Hacker News Reader

Comment by Dwedit | Hacker News Reader

In this example, 25 frames are generated using Stable Diffusion, then frames are interpolated using FILM-Net. I hadn't see FILM-net before, it looks really neat.

View on HN

This? Looks pretty amazing:

https://film-net.github.io

https://github.com/google-research/frame-interpolation

You can run it on Replicate too! https://replicate.com/google-research/frame-interpolation

Neat. Didnt Microsoft release a tool that morphed between two photos a decade ago? I dont recall the name unfortunately, but the effect was similar, less quality.

I was doing this with an After Effects plugin called Twixtor long before a decade ago.

https://revisionfx.com/products/twixtor/

Back in the DOS days I had (and a still do) a copy of a tool called 'Morph', it took two GIF images, and you placed marker points on the first image and then again on the second, and it generated an MPEG2 file of the morphing.

Very impressive for the time.

Mid 90s, baby!

I had the "DMORPH" program, which had you construct a grid, and it would generate separate image for every frame. Then you had to use "DTA" to turn it into a FLIC file. No MPEG here, no animated .gif here, you had FLIC as your animation format.

FLIC animation, now that is a blast from the past!

You're thinking of Microsoft PhotoSynth from 2006. This is similar to what google streetview showed up with.

From what I can see, they later revamped PhotoSynth to include actual 3d mesh reconstruction in 2014.

Morphing is different to interpolation and has been available on consumer computers since the 1990s (I remember making gifs in 1996 with it).

In morphing you end up with a blury mess for the between frames. This technique tracks individual features (eg eyes) and keeps them coherent.

Reply on news.ycombinator.com