Posts

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

Search Results

Creative Corner » Need a new web based AI generator. » Topic Opener

Ace-Starfield

Anthro Connoisseur
Hey! I used to use Civit.ai until they locked anything NSFW behind a paywall. I’ve been trying to use Perchance but it’s far from amazing. Does anyone have any suggestions. Preferably something free lol.
Posted Report

Creative Corner » LoRA - Characters » Post 79

Creative Corner » Welcome to PPAA (Pony Porn Addicts Annonymous) » Topic Opener

Background Pony #26ED
Good Evening my name is [Background Pony #XXXX] And I…sniffs dramatically …am a Pony Porn Addict…
It started with E621… Just a normal furry, consuming my daily yiff… not a speck of Brony Blood in me…
But then… I saw it.. art by Xennos… adorable mares and fillies… all cute and fluffy and adorable…
I was lost in an instant… And with the power the AI Overlords have given us… looks dramatically in the distance
But we are not alone everypony… we have hope… we have each other! Join the PPAA! Puts down mic and stares back into the empty room

Creative Corner » I've Been away for about a year... » Post 10

VenisonCreamPie

EquineCreamPie~<3
@VenisonCreamPie
Your user name is truly a sight to behold. It explains why I only see 10 of 110 images under your artist tag.
I’m just generally curious what people wanna see!
Something SFW so I can actually see it. :P
Huh… only 10 huh… that’s some legit shots fired lmao xD
I accept this incredibly reasonable request~<3

Creative Corner » I've Been away for about a year... » Post 9

Background Pony #120D
@VenisonCreamPie
Your user name is truly a sight to behold. It explains why I only see 10 of 110 images under your artist tag.
I’m just generally curious what people wanna see!
Something SFW so I can actually see it. :P

Creative Corner » I've Been away for about a year... » Post 8

Ah okay, I didn’t know ForgeUI can also be used as a service. I know what you mean with Forge Coupler feeling less intuitive. I needed to get used to it when I first started using it and I still need to learn a lot of its potential.
No problem!

Creative Corner » Diary of a prompter » Post 10

Creative Corner » LoRA - Characters » Post 78

Creative Corner » LoRA - Characters » Post 77

Creative Corner » LoRA - Characters » Post 75

Creative Corner » LoRA - Characters » Post 74

Creative Corner » LoRA - Characters » Post 73

Creative Corner » I've Been away for about a year... » Post 7

VenisonCreamPie

EquineCreamPie~<3
It’s not really my setup, its a service I use, they don’t have Regional Prompter anymore. (One of these days I’ll properly use my own PC)
Any I Hate Forge Couple with a hot firey passion, I can’t intuit it as much as easily as I did regional prompter lol it usually just refuses to listen… but… I did have a minor breath thru the other day with the method I was attempting to do it… so if you see an image by me Cherilee showing a chalkboard…with a sex Ed lesson that was Forge Couple magic after a full day of internal screaming xD - just another happy day of ai wrangling~<3
And thank you for the advice and enduring my mini rant xD

Creative Corner » I've Been away for about a year... » Post 6

@VenisonCreamPie
I don’t know in what way regional prompter doesn’t work on your ForgeUI but if the problem is that it doesn’t show itself while you do have it installed, then just updating ForgeUI helped in my case.
A more user friendly alternative is Forge Coupler. You can also install that instead :)

Creative Corner » I've Been away for about a year... » Post 5

tyto4tme4l

Something of an artist
@VenisonCreamPie
I did see your reply, but I didn’t have anything to add.
There is no official upload limit as far as I know, just mind the Rule 9 (“Be mindful of image quality”, “Do not spam the site with large numbers of variations of the same image / prompt; space such generations out.”).

Creative Corner » I've Been away for about a year... » Post 4

VenisonCreamPie

EquineCreamPie~<3
Oh… I realized that If you didn’t subscribe you might not have seen my reply xD
@Star Streaker
Thank you! Fun to be back!!!

Btw… is there actually an official upload limit or is it just… be respectful, don’t spam, don’t slack on quality?

Creative Corner » I've Been away for about a year... » Post 3

Creative Corner » I've Been away for about a year... » Post 2

VenisonCreamPie

EquineCreamPie~<3
Oh my fluffy goodness… I haven’t used YiffyMix (thru Noobai now I guess) since before I hopped onto the Pony Diffusion boat to experiment SDXL Models… I immediately see the appeal! >w< I actually really loved Yiffymix early on… to see that it has grown so strong is incredible… i’ma have to tinker more to see if it’s worth shifting my loyalty from the Nova Illustrious Models…>w> and I’ll have to look up Your ZoinksNoob later…
I really tend to use Google’s Nano Banana for inspiration and some prompt writing.. sometimes i’ll have it pre generate me a sfw image to bring into img2img… I do wish some of these commercial platforms like Dall E and Nano Banana to loosen up a bit and let us enjoy the nsfw lol
But seriously thanks for the call out on the model and the welcome back! I would have been slow to notice it otherwise! I will see what I can add to the community… at least for today.. I am trying to work on one of my greatest weakness… wholesome innocent safe for work art… gulps

