Tantabus
Filters (Default) SettingsRegisterLogin
Rules Update - For a short summary on changes, check Here
Welcome! Please check this thread

Posts

For more information, see the search syntax documentation. Search results are sorted by creation date.

Search Results

Creative Corner » AI News » Topic Opener

mp40

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.
AISearch youtube
Posted Report

Creative Corner » Zebrasub generation (18+) » Topic Opener

Xada

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?
Posted Report

Site and Policy » Featured Image » Topic Opener

Creative Corner » Image Analysis and Feedback Thread » Topic Opener

AIPonyAnon

I’m creating this thread in the hope that we can get people to give each other useful feedback on the images that they create. This should help people to develop their own critical eye.
I was going to use ‘critique’ in the title, but that implies a level of interpretation. The intention here is to give reasonably objective feedback on errors or elements that detract from an image, and well-done things that improve the image.
If the creator has some stated goals or issues with the image, then feedback on how they might better reach these goals or solve these issues can also be given. Creators specifically asking for opinions on certain things is also fine.
In your analysis and feedback you should include, where possible, ideas and techniques for fixing the issues that you point out.
As an example, here’s one my recent gens:
Looking for basic errors we can see the following:
  • Cadance does not appear to have any sign of wings.
  • The bottom right of the inset section on the door behind Cadance is missing.
  • Her hooves (hoof shoes?) have slightly different shapes and embellishments.
  • Cadance’s tail is exceptionally long.
All of these issue can be fixed by starting with a different base gen, or by overpainting/inpainting/detailing.
A positive of the image is that the armor, clothing, and regalia all seem very coherent.
One issue I have is that I feel like the image is just sort of boring. Causes and solutions for this might include:
Problem Solutions
1girl standing Use more varied pose descriptions. Add more characters.
Basic, head-on camera angle Use a more interesting camera angle.
Basic lighting Use more interesting lighting descriptions (not well tagged, requires experimentation).
Background that is simultaneously dull yet distracting Use a different gen. Inpaint out distracting features. Describe the background differently.
No objects of interest. A weapon, shield, goblet, etc. might add some interest.
As I’m using a Noob based model, useful tags for things such as pose and camera-angle can be found in the e6 and danbooru tag wikis.
Some things I would like feedback from others on are:
  • Is the color grading okay? (difficult because I and many people do not have color accurate monitors)
  • What do people think of the face? I feel like it has a somewhat porcine influence to it and I’m not sure if I like it.
  • Is white and red a bad color combination with Cadance’s fur?
Please try to include feedback for others when you post a request for feedback. This should help to keep a good balance between giving and requesting feedback.

Tagging Discussion » "Generator:" tags should not imply "ai generated" » Topic Opener

tyto4tme4l

Something of an artist
Since “ai composition” is a thing now, tags like “generator:zoinksnoob” should not imply “ai generated” IMO.
Tag group
BTW: I feel like this “generator” term is pretty vague, I would prefer something like “model” or “checkpoint” instead.
Posted Report

Site and Policy » Victory from the jaws of defeat? » Topic Opener

mp40

initially I felt quite frustrated at the prospect of managing another booru for pony-related content, believing that existing filters were adequate to address unwanted material. It seems ironic, given that ponyV6 is a leading Al checkpoint and the filtering methods used on these image boards directly foreshadowed the current practice of prompt engineering.
After thinking about it maybe this is the best solution hopefully this helps concentrate and collaboration will thrive here. I hope this become a place that can pioneer ai generated art in its many forms to come!
What do you think? Could this approach help foster creativity, or are we just creating more silos for content? How can we ensure this space truly thrives as a collaborative hub?
Posted Report

Tagging Discussion » derpibooru exclusive should be aliased » Topic Opener

Site and Policy » The writing on the quality guidelines page is riddled with errors » Topic Opener

IWTCIPP

Honestly, this is just extra insulting.
Images that fail one of the criteria listed further down may to be deleted.
“may to be”
Practically all the examples of errors listed below could be be spotted and fixed before upload
“be be”
These sort of artifacts commonly appear on the the corners of an image
“the the”
Artifact on plant leave is clearly not a detail related to the plant.
“leave” should be “leaf”
Extra limbs, miss-sized torsos or limbs
“miss-sized” should be “mis-sized”
Pinkie’s left forelg vanishes into her apron or just missing entirely.
“forelg”
Big Mac’s arm would be unnaturally long, particularly as it’s wouldn’t be straight.
“it’s wouldn’t be” should be “it wouldn’t be”
Bad hands, too many fingers, things bending how they shouldn’t, weird bumps… Stylization is OK, fleshblobs are not.
“Stylization” shouldn’t be capitalized
AJ’s fingers aren’t great, but they’re not obviously wrong or the close to being the focus of the image.
Extra “the” before “close”
Weird eyes, extra nostrils, mouths that just aren’t right, eyelashes and eyebrows that are blobs or simply broken… There’s a lot of small things that can go wrong here, but given how important the face is, they have a lot of impact; faces are important!
“There’s” shouldn’t be capitalized
Iris / pupil shapes aren’t perfect, but not too bad either. Vague muzzle outline is again OK for cartoonish styles. (and AI really likes four freckes…)
“and” should be capitalized
“freckes”
The two characters on the left are noticeably low quality, and the Flutershy clone on the right is a mess.
“Flutershy”
That beach hair would snap immediately, and one of the supports o the back vanishes.
“hair” should be “chair”
“o” should be “on”
The outline isn’t bad or crunchy, and the weird eyes tears likely intentional.
“eyes tears” should be “eyes/tears”
For a fashion magazine cover, the focus would be the photo/model, so fake “ponish” language is fine. and the big magazine title text is OK; however, the smaller text is mostly just chicken scratches.
“and” should be capitalized
The sign at the top isn’t too prominent or seems important
Nonsensical/contradictory
All in all, I think that page is too low quality and you should delete it.
Posted Report

