sexual situations

physical violence

disturbing

male nudity

extremist

hanging

hate symbols

nazi party

revealing clothes

weapon violence

female swimwear or underwear

male swimwear or underwear

partial nudity

white supremacy

adult toys

graphic male nudity

illustrated explicit nudity

nudity

self injury

graphic violence or gore

graphic female nudity

corpses

wide hips

convenient censoring

peeing

oral invitation

emaciated bodies

exposed female nipple

blowjob

female nudity

sexual activity

sexual intent

undressed

male underwear

female swimwear

genitals

female underwear

thick thighs

breasts out

strapless leotard

vore

bestiality

breast out

one breast out

huge breasts

gigantic breasts

huge butt

covered nipples

hair over breasts

no panties

sitting on face

anal

dildo riding

downblouse

oral

porn

futanari

hentai

nude

lingerie

sexy

nsfw

suggestive

bukkake

cumshot

cumdrip

cum in pussy

cum on face

cum on hair

cum on body

cum on tongue

cum on hands

cum in mouth

cum on pussy

eat_cum

fellatio

implied fellatio

after fellatio

triple fellatio

autofellatio

pov fellatio

fucked silly

presenting ass

presenting pussy

spreading legs

spread legs

swimwear

Update: 2024-12-01 - Hybrid Model - I know I mentioned that the other version was the final, but there was one other project I was messing around with a few months ago that I find I've been using more than the others. The better models I mentioned when retiring this project was the Indigo Furry Mix project. My one complaint with it was that it was was very 'same-y' IE: Every sheath looked the same, every expression was similar, etc. In an attempt to fix that created a hybrid model between one of the indigo furry mixes (I believe 105) and the multiple character model posted here (Roughly 40% indigo, 60% multiple character, and then trained for a few epoch on a small subset of images from the solo version, as well as a small subset of masculine females to better work with femboys). I think this results in the best choice of the models on this project if you just want a general purpose 'create gay furry stuff' model out of the box. However there are still models that do everything this does better out there. I do know many of you still use this project though and I'd feel bad if I was withholding something from y'all for the sake of assuming nobody wants it. Recommend generating images between 640x640 and 768x768, still using e621 tags. This model is slightly prone to burnout however, so be careful. Given the 40% weighting of the indigo furry mix project, some of the resources they provide are relevant to this version. A Great resource for picking an artist style is provided by their project here <a target="_blank" rel="ugc" href="https://mega.nz/folder/FoQR1RgA#gDLJyJe9-JK2_FDaosgSzg/folder/osYgSBCb">https://mega.nz/folder/FoQR1RgA#gDLJyJe9-JK2_FDaosgSzg/folder/osYgSBCb</a> Check out the indigo furry mix project here as well <a target="_blank" rel="ugc" href="https://civitai.com/models/34469?modelVersionId=480978">https://civitai.com/models/34469?modelVersionId=480978</a> With the exception of what I mentioned above, it's (indigo) generally a better model and a little less prone to burnout. Being blended with indigo as well also greatly improves this models ability to break from super strict E621 tags (though it's still recommended) I currently am utilizing my hardware for other AI projects, so continued development on this is very unlikely, if it were to continue it would be experimenting with newer models and likely starting from scratch with a more current image dataset. Update: 2023-08-07 In my mind there are now other models that do what this one does better, so I've stopped development on it. The 'Solo' Version is the original model, which does solo males quite well. The 'Multiple Character' model was a separate project that I was working on, but am just not completely satisfied with the results so won't be continuing work on it. It can also do solo males quite well however. Thanks for enjoying the project for the last few months! While I'm not currently planning a sd 2.1 flavor, I may look into creating a similar model using future versions. As with the original model, prompting on the multiple character model uses e-621 tags and you should be very specific. I was testing using Euler A 32 832x448 cfg 10 The primary goal of the 'multiple characters' model was to accomplish two things: 1. Get reasonably acceptable base images without having to use additional addins or hi-res. 2. Make generating huffy sheaths (uwu) easier than in the solo model, which struggled a bit to get them correct.3. Make it understand that it's okay for PPs and Balls to touch without merging together --Original-- This is intended to be a semi specialized solo gay male pinup / character creator. If you are looking for a model strong at generating females, this is not it lol. It is able to create multiple character images, but that's not what it's ideal for. There is currently another project I'm working on which will be better suited for that. This models ideal range is femboy to twunk. See testing prompt for a good place to start. Early version, still lots of work to do, but does not re-use any previous furry or yiffy models, which always messed up the pps (uwu). Trained various combinations of around 120,000 male gay focused furry images, for use with stable diffusion web UI. Tagging uses comma separated e-621 options without any underscores. Exception to tags: YMMV, but underscores are still needed when specifying a specific character tags and MetaTags. Meta tags are preserved as well, and continue to use underscores. IE: Vincent_(FoxMcC) on e621 would be represented as Vincent_\(FoxMcC\) in this model. IE: hi_res and digital_media_(artwork) on e621 would be hi_res, digital_media_\(artwork\) Artist tags will usually work okay with just the name, but you'll have the best luck prefixing them with 'by' IE: by chunie, by richard foley, etc. Be VERY SPECIFIC with what you want in an image with this, down to specifying eye color. See sample prompt. It is intended to be more of a character or pinup generator, but it's able to do well with multiple characters as well with careful sculpting. Some kinks are not represented in the model, images which were tagged with the following are not included in the image training dataset -animated -humanonly -hyper -watersports -scat -cub -comic -diaper -pixel(artwork) -3d_(artwork) -vore -chibi This isn't because I have anything against those kinks, rather I'm trying to create a slight built-in bias or remove unexpected elements from the images it generates. The criteria to be included in the training was a favcount greater than 200 and a score over 100, which also contain the tags 'anthro' and 'male' Note: Specifying the number of fingers you want helps immensely, and put your most important criteria at the front of the prompt, and nice to haves near the back. Testing configuration /prompts Euler A - 28 (Heun 30 usually is an interesting vatiation) CFG 8 (works well between 6 and 9 depending on the prompt) Seed - 855213688 (you can set it to whatever but this is what I test with) Optional Hires testing configuration Upscaler - Latent (nearest) Denoising strength 0.6 Upscale 2 Positive Prompt: wolf, wolfdog, striped hyena, anthro, male, detailed, (detailed fur), (athletic), athletic anthro, muscular, muscular anthro, muscular male, fluffy, fluffy fur, fluffy ears, fluffy hair, fluffy chest, mane, pinup, canine ears, canine penis, canine anatomy, chest tuft, (balls), big balls, nude, nude male, solo, (fully sheathed), (penis tip), thigh up, (yellow eyes), ((sheath)), (white sheath), (black sheath), (brown sheath), tan sheath, gray sheath, retracted sheath, smug, grin, horny, lustful gaze, [orange fur], [red fur], [white fur], [blue fur], [yellow fur], two tone fur, two tone body, two tone hair, multi tone hair, sitting, posing, reclining, detailed background, five fingers, rating:explicit, digital_media_\(artwork\) Negative Prompt: deformed, blurry, multi limb, taur, multiple limbs, bad anatomy, disfigured, poorly drawn face, mutated, extra limb, ugly, woman, female, multiple characters, feral, deformed hands, face out of frame, multiple tails, over saturated, hdr, high dynamic range, sketch, comic, human penis, no pupils, simple background, multiple characters, cub, child, jock, underwear, clothing, chastity, cage, abstract, chastity cage Possible future testing versions can be found in Furry Diffusion discord or at <a target="_blank" rel="ugc" href="https://wolf.gay/">https://wolf.gay/</a> No commercial for profit use of any kind, or selling images made by this model, or any derivations of this model / images created by them.

