When I'm trying to make consistent storyboards, MJ's latest composition memory feature really hits the spot.

Back in the day, the biggest headache when drawing a set of story illustrations was keeping things consistent. You’d generate one stunning image, but the next panel would have the characters in completely different positions and the background layout all messed up. The only fix was endless inpainting and local rework to force it together.

Lately I tried MJ’s dynamic composition feature, and it actually seems to remember the relative positions and spatial relationships of characters across a set of images. The transitions between multiple shots are way smoother now, and the emotional flow can carry through too. For us doing doujin storyboarding, this is way more useful than just stacking keywords.

Of course, it’s not perfect—complex multi-character scenes still drift—but at least I don’t have to start from scratch aligning every single panel. Has anyone here used it to run a sequence longer than four panels? Curious where the limit is.

Keeping shots consistent across frames has always been my weak point—if I can improve that, it’ll be a huge step forward.

Yeah, I’ve run into that issue with multi-person scenes too. Once you go past three people, it starts getting messy.

Yeah, so using an image as a base is way more reliable. Don’t trust its memory too much.

“Emotional continuity” sounds kinda vague, does it actually make a noticeable difference in practice?

Finally, some good news for fanart folks—no more having to line up positions one by one.

Waiting for the follow-up.

Reference images being reliable, sure, that’s true — but relying on them for an entire set of 20 will drive you insane.