Posts

@Lord Waite
thanks for the clarification!

For reference, Illustrious XL trying to handle ponies:

I’ve got a tendency not to use AI art generators that I can’t run locally, but I do remember Bing being good when I tried it previously.

As far as Pony v7 goes, that’s being trained on a different model, AuraFlow.
https://civitai.com/articles/6309/towards-pony-diffusion-v7-going-with-the-flow

There’s an interview from a few weeks ago here:
https://www.youtube.com/watch?v=8pw1LwRUGY4

Illustrious XL is more of a new XL based anime base model competing with pony. If you are generating anime/furry pictures, it might be interesting, and it seems to be big, but from what I remember, it didn’t do that well with ponies when I tried it, though I should give it another go. (SeaArt Furry XL can do ponies, IIRC.)

I heard that Illustrious XL is what ponyv7 is going to be on is that true?

Also shoutou5 to autismmix/confetti and pinkiepiemix

My go to has been Google Imagen 3.0
https://deepmind.google/technologies/imagen-3/

It’s a text to image model similar to Bing and DALL-E. Rather than using Gemini, I’ve been making images via the NightCafe creator studio. This checkpoint is very good at making ponies and anthros, and has a pretty solid idea of what the majority of characters are supposed to look like.

There are some issues with secondary characters, however, but there is an odd quirk about it: if for, example, you ask for an image of Big Macintosh, it will give you a pony that looks nothing like Mac. However, if you ask for an image of Big Macintosh, and then describe what he looks like, it will give you an image that’s pretty on point.

The checkpoint is also kind of weak when it comes to non-pony characters or creatures, such as Diamond Dogs, Buffalo, Griffons, and Yaks, and basically requires a bit more prompt tweaking to get them to come out close to the MLP style. However, it does have a good handle on Zebras and Dragons, and is able to fairly properly output images of those in the MLP style.

One other issue it has with creating anthros and some ponies is that sometimes simply describing their race (ie unicorn, pegasus, etc) isn’t enough, and will have a tendency to produce unicorns without horns or pegasi without wings, so you sometimes have to add in an additional prompt with things such as “glowing horn” or “spread wings” or some other descriptor of unicorn or pegasi elements to get it to stick properly.

Given this site is specifically for AI art, I feel like we should have a few threads for discussing things like prompts, and the models we use and such, and I felt models and loras deserved one (and embeddings, but it doesn’t seem like those get used as much any more).

So, what models and loras do you find yourself using often?

The obvious, of course, is Pony Diffusion v6 XL, and while there are a million spinoffs, I’m still highly likely to use the original.
https://civitai.com/models/257749/pony-diffusion-v6-xl

I’ve also been finding myself liking BlueFoxMix lately, and the style it gives pictures.
https://civitai.com/models/724196

Lora-wise, I like the Pony Quality lora for making the score tags a little less necessary.
https://civitai.com/models/333358/ponydiffusion-quality-slider

I also do rather like the Wholesome MLP Mix lora for style.
https://civitai.com/models/509312/wholesome-mlp-mix-pony-v6-xl

Of course, there are other, non-pony models I use. They may not be trained on ponies, but Flux and SD 3.5 Large can do text well. Flux is pretty good at actually following your prompt, and I think 3.5L edges it out style-size.

SeaArt Furry XL is a good general furry model, though it’s definitely one of these ones that relies on artist tags too much.
https://civitai.com/models/391781

Illustrious XL has promise and has already become a new base, though not great for ponies.
https://civitai.com/models/795765

NoobAI-XL is also looking good. I do need to explore these more.
https://civitai.com/models/833294/noobai-xl-nai-xl

But what loras and models do you like, and what things do you see that you like and dislike about them? (And, honestly, feel free to go into more detail on some of the ones I mentioned. I just wanted to throw out a few of the better ones to start things off…)

Oh, damn… I wanted to post it in General Discussions. Sorry everyone 😢

Seeing this place got me kinda curious, and now I have a big question.

Since this site is for AI generated content, is that logical to assume that if it had RP forum, it would be more like a place to give links to AI chatbots that users make? I mean, we have a Roleplay forum on main site for living people.

So… is that logical to assume that such forum, but for chatbots would make sense? Just a question, not an idea or a request.

@Montaraz13
No problem!

