then edited to create the action. The next challenge was the hat gag. It also require tedious setups for prompting. This film also made me aware of Vozo's lipsyncing weaknesses. Characters with beards are problematic.  Vozo is regarded as one of the most accessible AI generators for lipsyncing, using their precision mode, this was the best I could generate. I decided to not even bother for the last 2 shots of dialogue. The music was beautifully generated by Meta/music gen. It requi...

Circuits of Identity

Image
  Circuits of Identity 5:15 This one was written almost entirely by Eskritor. The idea was formed by some recent articles about gender assignment in robotics in Japan and Korea.  The challenge on this was creating an android that didn't look like everyone elses. Image prompting is limited to a language model and it's source material training. I've become more aware of the "styles" avalable and I'm beginning to learn how to morph my own. The next challenge was setting. Creating an environment, a "set" is a tedious process of acquiring the needed perspectives and weaving them together. I feel sometimes I'm working on a 3 camera stage set sometimes.  Creating the hand written note in the scene was another challenge that took a lot of effort. I was able to get GPT Image 1 to generate an image of the note that I layered into another image. I was unable to get any of the other image generators to do this. All the output had distorted and/or missing let...