Welcome!
Thanks for checking out my latest project! I spent a lot of time over the last week or two testing out possible updates for one of my other models. I ended up getting sidetracked, and "accidentally" created something that I thought turned out really well. As they say, beauty is in the eye of the beholder. If you try it out, please feel free to post your results and let me know what you think!
If you haven't used my merges before, my focus has been creating models that I really like the style of "out of the box", without needing to tweak the visuals with tons of LoRA or TIs. This model puts out some really nice looking 3d/realistic-ish images. It also carries a lot of the understanding of characters, creatures, etc baked into Pony.
All sample images were generated with no LoRA or TI. I use Adetailer and Hires.fix on all of my gallery images. Faces still generally look OK without Adetailer, but I recommend using it if possible.
If you are new to Pony, here are some tips:
Scoring - Use score_9, score_8_up, score_7_up, score_6_up, score_5_up in your positive prompt instead of SD1.5/SDXL quality tags. I have personally found that my images have much lower chance of frying if I keep the tokens below 200 (I usually shoot for under 150 when possible).
My base negative prompt looks like this:
score_1, score_2, score_3, score_4, score_5, score_6, watermark, text, signature, logo, monochrome, muscular, censored, ugly
Or use Zovya's Tis that do this for you with fewer keystrokes:
https://civarchive.com/models/332646/pony-pdxl-negative-embeddings
You can also use some of the baked in sources and content ratings to control the kind of output you get:
Sources - 'source_pony', 'source_furry', 'source_cartoon' and 'source_anime'
Ratings - 'rating_safe', 'rating_questionable' and 'rating_explicit'
My Usual Settings / Other Tested Options:
Sampler -DPM++ 2M SDE Karras / Restart / Euler A
Steps - 30--50 (30 for fast gens to test ideas, 50 for things I may save/post)
Resolution -896x1152, 832x1216 (or flip for landscape)
Hires.fix:
Upscaler - Ultramix_balanced, 4x_Ultrasharp
Steps - 15 or 20
Denoise -.3-.4
Upscale by - 1.5 - 2.0
Lastly, I'd like to thank the following amazing creators for their work on some of the components I used in this merge - Anzhc, insertusername, DucHaiten, and CitronLegacy!
Description
I had a few requests for a little more realistic mix, so I decided to put this together for everyone to play with. This model uses the original Serendipity model as the main base, with some Everyclear PNY by Zovya, Mklan Realistic, and 11 herbs and spices for some added goodness. I hope you enjoy the images it can create. I'm using mostly the same settings in A1111 for the gallery as I usually use. Keep in mind that with more realism, some Pony flexibility and creativity goes away. A little bit of tradeoff.
FAQ
Comments (6)
Was literally thinking just last night.. I hope Ghostbear updates Serendipity :-).. Simply the best behaving model. Every picture is a keeper.
I hope you enjoy this version as much as the original!
Now that hires and face fix are finally available with the Civitai generator, I would really love to see this model become available for onsite use. Hopefully in a future version once you have permissions from the merged models worked out.
Got some constructive criticism for you, sort of - overall this is great and produces stunning images, but there does seem to be a bit of a viewer fixation for characters.
Even when given the negative prompt "looking at viewer" they continue to do so, or glance slightly to the side of straight on instead. This is very apparent with prompts used in other models and then tried in this one, where the character will both look and face the viewer far more than in other models I've tried and resist negative prompts.
That's it, otherwise terrific thing you've put together here
I appreciate the feedback! I'll do some research and see if this is something I can fix for the next update.
@GhostBear1111 small follow-up -> I gave your Siren PDXL a try and didn't experience the same thing. Some element of what differentiates your two models places a lot of emphasis on pin-up/POV in this model. Obviously not necessarily a bad thing, not all models needs to be super flexible especially when they excel at what they're inclined towards producing
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.



















