ebsynth VS stable-diffusion

The only AI I can think of would be EbSynth, which would still require some frames to be fixed in Photoshop, but might work.

EbSynth - Transform Video by Painting Over a Single Frame

Download ebsyth from https://ebsynth.com/ , install it. (Make sure your anit-virus did not block it, or else it won't works)

EbSynth (Used to interpolate/animate using painted-over or stylized keyframes from a driving video, à la Joel Haver) https://ebsynth.com/

There is something called ebsynth on GitHub: https://github.com/jamriska/ebsynth

Anything AI is going to be divisive, but I think you already have a pretty good grasp of the issue. Adjacent to this there is stuff like EBSynth https://ebsynth.com/ which rotoscopes video footage. Joel Haver uses it to make all his animations solo and has a video going over the process - https://www.youtube.com/watch?v=tq_KOmXyVDo

Stable Diffusion: It is based on a kind of diffusion model called a latent diffusion model, which is trained to remove noise from images in an iterative process. It is one of the first text-to-image models that can run on consumer hardware and has its code and model weights publicly available.

Which is a 1-click install of Stable Diffusion with an alternative web interface. You can choose a different approach but this one is pretty simple and I am new to this stuff.

an invisible watermarking of the outputs, to help viewers identify the images as machine-generated.

It sounds like you just want to set up Stable Diffusion to run locally. I don't think your computer's specs will be able to do it. You need a graphics card with a decent amount of VRAM. Stable diffusion is in Python as is almost every AI open source project I've seen. If you can get your hands on a system with an Nvidia RTX card with as much VRAM as possible, you're in business. I have an RTX 3060 with 12 gigs of VRAM and I can run stable diffusion and a whole variety of open source LLMs as well as other projects like face swap, Roop, tortoise TTS, sadtalker, etc...

Use specific GPU on multi GPU systems · Issue #87 · CompVis/stable-diffusion · GitHub

I dealt with this in one of my posts. At least SD 1.1 till 1.5 are all trained on a batch size of 2048. The version pretty much everyone uses (1.5) is first pretrained at a resolution of 256x256 for 237K steps on laion2B-en, at the end of those training steps it will have seen roughly 500M images in laion2B-en. After that it is pre-trained for 194K steps on laion-high-resolution at a resolution of 512x512, which is a subset of 170M images from laion5B. Finally it is trained for 1.110K steps on LAION aesthetic v2 5+. This is easily verified by taking a glance at the model card of SD 1.5. Though that one doesn't specify for part of the training exactly which aesthetic set was used for part of the training, for that you have to look at the CompVis github repo. Thus at the end of it all both the most recent images and the majority of images will have come from LAION aesthetic v2 5+ (seeing every image approx 4 times). Realistically a lot of the weights obtained from pretraining on 2B will have been lost, and only provided a good starting point for the weights.

stable diffusion · CompVis/stable-diffusion@2ff270f · GitHub