Posts

I’m curious which method/UI people are using for image generation. Is A1111 still widely used? Is ComfyUI more popular than Forge? How many are generating locally compared to online?

I’m actually in a hate/love relationship with Pony (SD XL) in general. In my honest opinion, SD 1.5 was so much better and generating detailed backgrounds. That’s why I, for quite a while actually, used both (like here). Back then I used Aniverse/Anitoon a lot in various versions and just used Pony to do the Characters.

But since it was a huge hassle and my pc crashed 50% of the time switching models one the go, I turned to PonyV6 full time. I used that an Autism for a while, got stuck on T-Ponynai3. It has this light “dirtyness” of left in sketch lines. And it can produce so much more detailed background than PonyV6 in my opinion. Here is an example. The light roughness makes it look a little more hand drawn in my opinion. Pics not done, so that is that.

I only use Loras for human chars. Since most people generated are either muscled dudes or near anorexic big boobed girls, I need them to stray away from that. For ponies I use non at all.

I tried out NoobAI-XL v-pred 1.0 yesterday, https://huggingface.co/Laxhar/noobai-XL-Vpred-1.0:

Wildcarded through a fair few combinations of artist styles when generating this image. Judging from that, it seems to have a better understanding of style and texture than the eps-pred version. It also seems to be slightly worse at fine detail, but that may just be a product of its better understanding of style. It needs further testing with artist tags that do highly detailed works to see if that is a limitation of the model.

@Sunny
It really is a great little engine for making ponies.

i used imagen to generate this

Bit of a note for those posting off-site image here; there’s a “spam protection” system that sends posts with hotlinked images for review, to prevent spam (and worse) attacks. After a month it goes away, but, well, no account (even this one) is older than a month yet…

Still, please do post, and if it gets flagged we’ll try to hit the Approve button ASAP. Sorry for the inconvenience!

I am personally interested in the best one can get from the AI pipeline from prompt to output image without human input of any kind after the initial prompt, so nothing I post uses any post-generation editing, not even inpainting. These are a couple of my favorites. I haven’t uploaded much yet, but I’ll be uploading more soon.

Flurry Heart

Scarlet Ribbon (my author avatar from an ongoing story on FimFiction)

Well, I’m not a programmer or anything. Originally I just wanted to ask a question, since it’s a close theme to the site’s theme. AI creativity.

I hope that people will see this question a good base for new way of creativity on site.

And if such forum or even separate mini-site run by Derpibooru, for bots will be created, I highly recommend to split it into SFW and NSFW sections, so bots won’t mix up. So people who just want a wholesome and heartwarming chat with characters won’t bump into a character that is programmed to act like if you put filters to everything completely.

I use bing ai! I’m probably a minority in that due to its censorship but it can produce some good images!

@Zerowinger
I hadn’t considered the lean being a little weird. He does look like he’s walking a little too leisurely to be leaning that much to turn.

The Noob based models seem much better at weapons and armor than other SDXL/1.5 models that I’ve used. The models in general also like to use cutiemarks in places where you might find an emblem.

An anthro pic of Sunny showing her wilder and more adventurous side.

@AIPonyAnon
Aside from the fact that Shining looks like he’s leaning to one side, I don’t see any issues with the image. I like the armor design you got on him and how it has his cutie mark as an emblem.

For AI News, MattVidPro does regular news videos about new AI things coming out:
https://www.youtube.com/@MattVidPro/videos

Nerdy Rodent has some pretty good AI art content, usually using ComfyUI:
https://www.youtube.com/@NerdyRodent/videos

Olivio Sarikas also puts out some good AI videos on things coming out:
https://www.youtube.com/@OlivioSarikas/videos

And there are some interesting things on Code Crafters Corner as well:
https://www.youtube.com/@CodeCraftersCorner/videos

And you’ve watched Civitai’s All things Pony v7 stream with AstraliteHeart by now, right?
https://www.youtube.com/watch?v=8pw1LwRUGY4

Hey, I’m starting this thread to save n share some cool videos, but I also im trying to collate some of these ai video and image tools, feel free to share your faves too, since they might inspire what we make.

I’m curious about the subtle differences between chatbots. Sometimes it feels like they’re all just the same LLM with a thin roleplay layer on top.

Like, Fluttershy shouldn’t automatically give advice on optimizing Stable Diffusion prompts, but I’d like to be able to guide her in that direction to personalize the character to my liking.

Something felt compositionally off in this one:

I realized it after upscaling and couldn’t get any outpainting to work well. I had hoped to add another section on the right-hand side in the hopes that it would balance the image a little better. Would be interested to hear if anyone has thoughts on if/why this has compositional issues, and ways you might fix it.

I have noticed that no matter what i do with Pony XL and AutismMix. When i try to pair a pony with a zebra, it will ALWAYS generate the zebra as the dominant partner. Even though i am trying to generate images where a zebra is a sub, it never works. Any ideas how i could actualy generate zebrasub?

I’ve done a lot of cute pics, but haven’t gotten around to uploading all that many of them here yet. Here’s one I did decide to upload.

It’s hard to choose, but from my SFW images I would pick these:

This was a test image of Flurry Heart I did to see if Imagen knew what she looked like, it produced a really nice output I think. Doesn’t show her wings, though it could be argued they’re under the dress.

@AIPonyAnon
I only general stallions, so yeah, I’d like to see more.

Here are my favourite AI-generated pony images, created using my custom model mix, BlueFox Mix.

This is one of the favorite images of those I’ve generated. I think I managed to get it realistic enough that it feels like you could reach out and feel the fur, but not so realistic that it’s in the uncanny valley.

@LightningBolt
Cute; I need to generate more stallions.

While I disagree about calling AI images art myself, this is my favorite one I have generated so far, and why it’s my avatar here. I minorly edited it as AI is terrible at understanding which eye should be what color for heterochromia.

It makes me wish I could do more local generation.

@Zerowinger
Maybe. What I’m probably going to do from time to time is post ponies cosplaying as/ponified characters from games I’m currently playing.