still no creation_service -> write a ticket to civitai pls :*
sry for spamming, new one is different and whoooo
THX ALL 15000 that downlaods all my REAL-Pony versions :)
-> here, seems my models not that bad (thx to Lord_Varos)
https://civarchive.com/articles/5942/lets-test-some-pony-checkpoints
for individual faces read my article "faceswap"
(all models are merges at least of 6 models, thx to jugger, leosam(still deleted), Pony Diffusion, GODDESS of Realism and some more)
newest not allways best for you (oc each has its weaknesses but try), most of my pics are without a lora and adetailer or hiresfix, most other models are blending with those stuff
-> choose yourself ... higher version more real but less pony_style (but hardcore)
Try my fully real NSFW-SDXL model
https://civarchive.com/models/270312/sevenof9photoartfantasy?modelVersionId=304720
to get back to cartoon/anime use:
https://civarchive.com/models/395523?modelVersionId=675712
with weight ~0.8 and (anime, cartoon, manhua in positiv | 3D, photo in negativ)
Versions: (suggestion, BEST, smart_evo, allyouwant and keephandsoff)
THEBEST - Base is my Allyouwant with merge a bit SDXL and Pony again, big changes are body-size (eg young girl in a kitchen vs woman), hands, faces ... a bit anime inside (force it) and all XXX stuff -> forget all other PONY-REAL models ;)
Smart_Evolution_contrast(last) - bit more contrast and more details, more sharp background, CFG 10 and right prompt is anime_style, try "instragram selfie" many other pony dont work with that ;) ->Schedule type SGM Uniform
Smart_Evolution - (CFG up to 10, Clip-2), more curvy, more naughty, handle complex prompts, resolution up to 1200pix, hardocre, for anime use NoctFlatStyle
nextgen - (low CFG, if high than steps up to 100, Clip-2), sharp, cozy, different than last, handle complex prompts, resolution up to 1400pix, hardcore back, no anime style
iTgoesON - (CFG 3-10, steps up to 60, Clip-2), sharp, contrast, call background, play with it, new base, bit less hardcore, resolution up to 1400pix
Allyouwant - (CFG 2-5, steps up to 60, Clip-2), bit brighter and more complex environment, not better in some cases. (Hardcore still insde), no_score! , most easy and lora compatible
for anime/cartoon: ad in positiv "manhua, anime" and in neg "realism, realistic, photo"
Keep_Hands_off - (CFG 2-5, steps up to 60), NO Pony-style "try loras", but all ALL is such as real like a Photo ... OMgush ^^ (Hardcore still insde), no_score!
for anime/cartoon: use https://civarchive.com/models/395523?modelVersionId=479629 and in negPrompt zPDXLrl style OR (without any lora)
ad in positiv "manhua, anime" and in neg "realism, realistic, photo"
Real_add - (CFG 3-7, steps up to 60), added more Pony-Sytle and realistic athmosphere (sorry for the fast updates, but i like the new), only change the words anime and photograph from pos to neg prompt to change style, sometimes better cartoon_style without score, sometime zPDXL work sometimes dont -> version final_face still the realest and more easy futa!
final_faces - (CFG 3-4, steps up to 60), added a face lora, now more than 10 different kind of cultures (african, japanese, brazillian ...), also a bit more neutral light, for close-up portraits you can leave any words to make it look like real, call background
final (still most complex prompts) - it follows prompts as much as you want, rise up steps until 60, CFG is good at 3-4, great complex and detailed, so no more anime - because most is gone, you can try to leave prompts that forces good photos, (you should call backgrounds if you want).
(also hardcore possible, score not absolutely necessary)
UPDATED(7/24) inpaint-model(for A1111) - push up CFG to 7 or more
only for following models:
so negativ and postiv prompt are important! but it is not 100%pony and not 100%realisitic!
Real:
Positive: source_realistic, photograph, (score_9, score_8_up, score_7_up, score_6_up)
Negative: sketch, drawing, cartoon, signature, greyscale, monochrome, anime,
Anime:
Positive: source_anime, (score_9, score_8_up, score_7_up, score_6_up)
Negative: photograph, realistic, 3d, render
i suggest an ebedding: zPDXLrl https://civarchive.com/models/332646?modelVersionId=372656 and you can leave that score stuff
at least 40 steps (CFG 3 to 7)
V88b - better background, more listen, more interesting, use my LORA-CFG-Slider to get more real images on very low CFG use it with (-0.4) https://civarchive.com/models/283589?modelVersionId=319151 ; maybe i merge it in next - "last" version ;)
V77j - mostly better hands and better small faces - background more consistent and interesting, only simple nipples -> try ((dark nipples, (puffy nipples:1.2) ,(big areolas:1.2)):0.8) (lactation:1) ; but sorry a bit blurry all in all, bit pony
V9 - bit more easy to provide NSFW, very sharp, less good small faces, also pony style
be aware that pony is a strong NSFW model!
