Tantabus
Filters (Default) SettingsRegisterLogin
Character LoRAs - Want more character variety? Then check This List!
šŸ‘» Ghost Signatures! Want to know how to easily remove them? - Check Here!

Posts

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

Search Results

Creative Corner » Liquid Rainbow Effect » Topic Opener

truekry

Not an Artist

Liquid Rainbow

Foreword
So, around a week ago I started playing around with Illustrious. And coming from PonyV6, I fast learned that it can be a lot more ā€œcreativeā€. Yes, a PonyV6 models knows ponies better, but Illustrious, in my opinion, knows more ā€œconceptsā€. As I do with new toys, I played around and found the effect mentioned in the title:
Resources
We need 3 things:
  • An Illustrious model. I worked with this one. But I tested it with this one, too. Both work, for others you have to try yourself.
  • The ā€œVelvetā€™s Mythic Fantasy Stylesā€ Lora in version 2 for illustrious. (This Lora add a detailed anime style. Any Lora adding could work, I like this one.)
  • The ā€œLeIsT0 | Shiiroā€™s Stylesā€ Lora. (This one helps making the colors ā€œpopā€.)
The Prompt
The prompt for the Twilight picture looked something like this:
QUALITY WORDS, 1pony, my little pony, pony, feral pony, unicorn, Twilight Sparkle, casting magic at viewer, shiny fur, limited palette, (glow, liquid glowing magic, glowing liquid purple magic)++, intense expression, dramatic lighting, strong depth of field, wind-blown hair, gritty realism, cinematic shot, dutch angle, (simple background, black background)++, dust particles, dynamic pose, dynamic composition, foreshortening, blurry edges, MORE QUALITY WORDS
Some may be confused about the ā€œ++ā€ signs. I work with Invoke, which takes ā€œ-ā€ and ā€œ+ā€ signs as weights. A ā€œ++ā€ is around 1.2. So if you use a different UI, you will have to try around a little. The important parts are simple background, black background for the mat black background to play with. If I lowered the weights, the loras added stuff into it.
The effect itself is achieved with limited palette, dramatic lighting, glow, liquid glowing magic, glowing liquid purple magic. Limited palette makes the AI use as few colors as possible, what is then overridden by the ā€œpurple magicā€ part with a higher weight. Muting any other color beside the one mentioned. If you replace ā€œpurpleā€ with ā€œrainbowā€, you get the colors of the rainbow. Easy.
Now the lora weights. I used both with good results at 0.8. The trigger words are not in the prompt since Invoke has its own way to add loras that doesnā€™t need them. If you add a lora, it gets activated, thatā€™s it. You find the trigger words on the civitai page.
I used Euler A at 25 steps with a CFG around 7 for all the pictures here.
That should be it, really. Have fun!
Important
The more in detail you describe the character in the prompt, the more detail gets added, and with that: color. If you want good ā€œshade playā€ be as brief as possible. (Thatā€™s why it works better with known characters since you only have to add there name most of the time.)
More Examples
A few more raw examples:

Side Note
If you use the Fantasy Lora at 0.8-1.0 and the ā€œLeIsT0ā€ Lora at 1, with ā€˜limited paletteā€™ and no rainbow liquid you get this comic looking style:

Site and Policy » Badges? » Topic Opener

Site and Policy » Site Development Notification and Feedback Thread » Topic Opener

Admin

Administrator
This will mostly be used to highlight features specific to Tantabus, or that could be relevant to all users. For most updates and feedback you should check the thread on derpi, as thatā€™s the primary for Philomena development.
Now with that saidā€¦

[March 19 2025]

- New search and tag suggestions

  • Go to Settings and Metadata (Fancy tags) and Local (search auto-completion) to enable
  • This will autosuggest tags as you type so long as they exist on an image
  • This will show if a suggestion is aliased
  • For searches, you can set to also keep search history

- CivitAI post scraper

  • The upload ā€œFetchā€ function now supports CivitAI /posts/# URLs
  • This will grab the images under a given CivitAI post, and you can select which to use
  • Direct image URLs arenā€™t supported (API limitation), but every image is part of a Post, even if itā€™s just one
  • Fetch still uses ā€œartist:ā€ instead of something more appropriateā€¦ weā€™ll work on that
Posted Report
Edited