More pony G.I. Joe cosplays. From the top left - Rainbow Dash as Ripcord, Applejack as Leatherneck, Fluttershy as Lifeline, Rarity as Scarlett, Pinkie Pie as Shipwreck, and Spike as Dial-Tone.

Leeets see

Yaaay it works! Thaanks you. I could never figured it out!

@Montaraz13
That’s another nice one.

To display the image, type in >>image number plus either t or p added to the end.

For example, >>13462 with t added at the end gives you

Thumbnail resolution

>>13462 with p added at the end gives you

Preview image resolution

Ops it was missing the one that was supposed to be on display. How do you make it display pictures?

Here is the missign one: https://tantabus.ai/images/13462?q=prompter%3Amontaraz13

And yeah Bing is only text to image, squeare, no tools nor options (stuff at the start of prompt have more weight) and has quiiite heavy nsfw filters (Tried to make one of Fluttershy reading a book on bed or sleeping in bed and that triggers filters most of the time lol).

On the good side though, it is suuuper easy to use. You put in just a few words, even badly structured and usually you get pretty cool results and I really love these styles you can get out of it easily. Still trying to figure ways to mimic it in local AI.

@Montaraz13
Those are fantastic!

I haven’t used Bing image creator before. Is it simple text to image?

I really like how Bing does some fantasy/epic/out there concepts

Here is other two concepts that I really liked

Luna facing a giant cloud creature: https://tantabus.ai/images/13464?q=prompter%3Amontaraz13
Twilight watching over a dark city: https://tantabus.ai/images/13229?q=prompter%3Amontaraz13

@Lord Waite
Strange that it wouldn’t recognize stallions like those.

@Zerowinger
It is, and I knew I had to upload it when I generated it. I’ve always been fond of the two of them, and testing generating them and Twist is one of my typical tests for a new pony model.

(I also test generating named stallions because ponies like Prince Blueblood, Fancypants, Trenderhoof, and such really should be in there, but generally don’t have much luck on that one…)

@Lord Waite
That image is really cute.

While I can definitely see some issues I probably should’ve img2img’d away, I’m rather fond of this one.

@Zealousmagician
Yeah, that’s what I’ve discovered with Imagen. I don’t think it was trained on too many image sets with non-pony characters. It has a general idea of what the style should be like for some, like say dragons and hippogriffs, and it definitely knows what Discord and Chrysalis should look like, but for others like, say, diamond dogs and buffalo, it has a real hard time getting images in a MLP-style. Here’s one I made that’s supposed to be Little Strongheart:

Sort of close, but not really. Of course, the fact that I was trying to make an anthro probably didn’t help either. I think it’s one of those things where I need to do more experimenting.

@Zerowinger
I’m glad you like it! It’s a fun little experiment from way back in the Pony V1 days.

Pretty good birb- I’m not too familiar with imagen, but getting mlp characters with a non-pony focused model can be pretty tough, especially if they’re not too popular

@Zealousmagician
I love that starry elemental Luna one, I saw it while browsing the old uploads and thought it was amazing.

This was one of my first attempts at Captain Celaeno. One of the things about Imagen is that while it’s pretty great at getting pony characters, non-pony characters are far more hit and miss.

That Chrysalis looks pretty cool!

Here are some of my fav SFW images:

The mare in bed and the Luna ones are AI-generated with cleanups or a couple img2img runs, while the other two have much more substantial intentional edits and were tagged AI-assisted. I’ll hold off on the NSFW ones since it’s a safe thread.

@Montaraz13
That’s a great Luna and Celestia - something about leather jackets just look cool.

Admittedly the majority of my AI uploads on Derpi (and thus the majority of my artworks here) were dedicated to my rather autistic little series of character fusions between FiM characters and G.I. Joe characters:

Nightmare Moon as Cobra Commander

Chrysalis as The Baroness

Twilight as Duke

Cadance as Lady Jay

I still love this one:

(I have more)

Oh I love that one of chrysalis! I recall seeing it and I actually went and tested making a similar concept with Luna and then Celestia to match
Luna: https://tantabus.ai/images/25280?q=prompter%3Amontaraz13
Celestia: https://tantabus.ai/images/25281?q=prompter%3Amontaraz13

This is probably the one I dedicated the most time to (Light bondage/nsfw warning): https://tantabus.ai/images/6784?q=prompter%3Amontaraz13