Run Locally
CosmicEyes.safetensors
36 MB · SafeTensor
Downloads are served by Civitai. Some creators ask for a Civitai login first.
About This Model
STABLE DIFFUSION 1.5 · LoRAs
LoRA Cosmic Eyes \ Concept by Gwess. Universal-auxiliary LoRA for creating eyelashes, beautiful eyes and portraits! Eye color adjustment occurs either from the character parameter when used with other LoRA or manually using Prompt* LoRA works great with values from 0.6 to 1.0, in the examples it was used at 1.0! Various Prompt* are supported, for example "+_+" and the like. Trigger Words * CosmiEyes
Creator notes
created with private LoRA that I don't post on
I have created a discord server where you can post your work and offer your ideas for LoRA.
Universal-auxiliary LoRA for creating eyelashes, beautiful eyes and portraits!
Eye color adjustment occurs either from the character parameter when used with other LoRA or manually using Prompt*
LoRA works great with values from 0.6 to 1.0, in the examples it was used at 1.0! Various Prompt* are supported, for example "+_+" and the like.
Trigger Words *
CosmiEyes
Promts for this LoRA:
At your discretion! Her clothes become a trigger prompt.
Trigger words
CosmiEyes
SHA256
379014B216D027EB62EAAEFCB6B6777EB07528E679D60954CA420CBB5CC98BD1
ModelTrends.ai Model ID
#1513
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
DPM++ 2M Karras
Steps
20
Guidance
7.5
Seed
3954888707
Size
900x800
Clip skip
2
Prompt
cervina, face, masterpiece, high quality, high detailed eyes, (looking at viewer), cosmieyes, eye focus, eyelashes <lora:CosmicEyes:1><lora:cervina:1><lora:cervina:1>
Negative prompt
(worst quality, low quality:1.2),myself-badhand-v5,blurry, bokeh, dof, fog, by bad-artist, (bad eyes:1.2), (misfigured pupils:1.2), (bad clothing:1.3), (undetailed clothing:1.3), ng_deepnegative_v1_75t, verybadimagenegative_v1.3, (nonsensical backrounds:1.2), (bad backrounds:1.2), (bad shadows:1.2),(bad anatomy:1.1),multiple hands,nipples,
Settings
Sampler
Euler a
Steps
30
Guidance
7
Seed
3711442484
Size
512x768
Clip skip
2
Prompt
masterpiece, best quality, solo, 1girl, detailed eyes, detailed hands, detailed lighting, highres, full body,
<lora:add_detail:0.4>
<lora:CosmicEyes:0.2>, blue eyes,
<lora:EraseGroinSkirt:0.7>
<lora:swordmaiden:1> , sword_maiden, long hair, blindfold, dress, white dress, habit, jewelry, black blindfold, necklace, detached sleeves,
Negative prompt
(badhandv4:1.5), easynegative, FastNegativeV2, extra limbs, censored, title, signature, cameltoe, low quality, worst quality, (bad anatomy:1.5), inaccurate limb, bad composition, inaccurate eyes, extra digit, fewer digits, ((realistic:0.5)), (((watermark:2))), (stars, cosmos, cosmic:1.2), censored, city, black background, 2.5D,
Settings
Sampler
DPM++ 2M Karras
Steps
25
Guidance
7
Seed
879690617
Size
512x768
Clip skip
2
Weight used
1.2
Prompt
female, long silky yellow hair, giant eyes, big perky breasts, extravagant revealing dress, environment in a forest full of colorful alien trees and plants, detailed backround, detailed environment, perfect face, perfect body, dreamy digital painting, colorful, gradient, professionally color graded, high contrast, magnificent, celestial, ethereal, painterly, epic, low contrast, unreal engine
Negative prompt
EasyNegativeV2, (low quality:1.32), (normal quality:1.31), (worst quality:1.33), (bad Hands), (mutated hands, mutated feet, mutated limbs:1.2), (deformed hands:1.2), (text:1.5), simple background, (missing fingers, missing toes, extra fingers, extra toes), normal breasts
Similar Models
AI Models for Image, Video & Text Generation
cosmic eyes is a LoRA for the Stable Diffusion 1.5 family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Stable Diffusion 1.5 models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.
More Stable Diffusion 1.5 modelsMore Stable Diffusion 1.5 LoRAsanimephotographyanatomywomanconcept artcute2dgirls
Browse by Model Family
Text / LLM Models
411
Anima Models
509
Chroma Models
14
Flux Models
1,071
Flux 2 / Klein Models
1,237
MiniMax H3 Models
331
Hunyuan Models
197
Ideogram Models
20
Krea2 Models
674
Qwen Models
17
Qwen2 Models
36
Ltx2 Models
150
Stable Diffusion 1.5 Models
6,465
Stable Diffusion XL 1.0 Models
15,432
Zimage Models
804
Wan Models
919

Model
Trends
.ai
© ModelTrends.ai
|
Made in Japan
|
© 2026
