First AI Art Copyright Granted
The first-ever copyright for an AI-generated image has been granted apparently to the human author. Never thought it would be that fast and I’m very glad to see it as AI-generated images and video are here to stay whether we like it or not. We might as well move on with it so we can start creating more income opportunities on the other side of this AI art revolution.
This is very interesting since many tech news outlets including the Smithsonian produced articles stating the Copyright board had ruled earlier that AI-generated images didn’t qualify for protection. According to the above Ars Technica piece that was a common misconception as the board ruled copyright couldn’t be granted to the AI only a human.
It has been reported that stock photo sites are already being flooded with AI-generated images prompting Getty Images to ban them altogether. At least for now, due to very valid copyright concerns and not wanting to be a party to future legal action.
Let the legal battles begin!
SD Video, a Google collab runtime that runs online with Google collab and Google Drive. It’s not a straightforward setup. In fact, it can be rather daunting to jump in it the first time… just like the deep end of the pool… it looks scary. There are a few things you have to initialize on the way that starts up the process and loads the UI. They are in order on the collab page but if you’ve never worked with this type of interface before then it can be almost impossible to get started.
Several YouTube channels have videos on the process but the one I like was just one part of three different ways to produce Stable Diffusion videos. It runs from the 4:28 mark to the 8:00 minute mark and shows you step by step how to initiate the process, get a security token, set up your Google Drive, and start rocking with SD Video.
SD Video Setup and Usage – 4:28 to 8:00
A good portion of the video is devoted to running Deforum Stable Diffusion locally but, according to the video host, requires at least an RTX 3080 or 3090 so I haven’t tried it or the first method FILM: Frame Interpolation for Large Motion (simpler tweener generator) but the video is worth a watch to those interested in options. I will also point out that while it seems complicated… you just follow the video and forget the technical stuff, you should be up and running.
Also… when generating the UI for the first time you will get an error message. Press on the link for more information and look for a link on the subsequent page that gets you past some Legalese to use the AI model. Don’t panic… just read the page, press the link if you agree then go back and initialize the GUI again. You should be good to go now.
It’s not as complicated as it seems if you follow the video.
The GUI is nice, clean, and simple, and can be run in the small window you just initialized, or you can run it on the public thread which I ignored to use the already generated GUI. You check out that option for yourself. You put in a beginning and ending image prompt, set the variables, and go do something else while SD Video does its thing. You don’t have to leave the computer… but it will take some time. Up to 2 hours for 60 images which are four seconds of video.
If the prompts are right… it is four seconds of cool video too.
Once you run through the process one time, you’ll see how it all works. You might want to make a short 10-image video first, just to make sure you have it running right without having to wait an hour or two to see the results. This will also give you an idea of how long it will take to generate a video in the future. I had no snags and was running SD Video within a few minutes with the help of the first video above.
You will get the SD mpg video and all the images used to make the video which you download from your google drive. Links to everything you need including the other two methods of making AI-generated videos are available in the first video’s description on YouTube.
M.D. McCallum, aka WarLord, is an international award-winning commercial graphics artist, 3D animator, published author, project director, and webmaster with a freelance career that spans over 20 years. Now retired, M.D. is currently working part-time on writing and select character development projects. You can learn more about MD on his website.