Creative Corner » Ghost Signature Removal » Topic Opener

truekry

Not an Artist
Ghost Signatures are these text artifacts that sometimes pop up in the corners of AI generated images. They are unsightly, and are counted as a generation error on Tantabus. But there is a very easy solution to rid your picture of them before uploading and all you need is your trusty browser:
This quick edit can be performed in a few minutes and most of the time not even one. So help us fight the good cause and get rid of these nasty errors.
If itā€™s something weird
And it donā€™t look good
Who ya gonna call?
Posted Report

General Discussion » What are you listening to? » Topic Opener

Creative Corner » NSFW Animations » Topic Opener

Mercurial

Has anyone been able to get a decent nsfw output with a video model like Hunyuan or the new Wan 2.1?
I tried out Wan2GP i2v with a pony image, but it ended up being terrible with basically none of the expected motion.
And each generation takes like an entire hour for me so Iā€™m not sure itā€™s even worth trying at this point.
Anyone else had better luck?
Posted Report

General Discussion » Post a random image from your Favorited images [A.I. Edition] » Topic Opener

Creative Corner » Post Your NSFW AI Art... here! » Topic Opener

Creative Corner » Image Preference Sorter » Topic Opener

Teaspoon

poni
So I was looking for a simple pair comparison sort tool and all the ones I could find were ad bloated or just not good.
So I set on up myself.
large large
Why? idk. Often I gen a bunch of stuff with minor differences, or do several inpaintings in one go, or tinker with styles and end up mired in indecision. You can use it for whatever, deciding whoā€™s best pony or which meal you want I guess.
Posted Report

Creative Corner » Best way to generate X Y plots? » Topic Opener

Thoryn

Latter Liaison
I saw a couple of X Y plots ages ago, and wonder what is the best way to generate them, automatically adding image as well as the configuration that changed for them in the plot.
(Things like model, sampler, scheduler, steps, prompt, CFG, size/aspect ratio etc.)
Posted Report

Site and Policy » The tag change post limit problem » Topic Opener

Adusak90

Background pony enjoyer
Iā€™ve been editing the tags in the pictures for some time and it has become a real chore to need to wait for the next day when backlog of pictures gets higher than my ability to edit them (even if I only edit the feral ones). Is there any way to remove that limit to trusted tag editors?
I think 500+ changed tags that are valid (even if we make 10% wrong as the benefit of the doubt) should be enough to get me enough trust to give someone unlimited tag edits.
Posted Report

Creative Corner » Images with character in mirror » Topic Opener

Thoryn

Latter Liaison
Iā€™ve been trying to make images where a character is also seen in a mirror, but donā€™t get any results that are remotely close to decent.
Is it possible with just text to image prompting, or do I have to use sketching and image to image, external image tools or other tricks?
For the record currently using Pony V6.
Posted Report

Creative Corner » Samplers » Topic Opener

mp40

Hey, so whatā€™s the deal with Stable Diffusion samplers? Iā€™ve used Notebook LLM to get a summary of their differences and aims, but does anyone have any practical insight using them?
Heres a notebooklm podcast where it breaks down in depth the differences https://notebooklm.google.com/notebook/0676cdde-a432-4322-94d9-99f2e99e2603/audio
And a abridged briefing doc in laymanā€™s terms
Euler: "Basic Steps" or "Simple Subtraction" - This sampler works by simply removing noise in each step. It's like taking away a layer of blur to reveal the image. It is also one of the fastest and most straightforward samplers 

Euler a: "Creative Variation" or "Adding Noise" ā€“ This one is like the "Basic Steps" sampler, but with a bit of random noise added back in at each step. This makes the results more unpredictable, like a creative filter that produces a slightly different image each time [2, 3]. This also means that the image will keep changing as more steps are added [4, 5].

DPM2: "Smart Prediction" - This sampler uses a smarter way to predict how to remove the noise, making it more accurate [6].

DPM2 Karras: "Smart Prediction, Better Colors" ā€“ Like the previous one but with improved color quality.

DPM++ 2M: "Advanced Smart Prediction" ā€“ An improved version of "Smart Prediction" that uses some extra information from previous steps to make better predictions [6, 7].

DPM++ 2M Karras: "Advanced Smart Prediction, Better Colors" ā€“ Like the previous one but with improved color quality [6, 7].

