Join me on my Patreon for exclusive perks and early access to unique resources.
To discuss custom LoRa's or models, feel free to connect on Discord.👍 Like this model to keep me motivated and inspired to create more!
💬 Drop a comment and let me know what you'd love to see next.
🌟 Review this model to help me improve and make even better creations.
🔔 Hit that notification bell to stay updated with my latest models and updates!
Important Usage Tips
Add Stable_Yogis_PDXL_Positives at the beginning of your prompt section.
Add Stable_Yogis_PDXL_Negatives-neg at the beginning of your negative prompt section.
Why?
The difference is enormous—check the image below for same-seed comparison with and without these Embeddings. Link to comparison images https://civarchive.com/images/41648855
For Best Results use My Negative Embedding with Detail sliders and Checkpoints
Description
Super_Eye_Detailer SDXL+PONY
Trained on 2407 images, this LoRA works seamlessly with SDXL and PONY, delivering stunning results for realistic and anime-style images. Pair it with Adetailer to unlock eye perfection like never before.
Bonus: It also enhances skin texture, making close-ups and portraits look flawless.
Tags:
detailed eyes,
perfect eyes,
photorealistic eyes,
perfect skin texture,
freckles,
This is just the beginning—I’d love your feedback to make it even better. Drop your thoughts below! 😊
XYZ Plots Here https://civitai.com/posts/9255048
Join me on my Patreon for exclusive perks and early access to unique resources.
To discuss custom Lora's or models, feel free to connect on Discord.
FAQ
Comments (17)
this is generally great — when it works. unfortunately it frequently generates random noise, here's one example.
it seems to work well with some realism-oriented models, but not others (perhaps most). while i haven't been keeping track of which, it generally seems to work well with "cyberrealistic pony" and "real dream", and i have found it to always work with "babes by stable yogi". but even with "realism by stable yogi", i frequently get random blue noise (in the example above, it's red). i unfortunately deleted those though, so i can't show you an example.
however, i can say that it isn't a problem with img2img: nearly (if not) every post i've made using this LoRA and the "realism" model were img2img; otherwise, text-to-image with it is so often unusable as to make me avoid it 😕.
as i said above though, it is great when it works, and your assets are typically fantastic.
edit: that image was taken down for somehow violating civit's TOS(?!), so here it is rehosted on imgur: https://i.imgur.com/NLVmoLQ.jpeg
Do I need to add both the <lora name> AND keywords, or is it enough with the lora name? I never seem to learn this. And does the negative lora also require certain keywords to be activated? (using Comfy)
If you see that keywords are specified on model page then Lora + keyword is the way to go.
if no keywords are specified that means you don't have to worry about keywords. Quite simple it is.
same goes for negative lora as well.
As of Feb. 12th, the CIVITAI generator is not allowing this LoRA to be used with Pony models. Does anyone know why?
Okay - it looks like CIVITAI is now limiting LoRAs that are specifically tagged as SDXL to only work with SDXL models. I checked the Sinfully Stylish LoRA - you used to be able to use both the SDXL and Pony versions with Pony base checkpoints. But not anymore it seems. That sucks.
I'm new to comfyui, which folder do I put this in?Is it a lora? Is it a custom node?
This is a Lora, add in Models\lora
Stable_Yogi ... The best LORAs ..gonna start using your checkpoints soon ...gotta say.. keep up the amazing work ...
Thanks for the love and feedback, much appreciated ! 🙏
Super_Detailer_SDXL_PONY is still one of my favorite detailers. I hope it will continue to evolve.
ah , now i have to work on it 😊
Can the XL and/or Pony versions work with Illustrious, or will that need a new lora?
They should work, but some models may not give better results. Try it.
Is it "super eye detailer", though? I can't find a single sharp portrait - from a photographer's point of view.
In comparison to not using it. Yes. I particularly do use super eye detailer a lot (one of my base Loras I use often) and have tested and I believe it does add quality. it might not make a photographers view eye like you say but if you keep the seed same, and turn it off, then on, then raise it. you will see the eye detail enhanced without a doubt. Thus, I do believe it completes its intended purpose.
This does improve eyes noticeably; can you maybe do one for hands/fingers in the future?
sure will try
Details
Files
Super_Eye_Detailer_By_Stable_Yogi_SDPD0.safetensors
Mirrors
Super_Eye_Detailer_By_Stable_Yogi_SDPD0.safetensors
Super_Eye_Detailer_By_Stable_Yogi_SDPD0.safetensors
Super_Eye_Detailer_By_Stable_Yogi_SDPD0.safetensors
Super_Eye_Detailer_By_Stable_Yogi_SDPD0.safetensors
Super_Eye_Detailer_By_Stable_Yogi_SDPD0.safetensors
Super_Eye_Detailer_By_Stable_Yogi_SDPD0.safetensors
Super_Eye_Detailer_By_Stable_Yogi_SDPD0.safetensors
Super_Eye_Detailer_By_Stable_Yogi_SDPD0.safetensors
Super_Eye_Detailer_By_Stable_Yogi_SDPD0.safetensors
Super_Eye_Detailer_By_Stable_Yogi_SDPD0.safetensors
Super_Eye_Detailer_By_Stable_Yogi_SDPD0 (1).safetensors
Super_Eye_Detailer_By_Stable_Yogi_SDPD0 (1).safetensors
Super_Eye_Detailer_By_Stable_Yogi_SDPD0.safetensors
BODY-Super_Eye_Detailer_By_Stable_Yogi.safetensors
Super_Eye_Detailer_By_Stable_Yogi_SDPD0.safetensors
Super_Eye_Detailer_By_Stable_Yogi_SDPD0.safetensors
Available On (3 platforms)
Same model published on other platforms. May have additional downloads or version variants.