Trying out AnimeGAN (september 23rd, 2023)

 AnimeGAN

September 23rd

animeGAN_inference



I spent a lot of time trying to locally install animeGAN on my computer. What kept me from using animeGAN on my computer, is that I got an error related to CUDA not being compatible with the version of python I had. I’ve run into CUDA issues before and I still don’t quite understand the point of CUDA and why different programs require different CUDA versions and also why GPU’s require additional CUDA installations.


The error message was suggesting that I install an older python version. I decided not to proceed because I was afraid it would mess up my local installation of a different AI tool that I use on a weekly basis. I tried to figure out how to make a virtual environment for animeGAN but I still got the same error. I looked into setting up a virtual environment because the other AI image based tool I use, uses a “venv”. Since I got the same CUDA error when trying to set up a virtual environment, I decided it’s probably best I hold off on that; animeGAN isn’t a tool I plan to use again.


I ended up using Google Colab for animeGAN. The notebook is pretty straightforward and I was able to generate some images quickly. I tried to input a video into the colab notebook but ran into some errors. I tried various things such as using a shorter video clip, directing the code in colab to a folder of a PNG sequence instead of an MP4, but I got a moviepy error related to FFMPEG. I used chatGPT to help me troubleshoot but even after I tried to install moviepy and ffmpeg, it didn’t work. 


I tried to install moviepy and ffmpeg:







MoviePy error: FFMPEG encountered the following error while writing file /content/result.mp4


Below are the results from animeGAN_inference.




I was curious to try inputting an unrealistic picture that is closer to a drawing to see what I would get: 

Comments

Post a Comment

Popular posts from this blog

(October 29th, 2023)Development of a Customized Lora: A Deep Dive into Personalized AI-Generated Imagery

Image
  Development of a Customized Lora: A Deep Dive into Personalized AI-Generated Imagery October 29th, 2023 Objective: The primary objective of this project was to create a professional-grade photograph using a custom AI model, termed "Lora." This initiative was inspired by Aragon (https://www.aragon.ai/), a commercial AI tool available at Aragon AI, which offers similar capabilities but at a cost. Methodology: The project began with the compilation of two image datasets. The initial dataset lacked diversity, consisting of overly similar images, which necessitated the creation of a second, more varied dataset. Both the standard definition (SD) and extra-large (XL) versions of Lora were trained using Kohya's framework, renowned for its robustness and versatility in managing advanced AI models. Challenges and Results: The anticipated high-quality output from the XL Lora did not meet expectations initially, as the images suffered from pixelation and blurriness. Adjusting the s
Read more

Digital Marketing with AI - 30 Page Marketing Plan

Image
I created a marketing 30 page marketing document utilizing AI. Check it out below. It's quite long!!! I also can't figure out why the formatting is messed up here.... G.M.O.: AI Content Generation Services   Project Description Summary: G.M.O. (Graphically Modified Organisms) harnesses innovative AI tools to produce unique and cost-effective music videos and digital content tailored for artists and musicians. By leveraging advanced AI technologies, G.M.O. enhances online engagement through creative visuals and animations, offering an economical alternative to traditional content production methods. This approach not only amplifies the digital presence of artists but also delivers distinctive content that resonates with their audiences. 1. Persona The goal of G.M.O. is dedicated to bridging the gap between artists and musicians and our innovative AI video solutions, ensuring their digital presence is not just seen, but felt 2. Organization G.M.O. is at the forefront of AI-driven
Read more