stable-diffusion-videos VS frame-interpolation

Main Code: https://github.com/nateraw/stable-diffusion-videos/

So I've continued to experiment with how many papers I can fit into a single pipe and have them play nicely together. The images below were created by combining the panorama code from omerbt/MultiDiffusion with the ideas from albarji/mixture-of-diffusers. Also turns out nateraw/stable-diffusion-videos can be seen as a special case of a panorama (in latent space rather than prompt space).

https://huggingface.co/spaces/tomg-group-umd/pez-dispenser https://huggingface.co/spaces/AIML-TUDA/safe-stable-diffusion https://huggingface.co/spaces/AIML-TUDA/semantic-diffusion https://github.com/nateraw/stable-diffusion-videos

The goal is to make a (short) video out of a given first and last frame. It is similar to what this guy does (https://github.com/nateraw/stable-diffusion-videos (7sec example video half way down page)). But instead of starting and ending with a prompt, I want to start and end with 2 different frames.

Hey Y'all! We've been working on a tool that extends Nate Raw's Stable Diffusion Videos repo and makes it as easy as possible to use for artists and are having a competition this week to stress test the beta and see who can use it to make the most compelling short video (40 seconds max)

Of course! There might be a better process but mainly used: 1.) Nate Raw's repo for morphing between prompts https://github.com/nateraw/stable-diffusion-videos 2.) Google FILM interpolation to smooth out transitions https://github.com/google-research/frame-interpolation

There are directions in the readme and an example script.

This does exactly that - https://github.com/nateraw/stable-diffusion-videos

- Lastly I used FILM, an image interpolation library to interpolate between images

1) generate video using https://github.com/camenduru/animatediff 2) upscale using SD-CN https://github.com/volotat/SD-CN-Animation 3) interpolate frames using https://github.com/google-research/frame-interpolation 4) add audio using https://huggingface.co/spaces/suno/bark

I am aware of interpolation as well (https://github.com/google-research/frame-interpolation) where you give it two images and it generates the images in between to get there but not sure I have good enough images to attempt to use this yet.

Super neat though. With some interpolation (possibly this Google Research one I just found via ChatGPT), it wouldn't be too bad to dump a video in and have it process in the background.

FILM repo by Google Research, they made this very cool interpolation method, my favourite so far. It's a pain to set up, didn't manage to run it on my local machine, I'm not very smart, and I can't get "pip install tensorflow==2.6.2" to run on my Windows, so can't run the requirements, so can't run the script.. BUTTTT you can use colab here, and once you hook it up to your GDrive, you can change the path to your folder of images, and it will process and spit out the interpolated video for you. I only have free tier, and it took 16 minutes for the sample video.

FILM (Frame Interpolation for Large Motion)

Edit: used this for the interpolation. Flow wasn't the correct word. https://github.com/google-research/frame-interpolation

Also off-topic, but their github.io page has a bibtex snippet for anyone wanting to cite their work in their papers. I'm not an academic, but I still strangely appreciate the gesture.

FILM? https://film-net.github.io/