In this photorealistic XL-Pony-Illustrious hybrid model I tried to adopt multiple features, styles and concepts from other resources I used internally. It was trained on a big dataset of carefully selected SFW and NSFW images of different themes. Due to multistage training and additional tuning some PONY and ILL concepts might be washed out. Let me know if something is missing - I will try to bring them back.
v0.7a 1216px
Recommendations:
Don't put style / quality tags to the beginning of the prompt. If you put "beautiful face" at the start of the prompt you probably will get an extreme close-up of the "beautiful face" ;)
Text-to-Image (drafts) - use Euler A or DDPM, CFG 2.0 .. 3.0, 16..24 steps at 832x1216 px.
Image-to-Image (HiRes Fix) - DPM++ 2S a, Karras, CFG 1.0 .. 1.5, 12..16 steps, Denoise 0.45..0.67 at 2.5..3.5 MPx resolution.
More steps - more contrast / sharpness.
I2I at 4 Mpx resolution - set lower denoise because at high resolution elements duplication may occur.
Pony tags may work, but this version trained with more natural SDXL captions.
Tags like "anime style", "painting", "brush strokes", "digital art" may give a drawing style instead of realism. This version can render arts / anime if you ask so.
v0.5 1280px
Recommendations:
ComfyUI user can drop my samples into Comfy window. My complex workflow contains Qwen 3VL based best image selector - you can remove this option. Main feature of the Comfy workflow is the multi-stage rendering.
Text-to-Image stage usually gives the draft with good composition but bad details (so I recommend Euler A sampler for T2I). One or two Image-to-Image stages is crucial to polish the draft. It will give smooth background, more realistic textures and better detailing. Good results in I2I can be achieved in 2.0..2.5 MPx resolutions. You can also try 4 Mpx resolution.
For the CivitAI generator users I can recommend use the T2I with Euler A for drafts, then apply HiRes Fix with more contrast samplers (DMP++ *).
My apologies, I didn't manage to make it possible to get good results using the single stage render. All my attempts to train single T2I ckpt resulted in different critical flaws.
This version is trained with addition of DMD2 so it have reduced the number of steps required. I see some good drafts rendered with Euler A at 16 steps (or maybe 12) posted by other users, but I recommend 20.
v0.5 1280px
Recommendation for CivitAI Image Generator: start with Euler or Euler A (DPM++ samplers are too contrast for the first run); then use HiRes Fix mode and DPM++ 2M Karras sampler (if you get too contrast image, then try Euler A for HiRes Fix); see my samples made with CivitAI Gen.
This version is trained in high resolution and uses big number of steps. For speed, apply DMD2 4steps CFG 1.0 of DMD2 8steps CFG 1.5 LORA.
You can render from scratch at resolution of 1440px by longest side and then use ADetailer or HighRes Fix at resolutions of up to 4 MPx.
Use Euler A for Text-ti-Image render - this will produce smooth textures.
Use other contrast samplers with higher CFG to refine the textures.
Ultimate SD Upscale in ComfyUI with tile size of 1216 is a recommended way to produce the high quality images.
If you want to render images with only the Text-to-Image aproach then please give this version more steps. Also, you can post undercooked images if you need my assistance. I will try to help you with better render parameters.
FEEDBACK appreciated!
PS: eyes may be unstable for characters at the distance; I'm working on fixing it asap.
v0.3 params for CivitAI generator
https://civarchive.com/posts/27865267
I hope you will engoy using this. And I hope you will convert your pleasure into BUZZ donation ;) because I need more fuel to continue my work on training dataset improvements.
🥰 THANKS for attention, posts and comments! 🥰
Description
v0.2-DMD-8step trained with new photorealistic dataset (more interactions between multiple characters, sharper and more detailed closeups, anatomical improvements, better eyes and fingers, more texture). Use Comfy workflow from my samples as a start for your experiments.
FAQ
Comments (8)
beautiful new model.
This is really good, though unfortunately it falls victim to pretty much every pony model when it's trained form what I've seen. Cunnilingus isn't really in it anymore. Like, you can kinda sort do it, but often times the ai gives like fellatio, or just intercourse or nothing really at all as it seems confused. From my initial findings on the very first pony model, for whatever reason, when I put "pony" in the negatives it also affected it's ability to generate cunnilingus... A very odd thing indeed.
Cunny things are fixable I suppose. Thanks for letting me know!
@iwantobeleaf Of course! Glad I could help if I did
i like the dmd version but the plain version, this latest one, I can't get to work. I have a few that look nice, and the rest that looks over baked. I tried dp++ and euler a and the results seem random
something is wrong with v0.3, but cant get an idea what exactly. Works well in comfy on my side, but Lizard and you report the issue. I'm in debug...
I get great detailing with this model and realistic musculature and proportions. Nice work. Thanks for releasing it to create on here.
what tooling you are using?
I tried the CivitAI's generator. Single pass gives smooth image. Second HiRes fix gives grainy textures but not so high quality. ComfyUI workflow with HiRes fix and CLIP Text encoder nodes gives noticeably different quality. Can't understand why.