Run Locally
PerfectEyesXL.safetensors
218 MB · SafeTensor
Downloads are served by Civitai. Some creators ask for a Civitai login first.
About This Model
STABLE DIFFUSION XL 1.0 · LoRAs
Creator notes
Best at inpainting! Enhance your eyes with this new Lora for SDXL
It understands these type of prompts:
Picture of 1 eye: [color] eye, close up, perfecteyes
Picture of 2 eyes: [color] [optional:color2] eyes, perfecteyes
Extra tags: heterchromia (works 30% of time), extreme close up,
Colors supported natively: green, blue, brown, grey, hazel, yellow (sort of)
New in V3: (Not an upgrade but a different version with different prompting technique)
bloodshot eyes
grey eyes
Trigger words
green eyes
blue eyes
brown eyes
perfecteyes
SHA256
F248364CF0ACC7A00BC4B5145B44C0DFBF10E71E9B0EFB6B77F0956AEAF2411C
ModelTrends.ai Model ID
#2825
Flag content
Example renders
Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.
Settings
Sampler
Euler a
Steps
30
Guidance
4
Seed
860768588
Size
768x1152
Prompt
by Mark Keathley and Michael Garmash, <lora:EnvyImpressionismXL01:0.75> , awesomize <lora:EnvyAwesomizeXL01:1.00> <lora:more_art:0.35> <lora:RMSDXL_Enhance:0.50> <lora:RMSDXL_Creative:0.50> <lora:RMSDXL_Photo:0.50> <lora:RMSDXL_Darkness_Cinema:0.50> <lora:clothing_slider:1.50> <lora:great_lighting:1.50> <lora:aesthetic:1.50> <lora:looking_at_viewer:1.50> <lora:photorealistic_portrait_v2:0.25> <lora:attractive_v2:0.15> <lora:extremely_detailed_v2:0.25> <lora:add_detail:0.25> <lora:perfect_eyes:0.25> <lora:perfect_hands:0.50> <lora:midjourney:-0.15>
Negative prompt
Unspeakable-Horrors-Composition-SDXL, SDXL_TI_my_eyes_are_bleeding, unaestheticXL_Alb2, poorly drawn, gloomy, messy, low quality, blurry, doll, deviant, animal ears, topless, breasts, nipples, strange clothing, multicolored hair
Settings
Sampler
DPM++ 2M Karras
Steps
24
Guidance
7
Seed
2160243031
Size
768x1152
Prompt
,by Adam Elsheimer and Evgeny Lushpin in the style of Catherine Hyde and Kelly Mckernan, movie still, film still, cinematic, cinematic shot, cinematic lighting <lora:juggernaut_cinematic:1.00> ,, (polaroid film photography:0.000), professional studio photo <lora:Polaroid_Film-000005:0.55> ,sorcerous, fancy, alchemical, reverie <lora:more_art:0.30> <lora:RMSDXL_Enhance:0.45> <lora:RMSDXL_Creative:0.45> <lora:RMSDXL_Photo:0.45> <lora:RMSDXL_Darkness_Cinema:0.45> <lora:clothing_slider:0.00> <lora:great_lighting:1.00> <lora:aesthetic:1.00> <lora:looking_at_viewer:1.00> <lora:photorealistic_portrait_v2:0.25> <lora:attractive_v2:0.10> <lora:extremely_detailed_v2:0.25> <lora:add_detail:0.75> <lora:perfect_eyes:0.25> <lora:perfect_hands:0.50>
Negative prompt
Unspeakable-Horrors-Composition-SDXL, SDXL_TI_my_eyes_are_bleeding, unaestheticXL_Alb2, poorly drawn, gloomy, messy, low quality, blurry, doll, deviant, animal ears, topless, breasts, nipples, strange clothing
Settings
Sampler
DDIM
Steps
48
Guidance
6
Seed
89869746
Size
832x1216
Clip skip
2
Weight used
0.75
Prompt
Style, Aesthetic, Background by: "harles Douglas Richardson and Mr Than and John Berkey Midjourney v6".
Subject: "Tesseract".
Life-like details.
Refined lines and and shapes.
Refined details on objects.
Sharp details.
Wide range of colors.
Many details everywhere.
Realistic soft shadows.
Low saturation colors.
Insane quality.
Insane resolution.
Insane details.
Masterpiece.
32k resolution.
OverallDetail.
perfecteyes.
Negative prompt
deformed, glitch, noisy, signature, watermark. (worst quality, low quality:1.4),(easynegative, negative_hand-neg),(crown:1.5), horns, long ears, stars, fake ears, cat ears, donkey ears, tattoo, tattooes, inked, bad face.
Settings
Sampler
DPM++ 2M Karras
Steps
48
Guidance
6
Seed
445523865
Size
832x1216
Clip skip
2
Weight used
0.75
Prompt
Generate a captivating artwork showcasing abstract shapes composed of glass, diamonds, and gold, with a dispersion effect emanating from the glass. Emphasize intricate details, refined lines, and vibrant colors throughout the composition. Ensure that the focus remains on the abstract elements rather than human subjects.