Creative Corner » I've Been away for about a year... » Post 1

tyto4tme4l

Something of an artist
Hi, welcome back. I don’t think a lot has changed. I think most people are using Noob-based models now (I’m using ZoinksNoob). Don’t bother with PonyV7, it’s been dead on arrival. Google’s Nano Banana Pro and Nano Banana 2 give a ton of possibilities, but trying to use them for free can be problematic.
Personally, I would love to see something unique and creative. Forge UI does support Regional Prompter, not sure why you seemingly can’t run it. You might try using Neo Forge or ReForge instead of the original.

Creative Corner » I've Been away for about a year... » Topic Opener

VenisonCreamPie

EquineCreamPie~<3
What have I missed? :D I have been playing around with Nova MLP XL V2 but I haven’t been able to touch any other Models outside the Nova Illustrious Family Lately… Been giving Pony Diffusion Models a break and can’t seem to get Pony V7 to work with the service I use…
Also I’m just generally curious what people wanna see! I know most of the people here can and will likely just create what they want with the power of the almighty AI lol but I would still love to cater to the community however I can! Though I am still pretty limited to mostly couple shippings and pinups since Forge UI can’t run Regional Prompter and that breaks my fluffy heart!~<3 Anyway… i’m back weather you know or cared about my existence before or not! Nyahahahah! >:D

Creative Corner » Diary of a prompter » Post 9

Creative Corner » [Tutorial] Replicating a generation from Stable Diffusion WebUI metadata » Post 3

Creative Corner » [Tutorial] Replicating a generation from Stable Diffusion WebUI metadata » Post 2

I use Fooocus, but it doesn’t produce as “clean” a result as Stable Diffusion, but Stable Diffusion is very difficult to understand

Creative Corner » [Tutorial] Replicating a generation from Stable Diffusion WebUI metadata » Post 1

Creative Corner » [Tutorial] Replicating a generation from Stable Diffusion WebUI metadata » Topic Opener

derp621

boop
I got a comment on one of my images recently asking what AI I use, which I assume to mean what model. I figure this is as good as a time as any to explain how you can regenerate most of the images I post here from what’s in the description.
Let’s use >>59493 as an example:
simple background, evil, (looking at you), smirk, unicorn, hat, outfit, flawless, sparklemoonilll <lora:Flawless_Sparklemoon_tamers12345:1>, countershading, high quality, detailed, solo, portrait, close up
Negative prompt: lips
Steps: 20, Sampler: Euler a, Schedule type: Automatic, CFG scale: 4, Seed: 4016617097, Size: 1080x1080, Model hash: 9d73bac23a, Clip skip: 2, ADetailer model: face_yolov8n.pt, ADetailer confidence: 0.3, ADetailer dilate erode: 4, ADetailer mask blur: 4, ADetailer denoising strength: 0.4, ADetailer inpaint only masked: True, ADetailer inpaint padding: 32, ADetailer version: 25.3.0, Lora hashes: "Flawless_Sparklemoon_tamers12345: 1032bc97f5da", Downcast alphas_cumprod: True, Version: v1.10.1
This is the same output Stable Diffusion WebUI can be configured to output in a txt file. The first two lines are positive and negative prompts and should be self explanatory. Below that is everything you need to know to regenerate the image.
When using Stable Diffusion WebUI yourself, you can paste the entire output above into the prompt field verbatim then press the ↙️ button to automatically setup almost everything. If there’s a setting WebUI doesn’t know how to setup it will appear in “Override Settings” section.
The only thing the ↙️ button can’t setup for you is the loaded checkpoint which you might not even have yet, so take note of the model and Lora hashes, in this case:
Model hash: 9d73bac23a,
Lora hashes: "Flawless_Sparklemoon_tamers12345: 1032bc97f5da",
Hashes are much better than model names or links for finding specific models. While links and tags can be convenient in the short term they are also subject to changes and errors over time. Hashes on the other hand are a mathematical guarantee that you have the identical model that was used in the original generation.
Since a lot of models used here come from CivitAI that would be a good place to start searching. CivitAI allows you to search for models by their hashes. Simply query the hash itself like this or this.
If you can’t find them on CivitAI you could try other sites like Hugging Face or even a generic web search for the hash. If you can’t find it anywhere it means one of the following:
  1. The model was private and never uploaded to the Internet
  2. The model once existed but has been nuked from the Internet
  3. The model was corrupted or modified by the generator in some way but was still able to generate an image
One last thing to know is even if you have everything to perfectly replicate the image, anomalies between AI stacks (Pytorch version, CUDA vs ROCm etc…) might still lead to different results but they should still be similar enough to be recognisable to one another and obviously, manual editing or inpainting that happens after the image was generated can’t be replicated. For example >>59493 has been uploaded with a transparent background.

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