General Discussion » General questions » Topic Opener

Tagging Discussion » "prompter:" should change to "artist:" » Topic Opener

Creative Corner » Model and Lora (and related) Discussion » Topic Opener

Lord Waite

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…)
Posted Report

Creative Corner » Logical or not? » Topic Opener

WolfartX1

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.
Posted Report
Edited

Site and Policy » Unique spoiler images? » Topic Opener

Site and Policy » Maximum Spoilers filter » Topic Opener

Site and Policy » Museum of Tantabus » Topic Opener

🐴

nickers softly @u
This would be a page linked in the site footer that showcases the capabilities of the various AI models from back in the old StyleGAN days through whatever latest PonyDiffusion beta. Each entry ideally would have at least four examples: two of “typical” output and two of the model at its best (potentially with light retouching). Perhaps also an optional bonus column for noteworthy fuckups and WTF moments.
Posted Report

General Discussion » 3rd, all-inclusive site » Topic Opener

Phemto

Somebody should make a third site that treats derpi and tanta as back ends and recombines the feeds. A lot of people don’t care about “purity” and don’t mind seeing them mixed together, and there are plenty of situations (like looking for a good reaction image) where having to search two sites is a PITA.
Posted Report

Creative Corner » Post Your AI Art! » Topic Opener

Site and Policy » Opening Thread » Topic Opener

Admin

Administrator
Welcome to this place.
If you’re here, you likely saw the announcement on Derpi. Please check the site Rules and the FAQ.
  1. We’re aware of some potential issues with outgoing mails; if you try to register and don’t receive a confirmation email within 15 minutes (not even in spam), try resending the confirmation mail. If that fails, you can poke us for support.
  2. Not everything is fully set up yet, some tags may not have all the implications and aliases they do on derpi. Please check the tagging forum, where you flag if there’s anything urgent missing.
  3. All new users will start off “unverified”, so uploads may take a while to go through the approval queue before showing up.
  4. All ai content images on derpi, sans ai voice, were copied over automatically as of this morning. You can search for them by their ID on derpi, ala derpibooru import, source_url:*3503287*
  5. Ask questions if you have them and we’ll try to answer as best we can.
Posted Report
Edited

Tagging Discussion » General "Whoa this tag is missing stuff!" Thread » Topic Opener

LightningBolt

Moderator
ADHD fueled
Snappy name, huh? Well this thread is for when you come across a tag that appears to be missing implications, aliases, color, category, anything. This site is still a work in progress. A lot of tags were set up ahead of time, but there’s still a lot that were not, or were missed, or that come along through the pipelines.
That’s where this thread comes in. If you run into a tag that you think needs something, even if you’re not sure, you can drop it in here and we can look at it. You can also do this with tags that were set up and appear wrong or missing something. Mistakes happen, we are human, after all. (Or are we?)
Please link to thinks if possible.
Posted Report
Edited

Tagging Discussion » General Tag Discussion » Topic Opener

Showing results 1 - 20 of 20 total

Default search

If you do not specify a field to search over, the search engine will search for posts with a body that is similar to the query's word stems. For example, posts containing the words winged humanization, wings, and spread wings would all be found by a search for wing, but sewing would not be.

Allowed fields

Field SelectorTypeDescriptionExample
authorLiteralMatches the author of this post. Anonymous authors will never match this term.author:Joey
bodyFull TextMatches the body of this post. This is the default field.body:test
created_atDate/Time RangeMatches the creation time of this post.created_at:2015
idNumeric RangeMatches the numeric surrogate key for this post.id:1000000
myMetamy:posts matches posts you have posted if you are signed in. my:posts
subjectFull TextMatches the title of the topic.subject:time wasting thread
topic_idLiteralMatches the numeric surrogate key for the topic this post belongs to.topic_id:7000
topic_positionNumeric RangeMatches the offset from the beginning of the topic of this post. Positions begin at 0.topic_position:0
updated_atDate/Time RangeMatches the creation or last edit time of this post.updated_at.gte:2 weeks ago
user_idLiteralMatches posts with the specified user_id. Anonymous users will never match this term.user_id:211190
forumLiteralMatches the short name for the forum this post belongs to.forum:meta