DPM++ SDE: "Detailed Stochastic Prediction" ā€“ This sampler uses a more complex math model to understand noise, resulting in detailed images [7]. It is stochastic, meaning that it introduces a degree of randomness, which can lead to varied results [8].

DPM++ SDE Karras: "Optimized Detailed Stochastic Prediction" - This is a version of the previous sampler that is optimized for better performance and image quality [7].

DPM fast: "Fast DPM" - This sampler is designed to be fast, but may require more steps and is not generally recommended [9-11].

DPM adaptive: "Self-Adjusting Detail" - Instead of using steps, this sampler adjusts itself based on a setting that changes the image's contrast and saturation [4, 12].

Heun: "Two-Step Correction" - This sampler works by predicting the image, checking the prediction, and then combining both for a better result [13]. It uses a weighted average of two noise estimates [14].

LMS: "Artistic Style" or "Painterly" ā€“ This sampler uses information from previous steps to create an image with a more artistic or painterly style [15]. It can struggle with generating detailed characters or animals [16].

LMS Karras: "Artistic Style, Better Colors" ā€“ Like the previous one but with improved color quality [16].

DDIM: "Photorealistic Detail" or "Smooth Solver" ā€“ This sampler uses a special method to generate images which are often photorealistic and highly detailed. It was widely used, but is now considered outdated by some [17, 18].

PLMS: "Quick Estimator" ā€“ This sampler quickly estimates the noise and removes it, but it is not generally recommended because it is slower and produces worse results [9, 19].

LCM: "Fast Refiner" or "Single Step Image" ā€“ This sampler can produce good images very quickly, in as little as one step. It uses a special technique to refine the image in its latent space [20].

Restart: "Noise Reset" or "Iterative Correction" - This sampler is like restarting the image generation by adding a lot of noise, and then starting again with the denoising process. It does this several times [21, 22].

UniPC: "Smart Combination" or "Flexible Solver" ā€“ This sampler is designed to combine information in a way that it can be used with many different models. It can also change its level of accuracy to work faster [23].
These names aim to be more intuitive, focusing on the core action or result of each sampler. For example, instead of ā€œDPM++ 2M,ā€ you get ā€œAdvanced Smart Prediction,ā€ which better describes what the sampler does, without needing to know the underlying math. The ā€œKarrasā€ variants are noted for their improved color quality. The ancestral samplers have ā€œvariationā€ or ā€œadding noiseā€ in their names. The goal is to provide a better, more intuitive understanding of how each sampler functions.

Site and Policy » 'Hide' Button Isn't Working for Me » Topic Opener

BigBuggyBastage

Go fsck yourself
If I click the Hide button for an image, I expect it to be hidden (unless I click the Show Hidden link at the top of any page) upon refreshing. But it is not doing so for me. The images remain visible.
Iā€™m using the ā€˜Everythingā€™ filter, but Iā€™m using the exact same for several other ā€™boorus, and not having this problem.
Any help would be appreciatedā€¦and Iā€™m sure itā€™s something silly Iā€™ve done wrong.
p.s. This is occurring across browsers (chromium & firefox) and OSes (Arch Linux & Win10), with and without extensions.
EDIT: As of now (~ 11 PM UTC 2025-01-12), the Hide functionality IS WORKING NORMALLY. Iā€™m unsure why ā€“ literally nothing has changed on my end ā€“ though Iā€™m thankful itā€™s ā€œfixed,ā€ even if temporarily. Iā€™ll keep an eye on it, and report back any change in this.
Posted Report
Edited

Site and Policy » We need quality standards » Topic Opener

truekry

Not an Artist
Hello and welcome to my little nitpick corner. I know the side is young and all, but we need a quality standard. And Iā€™m not talking about AI mistakes. AI is not it its infancy anymore and it is really easy to generate general good looking ponies these days. (Especially since they donā€™t have hands.)




You canā€™t tell me this arenā€™t gen-dumps. Just by following any guide/video and using a free online gen you get better looking results. I picked these examples at random from the last ten 5-6 pages, but there are so many more.
We need a bare minimum beyond ā€œplease only whole ponies, not disfigured garbageā€. To quote rule #9:
We strive to create a community that showcases the best of what AI has to offer, from raw generations to artworks that used AI as part of their creation process.