I know I mentioned that the other version was the final, but there was one other project I was messing around with a few months ago that I find I've been using more than the others. The better models I mentioned when retiring this project was the Indigo Furry Mix project. My one complaint with it was that it was was very 'same-y' IE: Every sheath looked the same, every expression was similar. In an attempt to fix that created a hybrid model between one of the indigo furry mixes (I believe 105) and the multiple character model posted here (Roughly 40% indigo, 60% multiple character, and then trained for a few epoch on a small subset of images from the solo version, as well as a small subset of masculine females to better work with femboys). I think this results in the best choice of the models on this project if you just want a general purpose 'create gay furry stuff' model out of the box. However there are still models that do everything this does better out there. I do know many of you still use this project though and I'd feel bad if I was withholding something from y'all for the sake of assuming nobody wants it. Recommend generating images between 640x640 and 768x768. Given the 40% weighting of the indigo furry mix project, some of the resources they provide are relevant to this version. A Great resource for picking an artist style is provided by their project here <a target="_blank" rel="ugc" href="https://mega.nz/folder/FoQR1RgA#gDLJyJe9-JK2_FDaosgSzg/folder/osYgSBCb">https://mega.nz/folder/FoQR1RgA#gDLJyJe9-JK2_FDaosgSzg/folder/osYgSBCb</a> Check out the indigo furry mix project here as well <a target="_blank" rel="ugc" href="https://civitai.com/models/34469?modelVersionId=480978">https://civitai.com/models/34469?modelVersionId=480978</a> With the exception of what I mentioned above, it's generally a better model and a little less prone to burnout.

Hybrid Model

I did stop training this model a while ago because I wasn't satisfied with how it was turning out on the 2.1 model results and the high resolution results I've been training compared to what other models could accomplish, so it just didn't seem necessary to continue. It does look like I never posted any of the final 'duo' version results though, which is significantly better than the previous super early training builds some of you have, so just going to throw them up here since they are already made. Prompting is the same as above, 640x640 for the base resolution sd1.5, so ideal resolutions for said Multi character model are [[640, 640], [704, 576], [576, 704], [768, 512], [512, 768], [832, 448], [448, 832], [896, 448], [448, 896], [1024, 384], [384, 1024] (Though the further down that list you get, or the more extreme the resolution sizes, the worse luck you'll have)

Multiple Character

Solo Focus

Gay621 Male Focus