dain-ncnn-vulkan VS frame-interpolation

Lien vers les instructions [https://github.com/nihui/dain-ncnn-vulkan/blob/master/readme.md de Readme.md)

I also found this and this, which FlowFrames seems to be based on. These would probably help with the frame extrapolation and increasing, but won't help me with the upscaling.

not SD based, but maybe this helps? https://github.com/nihui/dain-ncnn-vulkan https://github.com/nihui/rife-ncnn-vulkan

I can recommend DAIN for the 60 fps: https://github.com/nihui/dain-ncnn-vulkan

link to the instructions https://github.com/nihui/dain-ncnn-vulkan/blob/master/README.md

For AMD. But it takes forever to even do a few seconds on AMD for me (5700 XT; and Nvidia GPUs are impossible to get..). And NVIDIA. Generally you split the video in single frames; interpolate them with the DAIN AI Models (Idk which model is best for animation) and the images that the model created are then re-rendered to a video with ffmpeg.

- 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/