Creative Corner » LoRA - Characters » Topic Opener

Teaspoon

poni

Thread to compile known character LoRAs

https://tantabus.ai/pages/lorachar
Not all characters are well known (or at all) in PonyV6 or other SDXL models, so LoRAs are often required for quick gens. Multiple LoRAs for lesser known characters already exist, but are not always easy to find. Herein Iā€™d like to list known ones.
Of course, please comment in the thread with the ones youā€™re aware of, and any additional info you might have for it, like base model (PonyV6 for 99% of them, but still), trigger words, strength, etc. and Iā€™ll add them to the first post(s) the page above as soon as I can.
cleaned up to cut clutter
Posted Report
Edited

General Discussion » Ai Music? » Topic Opener

General Discussion » When did Tantabus.ai be founded? » Topic Opener

Background Pony #AB28
The earliest image >>8 was uploaded on 2016/12/12, but the first idā€™s image >>1 was uploaded on 2024/11/28, and it was in December 2024 when Tantabus.ai prospered. So when did it be founded? 2016 or 2024?
Posted Report
Edited

Creative Corner » ADetailer » Topic Opener

Shows and Movies » Sonic the Hedgehog » Topic Opener

Creative Corner » Pony Wildcards » Topic Opener

Site and Policy » Wrong link in description (to other parts of image series) » Topic Opener

Thoryn

Latter Liaison
The description in >>29315 should link to >>29316
Likewise, >>29316 should link to >>29315
Cause of the issue is that the link in descriptions uses the image ID from the source, which does not correlate to the image ID on here.
Iā€™m unsure if it should have been reported (using the Other cause) or not.
Posting it here instead in case reports are better meant for high priority matters.
Can probably use this thread to collect ā€™em all, unless you have a script to find and/or fix them, if there are many instances of the error.
Edit: Same issue is also with the 6-image-series of >>15156, >>15350, >>15398, >>15586, >>15638 and >>15685
At least in this instance, the series has its own tag tag to make them all easy to find, but although the current image linkā€™s ID gives a 404, itā€™ll eventually link to something completely wrong instead.

Site and Policy » Question regarding foalcon / anthro (of various types) » Topic Opener

Thoryn

Latter Liaison
Can we get descriptors somewhere of anthro, unguligrade anthro, semi-anthro, plantigrade anthro and possibly others, in addition to a table in the rule set of what is allowed to be mixed? Because Iā€™m a bit confused.
If I understand rule 5 (bullet point 2) correctly, sexual situations of anthro mature character is fine, sexual situations of non-anthro underage character is fine, sexual situations of anthro underage character is not fine?
Do not upload images of characters in sexual depictions or scenarios who look underage and look human or human-like (anthro), regardless of style. Do not discuss or link to sites that knowingly host such content.
So, for a sexual image of an underage character which has fingers and feet, itā€™s forbidden and nothing else matters?
Just wanting to know if I understand this right, or if itā€™s more like ā€œif it looks like MLP itā€™s fine, but if it looks like a real child cosplaying MLP, itā€™s notā€.
Posted Report

Creative Corner » Text-to-image prompting » Topic Opener

Thoryn

Latter Liaison
Hello all, Iā€™m hoping people can share their tips and tricks with regards to text-to-image prompting, as I am hitting a few hurdles that seem too silly to be a problem, yet they are.
My most basic issue at the moment, is that Iā€™ve been trying to make some Christmas artwork, where the composition in my head is that thereā€™d be a full view of the tree, with packages and a pony at the bottom of it. Sounds easy and very doable.
The biggest issue Iā€™m having, is that no matter what I prompt, it always crops the tree and only shows the very bottom of it.. in the rare instance it gives me a seed with a full tree, itā€™s pot-plant sized.
I have tried to put christmas tree at the start of the prompt, majestic christmas tree, full view of christmas tree, big christmas tree etc, as well as putting things like zoomed in, cropped etc in negative prompt. Iā€™ve also tried multiple aspect ratios. (1:1, 16:9 and 9:16)
Is there something obvious with my prompting that Iā€™m doing incorrectly? Do I really need to get a LoRA for such a common thing?
Model: ponyDiffusionV6XL_v6StartWithThisOne
Posted Report
Showing results 1 - 25 of 50 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