Posts

@Zerowinger
This is now canon and no one can tell me different. Vinyl is a martial artist.

>Makes picture adhering to their taste
>Gets off to pictures with their taste
>Ask if its odd to get off to pictures with exactly their taste

Hello, friends!

Is it odd or weird to get off to your own image generations?? I often find myself getting off to the stuff I create. Not that I use my own exclusively but I do use my own works. Granted what I make are within my specific tastes but does that just make me a perverted gooner? (Sorry this is the kind of shit that keeps me awake at night.)

Following character tags should be added:

Giselle, alias Irma, implies g4

Gaston, implies g4

Natalya, implies g4

@Thoryn
Glad I’m not the only one. My uploads have slowed dramatically.

@Equum Unfortunately, those are limitations of CLIP, which is what a lot of older models use, including PonyV6, Illustrious, and basically almost every model that competently renders ponies. One of the major limitations of CLIP is that it doesn’t really comprehend spatial relationships, which means it really only can do spatial relationships when the specific spatial relationship you’re prompting exists a lot in the training data. It’s not capable of dynamically putting together a new spatial relationship without a LoRA to assist.

Newer models have a much better understanding of spatial relationships (and most of them are also natural-language capable) which makes them much more useful for prompts like what you’re describing. Unfortunately, most of them suck at general pony knowledge; some of them might kinda vaguely get major characters like Twilight or Celestia right, but many of them can’t even comprehend the CMC. They’re also generally heavier models that require better hardware just to get tolerable generation times.

@Bendy and Boney
I think she’s trying to tell us something.

@ƿǣrloʒa
_{hey, that’s one of my pics}

@Equum
No, sadly haven’t had the time to play around with image generation that much the past year because of IRL things.

Garble should be a character tag and should imply g4.

@Thoryn
Did you end up making progress on this? Settle on any specific workflows?
I’m basically reliving this experience you’re having as I try to get up to speed on all this image generation stuff after stumbling into it in 2026. Lots of the same issues here.

Step 10 is super useful. Use that a lot.

Thanks for the feedback. I also added chapter 10.

Interesting, thanks.

Please alias closed eye -> one eye closed (main tag).

It mixed images of one eye closed and both eyes closed. I fixed the latter (on images shown with my filter) by replacing it with eyes closed. IDK how to handle images where only one eye is visible, so we don’t know if the other is closed or open.