🔧 Dev Update – Animation Experiments
🕑 Added 2025-09-06 15:57:18 +0000 UTCHey everyone!
I wanted to share a little behind-the-scenes look at what I’ve been experimenting with for Act 2. Lately, I’ve been working on making longer, smoother animations. My current process goes something like this:
Create a short 4–6 second animation
Save the last frame of that animation
Animate that last frame as a new sequence
Use FFMPEG to piece them together into one continuous clip
This works pretty well, but it also creates some challenges:
Color shifts over time can happen between stitched parts
The last frame doesn’t always have the same detail as the first (eyes closed, head turned, etc.)
When the character moves back into frame, details can sometimes change unexpectedly
Here’s an example:
First image (eyes open) → initial animation starting point
Second image (eyes closed) → the last frame of the 6-second video that I then try to animate
In the second image, certain details are missing or obscured (like eye color, facial features, expression, even the look of the man's penis). Since that’s what gets input into the model for the next sequence, it can cause the generated animation to drift away from the original look.
Another thing to consider is that this approach adds significant development time. Each sequence requires more trial and error before I can get a satisfying result. That means I can either create more shorter (4–6 second) videos, or focus on fewer but longer videos that take much more time to produce.
I’d love to hear your thoughts:
Do you prefer more frequent, shorter loops?
Or fewer, longer animations even if it means a slower pace of development?
This post may be a bit preemptive, but you’ll get to see the results of my efforts in the upcoming build this week!
– MorrakGames
Comments
Mike
Personally, I think it's a great idea. It gives you the opportunity to debug and assemble a longer video from small debugged sequences, at the cost of some inconsistencies, much faster than it takes to debug the whole thing at once. Sometimes it works right away, which is great, but that's rare. And so you have to try again and wait...and wait...and hypnotize the percentages on the screen. So for me: small and insignificant differences are not a problem, especially if they are outside the "central" area of the image. Figuratively speaking, if there is some action here, I don't look Celine in the eye too much. Maybe if the angle of view changed sometimes during the transitions, the resulting inconsistencies would be less disturbing... but that's just an idea. Anyway, Morrak, you are doing a great job that I really admire !! ... and I'm really looking forward to the next update.
BRobert
And a little rougher 😈