Posts

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...
Post a Comment
Read more

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...
Post a Comment
Read more

I'm Always Here

-
Image
  I'm Always Here 3:31 This film was written with assistance from Meta AI with Llama4. It's my first film of many that I'm  developing where I'll be exploring themes of AI and sentience. I wanted to make a film more dialogue driven as well. It's also a film to test lipsycing. I have had a rough time controlling mouth movements and I'll be using a new subscription to an AI app called Vozo. By uploading video or photo images with audio, a processed video can be created with synchronized lips and dialogue... at least almost. It's not perfect, but it's far better than anything I've utilizied to date. The ghosting on the girl's lips are distracting. I also wanted to prompt with a very specific location that involved movement and shadow. In this case, a subway car with moving shadows and reflections from the glass windows. There was a lot of misfired prompting on this one. I utilized google/veo 2 for some video generation. It saved me on a couple needs...
Post a Comment
Read more

Path Unfolding

-
Image
  Path Unfolding 5:13 This one was written with the help of Meta AI with Llama 4. It's inspired by my love of Japanese film, particularly the samurai theme films.  This film I wanted to have more engaging characters. I felt like my earlier films were more solo character driven. I also wanted to explore the use of action and space. The scene of having the owl and samurai in the same frame was challenging. Also I wanted to test the ability to create specific body postures and movement that I felt was necessary for this genre of film. Music is only Japanese flute and drum for a small segment. This I had to create using ElevenLabs sound effects AI generator. I cut and pasted what I thought was appropriate, thinking of Kabuki theater in the process. The end title music was created entirely by Meta/musicgen. The samurai was created as a character with openart AI's tool. I'm thinking of possibly doing more with this later. Once again, using layers of generated content in GIMP and ...
Post a Comment
Read more

Adagio for Ava

-
Image
  Adagio for Ava 4:37 This story was written with Meta AI with Llama 4. It evolved from an initial horror genre idea to what it is now. It's gone through many convolutions, the last major change due to the music generated by Meta/musicgen. I was able to cut and paste several runs into the final long progression. Changing the mood of the entire film, I think.  The challenge here was prompting. Many elements were needed that were very specific and keeping things consistent was difficult and impossible. The interaction with the vid screen scene and the violin performance. A lot of wasted images and video from failed promptings.  I did not make a character for this film. I utilized mostly cut and paste layers using Microsoft's Paint and the open source photoeditor GIMP. My dependence on editing is what made it all work.   Watch on YouTube:
Post a Comment
Read more

Drained

-
Image
  Drained 3:59 This film was written with Eskritor and my newest writing tool... Meta AI with Llama 4. Meta AI is absolutely free on WhatsApp. The interactive conversations I have working out story details has been extremely more efficent than the Eskitor app.  This story was inspired from my personal experiences with heat and mosquitos while living and sometimes trying to sleep in Thailand. I wanted to try building a story with no music, just sound effects. I also wanted to try to have more control of my setting and how my character behaved. I wanted to create an actor that had more personality and realism. To help with this, I created a special character using OpenArt AI's character creation tool. Most of the sound was created with the sound effect generator stackadoc/stable-audio-open 1.0, but a few analog sound effects from Freesound were incorporated. This particular film has given me more of an opportunity to use the sound editing program Audacity. It was instrumental in...
Post a Comment
Read more

Perhaps We Both Battle

-
Image
Perhaps We Both Battle  3:32 This one took 3 days to complete. The cost has gone up to about $34. I needed a subscription to an AI image generator. OpenArt AI has a vast amount of animation and image generators. I created my first character with their character creator tool, so I was able to prompt the old man into different settings. I also acquired a year subsription to the AI writing app Eskritor. This story was prompted with Eskritor. I developed the initial idea from a recent personal experience with a neighborhood dog. I'm living in a small village in Thailand and a dog named Som, likes to take bites at my ankles as I walk to the store. I eventually made friends by feeding him grilled chicken.  Som is Thai for the number 3. The dog has a stunted front leg that gives him only 3 legs to move about. I tried my best to generate a three legged dog and gave up. The art of prompting is beginning to dawn on me. My next goal was to move away from the storybook approach that styli...
Post a Comment
Read more