Negative prompt
Exclude any depictions of human faces from the artwork. Ensure that the composition solely features abstract shapes, diamonds, and gold without any human-like features. Prevent the inclusion of facial features, expressions, or any semblance of human anatomy. Steer clear of any elements that may suggest the presence of human figures in the image.
Settings
Sampler
Euler a
Steps
33
Guidance
7
Seed
28694997
Size
832x1216
Clip skip
2
Weight used
1
Prompt
cattail \(plants vs zombies\), plants vs zombies,1girl, cat girl, furry female, cat ears, cat tail, white hair, long hair, pink headwear, long sleeves, white fur
,(cowboy shot: 1.6)
,flat colors, thick lines, anime style, simplistic artstyle, A professional, high-quality, hyper-realistic portrait of a woman. The image features ultra-detailed eyes, realistic skin texture, intricate facial features, and cinematic lighting. Shot in low light with a Nikon Z7 II and a NIKKOR Z 50mm f/1.8 lens, showcasing shallow depth of field (bokeh) and RAW photography quality. Masterpiece-level, sharp and photorealistic, fine art photography style.
artist: incase,
,masterpiece, best quality, very awa, newest,yameroyandere
Negative prompt
worst quality, low quality, bad quality, lowres, low res, pixelated, blurry, blurred, compression artifacts, jpeg artifacts, downscaled, bad anatomy, bad hands, deformed hands, deformed fingers, deformed feet, deformed toes, extra limbs, extra arms, extra legs, extra legs and arms, extra fingers, extra digits, extra digit, mutated hands, mutation, mutated, fused fingers, fused toes, missing limbs, missing arms, missing fingers, missing toes, malformed, disfigured, wrong hands, ugly hands, ugly fingers, twisted hands, flexible deformity, disembodied, text, watermark, signature, logo, url, username, tagme, bad, ugly, worst, unfinished, poorly drawn face, poorly drawn hands, poorly drawn feet, artistic error, bad proportions, bad twitter id, out of frame, cropped, missing, missing id, bad id, overly saturated, overly vivid, expressionless, monochrome, abstract, sequence, lineup, turnaround, 2koma, 4koma, microsoft paint \(medium\), , has bad revision, scan artifacts, image sample
Settings
Sampler
DPM++ 2M
Steps
40
Guidance
4
Seed
3178234177
Size
832x1216
Clip skip
2
Weight used
0.25
Prompt
(Ink illustration on parchment). A futuristic The city of yharnam, bloodborne, oil painting, done with japanese brush technique, realistic, extreme detail, scary, terrifying, dark and warm environment, 8k, masterfully stylized, by Jeff Easley and Terry Redlin <lora:more_art:0.30> <lora:RMSDXL_Enhance:0.45> <lora:RMSDXL_Creative:0.45> <lora:RMSDXL_Photo:0.45> <lora:RMSDXL_Darkness_Cinema:0.45> <lora:clothing_slider:0.00> <lora:great_lighting:1.00> <lora:aesthetic:1.00> <lora:looking_at_viewer:1.00> <lora:photorealistic_portrait_v2:0.25> <lora:attractive_v2:0.10> <lora:extremely_detailed_v2:0.25> <lora:add_detail:0.75> <lora:perfect_eyes:0.25> <lora:perfect_hands:0.50>
Negative prompt
Unspeakable-Horrors-Composition-SDXL, SDXL_TI_my_eyes_are_bleeding, unaestheticXL_Alb2, poorly drawn, gloomy, messy, low quality, blurry, doll, deviant, animal ears, topless, breasts, nipples, strange clothing
Similar Models
Badges for creators
Made this model? Put its standing on your Civitai page, your Hugging Face card, your README or your site. Each badge is a small picture that shows the standing on the day you copy it and never changes afterwards, however the rankings move later. The date is part of the badge. Every badge links back to this page.
Badge shape
AI Models for Image, Video & Text Generation
Perfect Eyes XL is a LoRA for the Stable Diffusion XL 1.0 family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Stable Diffusion XL 1.0 models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.
More Stable Diffusion XL 1.0 modelsMore Stable Diffusion XL 1.0 LoRAseyespositivesanatomyphotorealisticconceptsinpaint
Browse by Model Family
Text / LLM Models
415
Anima Models
519
Chroma Models
17
Flux Models
1,498
Flux 2 / Klein Models
1,239
MiniMax H3 Models
330
Hunyuan Models
204
Ideogram Models
20
Krea2 Models
676
Qwen Models
20
Qwen2 Models
36
Ltx2 Models
152
Stable Diffusion 1.5 Models
7,042
Stable Diffusion XL 1.0 Models
17,420
Zimage Models
815
Wan Models
1,244

Model
Trends
.ai
© ModelTrends.ai
|
© 2026
|
All Rights Reserved
