✨ Latest | 🌐 Main | ⚡️ Ligthning/Hyper | 🌀 Alt version | 🖌 Inpaint | 📦 Old
🔸All Versions include VAE
✨REFERRAL CODE: DMD9XGMN
📩 Vote which version do you prefer on the generator
✨v2.3 ULTRA is a distinct variant of the standard v2.3.
While it technically improves overall output, my intention is to treat this version as experimental, exploring potential directions for future updates.
This release brings more natural and balanced lighting (also darkness), enhanced skin detail and an increased realism.
If you're using this model for Furry or Fur-based prompts, make sure to use the "Furry" trigger, or pair it with my Fur Enhancer LoRA for best results.
v2.3: (Latest) ✨
v2.2:
I have written an article that explains and provides some useful resources to help you achieve great generation results. You can check it out for detailed insights and recommendations.
🔁 Samplers
DPM++ 2M SDE Karras
DPM++ 2S a Karras
DPM++ SDE Karras
DPM++ 2M SDE Exponential
DPM2 a
DPM++ 2S a
DPM++ 3M *
Euler A
⚙️ Generation Settings
Steps: 30 or more
CFG Scale: 6–7
Clip Skip: 2
Resolution: Greater than 1024px
🗒️ Notes
Use Danbooru tags
Keep individual prompt weights ≤ 1.5
Use "female/male" instead of "woman/man" for better tagging compatibility
🖋️ Prompt Style
Positive Prompt Tags:
score_9,score_8_up,score_7_up,BREAKNegative Prompt Tags:
score_4,score_5,score_6
⚠️ Avoid DPM++ 2M Karras (Not recommended for generation)
✅ Recommended Samplers
Euler A
DPM2 A (Best for detail)
Read the following article for tips and my training preset
⚡️ Buzz for the Best Images ⚡️
Description
FAQ
Comments (27)
Initial testing in A111 - image outputs seem washed out/low contrast. Is there a specific VAE we should us? I just use "Auto" for VAE in settings.
Yes, the vae is listed in the model details
The vae is listed on the alpha but does not appear on v1
Ooohhh... I see. Looks like Civit changed the UI a bit. Thanks!
Any chance you could do a lightning version of this?
it is likely, but I can't promise anything
looks nice! please create a baked vae version if you can. some gui like fooocus don't let us change the vae, so it makes models like yours unusable there.
Sure, uploading it very soon
@ZyloO wow thank you so much!
i hope that lgbt people get included in future iterations like in other pony models! (currently, it seems like it wasn't trained to handle this from my testing, so that functionality has been largely lost, similar to other SDXL models)
dude…go here to get your peckers
https://civitai.com/models/343190/grle-mix-xl-6040-or-confetti-vs-pony-xl
Pony based
@Omikonz love ya!
may i know what is the version diff from v1 and alpha? which one is more updated version?
V1
Despite using adetailer and your recommended settings/prompts for the quality tags it feels rather difficult to get good looking faces- especially with smiles that show teeth, which I noticed your preview images don't have any examples of, nor do really any of the reviews/submissions, is this a known issue or am I doing something wrong?
I've tried different inpainting strengths on adetalier but it doesn't seem to help, the teeth still come out messed up every time and eyes even often get messed up.
Anyones input is welcome!
Yeah, smiles in pony are pretty bad, I will try to fix it for the next version
@ZyloO Thank you, it's both a relief and a disappointment to hear it's not something I was doing wrong, haha. Looking forward to your future releases! This model has a ton of potential for sure. Keep up the good work!
i keep getting this weird "haze" filter over every image, i have all the required prompts, VAE, adetailer, have messed with negative prompts too, anyone know what is the cause?
Instruction for Stable diffusion
Go in settings
Type "Quicksettings list" in the search bar
in the Quicksettings list, type "sd_vae"
Apply settings
Reload UI
You now have "SD VAE" next to "Stable Diffusion checkpoint" at the upper right corner.
Click on it and make sure "sdxl_vae.safetensors" is selected.
If the image is still grayish with spots
reclick on "SD VAE", select "None", then reselect "sdxl_vae.safetensors"
It should work now if you installed properly the sdxl_vae.safetensors and followed exactly the instruction I've gave you.
God speed.
@kevindesbiens727 thank you , my dumbass just forgot to hit apply settings
@kevindesbiens727 TY for that explanation. My SD VAE pull down only shows "none" and "automatic". Did I do something wrong?
@Gilmere be sure to download the VEA and put it in the VEA folder
@sickness4thickness Yep, that was it. The VAE was in the wrong folder. TY for the help!
@Gilmere , @sickness4thickness - It's recommended to use the Checkpoints tab, click the Tool icon for this model (edit model metadata), and choose the "preferred VAE". That way, if the VAE setting is "Automatic" it will automatically apply the preferred VAE
Great model, when you get it working!
Is there a lightning model coming out? I can't even seem to use an LCM lora with it
At the moment, I'm striving to achieve a good balance between realism and variety in facial features before proceeding to create various versions. I am currently satisfied with the latest update in terms of realism and quality. Next, I will focus on restoring the variety in facial features. Once this step is completed, I will begin creating different versions of the model
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.