This got a good laugh out of my wife this morning when my son asked to hear “Let it Snow” again.

Excellent - thanks for the heads up on those others

That was phenomenal.

I made this comment on another thread, but clearly it’s how the Romans spelled it: Tvvix. /s

Ah, yes, the traditional Latin spelling: Tvvix.

DOOM: Eternal (single-player) and Star Wars Battlefront 2 (2017) (with friends). DOOM is incredibly fun and great to play even for 30 min at a time as a busy adult. Battlefront likewise supports my relatively busy group of friends being able to play for a bit at a time and in various combinations without being a huge commitment. I love that I can play easily with 1 or 5 friends without issue and still have fun.

There’s a way to do this in Auto1111 (sort of):

1. generate an image with part of your steps
2. Enable openpose
3. Add the partially generated pixel image
4. Set controlnet to start at the halfway point, etc.
5. re-generate the image with the same settings

This feels pretty janky, though. I think you could do it better (and in one shot) in comfyUI by processing the partially generated latent, feeding that result to a controlnet preprocessor node, then adding the resulting controlnet conditioning plus the original half-finished latent to a new ksampler node. You’d then finish generation (continuing from the original latent) at whatever step you split off.

Yeah, I never had good luck with jerboa… it worked sometimes, but I was mostly using liftoff (which is pretty good, in my opinion).