(i only say: horse, futanari, gigantic, (size difference:1.4), (gigantic penis), egg, teats, knot penis, canine ...) you can also create good backgrounds and landscapes
So be private with hardcore stuff !!! i will delete all animal and cp !
Description
based on my last model
(CFG below 7)
added 1 real model and 2 pony_realmodels
OMG all run without ADetailer
may use zPDXLrl (embedding)
No Pony_Style but all hardcore inside
add "manhua, anime" in prompt for anime
use my facelora (pony_weak or strong) to push cultures
FAQ
Comments (25)
Fantastic model - thank you!
As someone who only stick with CFG 7 like all the time this is a bit of a new thing to get used to.
I love the looks of the new model though. Btw also loved some of the other models, esp the ADD one.
What I do not like much is that I seem to lose a lot of contol over the scene displayed with such low CFG value but maybe that's on me and I need to test more how to work with that.
Because it feels a bit like I got the nice visuals but the pony possibilities just in theory (or at least not at full strength) because it is difficult to create a nice scene for me with such low CFG.
Again: Might be on me. I am not used to it. Love the visuals and also some of your other shared works so thank you. <3
PS: I notice that characters of loras of male figures get a feminine touch. Something that unfortunately happens with lots of models I tried so far, but not all of them. Not sure what's with that. It was not as noticable with the ADD model of yours as well. It is a bit of a downside for me but I am probaly the minority here. Still a nice model.
thx for you impression...
low cfg is most times more real... but less control , yes
you can try my CFG lora (you can take tthe smaller)
https://civitai.com/models/283589/cfgslider
with CFG 12 , try weights arround 0.3 to 0.5
with CFG 4, try weights arround -0.3 to -0.5
last one i prefer ;)
this model is quickly becoming the best one! love the new release!
thx,
but i wonder why many bad models have such as much downloads and buzz ^^
High quality model,much better than I expected,thank you :)
After testing so many, this is the best for body generation. faces are not that great. but wow, the lighting, the textures, very very good job !
THX a lot ! (and may for porn generation too ^^)
faces, what do you try and oc real_real models are better (like my old but stable one)
https://civitai.com/models/270312/sevenof9photoartfantasy?modelVersionId=304720
I m having difficuly to generate different faces, is that normal, or do you need specific prompt for random faces?
yes thats a main challenges in pony/sdxl models...
you can try call cultures, in my model "final faces" you see some example images.
you can also try call celebrities and if to strong reduce it (Julia Roberts:0.5), for pony models more weight eg (Julia Roberts:1.5) .... or try to write (ugly) or with weighs (ugly:0.5) but in negprompt (old), because most models set ugly=(a bit old) ... try and play ;)
@sevenof9247 thanks!!
@Mumu1188 i have posted some images yesterday
This is the best one for me (keephandsoff) and I have tried a few pony real over the last days. Thanks so much for sharing. I am not sure if you can make it better but I surely will be here to download if you give it a try.
THX, iam only a lucky merger ... so we will see, special part maybe better with special loras ;)
I made a 50:50 merge with "Keep Your Hands Off" and "Real Pony Mix Add". Great consistent results!
every one has its own focus .. what is more consisten?
@sevenof9247 KYHO had too much grain and skin texture for my creations, but it seems to be more versatile in understanding prompts. I made a merge fromother models (70% Albedo 1.3 + 30% ICBINP XL6) that has the knowledge of realistic faces and it works great via inpaint. Now I can create consisten characters without an loras. Just using 2 checkpoints. Results are somewhere between 2.5d and photorealistic.
The last version is really good. One of the most realistic pony models and follows prompt really well too.
THX , so long yes - style is gone but real is real ^^
Nice checkpoint
thx, yes not only the top creators can make good things ;)
my real_real_one(v1) is also lucky merge and very creative
I'll try it, using final faces right now, its the first pony checkpoint I've used that actually looks good
Which one were you talking about, I don't see "real_real_one(v1)"
@getphat you can take a look here ... but the quality sais nothing about if all pony NSFW is inside ;)
https://civitai.com/articles/5942/lets-test-some-pony-checkpoints
@getphat
https://civitai.com/models/270312/sevenof9photoartfantasy
it follow prompts, good for text, but its also creative if you only write some adjectives... (leave neg empty until you see somewaht you dont want) ;)










