Character LoRAs - Want more character variety? Then check This List!
đź‘» Ghost Signatures! Want to know how to easily remove them? - Check Here!
Description

Image imported from Derpibooru.
Original: https://derpibooru.org/images/2951714
Metadata at the time of import:
Field Data
Favorites 151
Upvotes 221
Downvotes 17
Score 204
Comments 9
Uploader Diego96
Original description below this line

I LOVE MY WIFE I LOVE MY WIFE I LOVE MY WIFE
dunno how to fix hands though :C
Original:
Taken from Astralite Heart’s Discord server.

questionable3841 ai generated48284 automatically imported33021 derpibooru import33212 edit590 editor:diego9662 generator:purplesmart.ai5008 generator:stable diffusion23137 prompter:diego96188 lyra heartstrings350 unicorn11473 anthro18418 g442421 bad anatomy539 generation errors2081 adorasexy1001 belly2884 belly button6850 braces5 breasts21461 busty lyra heartstrings88 cheerleader143 cheerleader outfit109 cleavage2380 clothes18611 crowd100 cute5064 eyelashes685 female46718 horn19142 looking at you20071 mare15063 microskirt39 missing cutie mark314 pom pom50 ponytail797 sexy6586 skirt1924 slightly chubby25 smiling17610 smiling at you5310 solo36914 solo female20751 solo focus2960 stadium72 thighs1905 underass160 waifu27 wide hips2091 wrong eye color325

Comments

Syntax quick reference: **bold** *italic* ||hide text|| `code` __underline__ ~~strike~~ ^sup^ ~sub~

Detailed syntax guide

Background Pony #8255
@Background Pony #8255
Machine learning is used to train an AI on what are basically image tags.
It is provided an image, and all the tags relevant to the image are provided. This step is, at some point, human. Recently though, they’ve found out how to get the broad strokes of an images tags from it with a different machine learning model and then train that backwards into the image-generating machine learning model. It’s whacky. Basically though it is amalgamating tags to shape cues, color cues, and style guides. If it isn’t trained on a concept you provide it, it will “do its best” but its unlikely to be able to reproduce it. This is particularly the case for interactions between two characters in the same image. It also frequently has trouble with perspective, since turning tags into cues that get put into the final limitation cannot, broadly, generate a unique perspective. But it’s much more complicated than this. The important part is, rather than amalgamating images themselves, it’s amalgamating “learned concepts” of tags which come from people-made images. Usually.

Imported from Derpibooru - Posted by donut64s
Background Pony #8255
Really attempting to gather what this machines generated stuff are.
I don’t understand what i’m watching and how it’s made.

Imported from Derpibooru - Posted by Supermark