models/NoobAI-XL Detailer - EPS1.1_v1.0

NoobAI-XL Detailer - EPS1.1_v1.0

8/25/2025

11:41:22 PM

Related Keywords & Tags

concept,dark imagery,detailer,eps1.1_v1.0,image detailing,lora,noobai,noobai-xl,noobai-xl detailer,stable diffusion model,v-pred,volnovik

Anthro deer hybrid female with red hair holding a large torn green umbrella, wearing a leaf dress, standing in a coniferous forest under a cloudy sky, birds perched on her antlers in a nest.

Artwork showcasing a doll girl with white hair in a braided bun adorned with red ribbons and a key ornament. She kneels, wearing mechanical limbs and a white outfit, interacting with a small angelic cat with mechanical wings, presenting a key.

Pale gothic girl with black bob cut and feather hair ornament stands on a moonlit beach surrounded by red crabs and flying seagulls under a bright full moon reflecting on the ocean waves.

A black-haired girl with a bob cut and expressionless face is cheek-poked by a black cat while surrounded by grumpy white and black cats against a pink dithering background in pixel art style.

Recommended Prompts

1girl, (eversoul:0.9), achyue, momoko \momopoco\, masterpiece, best quality, (torino aqua:0.4), amazing quality, very aesthetic, absurdres, newest, very awa, crisp, sharp

Recommended Negative Prompts

worst quality, low quality, quality, lowres, worst aesthetic, jpeg artifacts, scan artifacts, signature, bad id, bad twitter id, english commentary, bad hands, username, mutated hands, mammal, logo, anthro, furry, scanlines, blur, blurry, comic, (long body, long neck:1.3), extra digit, missing digit, old, simple background, (censored:1.3), stomach bulge, cleft of venus, bar censor, half-closed eyes, twins, splatter, plump, harness, magical girl, wet, leotard, fake animal ears, maid headdress, yellow skin, red eyes, steam, extra ears, cum, blurry background, bokeh, forehead jewel, hair intakes

Recommended Parameters

samplers

DPM++ SDE

steps

cfg

resolution

1856x2464, 928x1232, 1024x1024

other models

NOOB_EPSv1_1_detailer_by_vlnvk_v1_0 (3d45d9ee77cb), noobaiXLNAIXL_epsilonPred11Version (6681e8e4b1), NOOB_EPSv1_1_detailer_by_vlnvk_v1_0 (fdac4e8f5dc2), ponyv5_noobE11_1_adamW (bed28b6a7ad2)

Recommended Hires (High-Resolution) Parameters

denoising strength

0.35 - 0.59

Tips

V-Pred versions work better on the V-Pred model. If not familiar, check checkpoint description.

For V0.5, use weight around 1.5 to improve image quality.

V1.0 version can darken dark areas creating strong dark imagery; more detailed prompts help avoid black silhouettes.

Recommended weight for V1.0 merged with custom flat color lora is about 1.

For V0.5 weight range is -6 to +6; recommended usage is between 1-2.

Version Highlights

Baked a custom undertrained symthetic flat color lora and merged at negative ratio with v0.5. Almost a week of experimentation.

Result is slightly changing the scene but in my tries only for good. Due to custom synthetic lora has little to no effect on artist styles. Intended to use at weight 1.

This is simple detailer trained on model NoobAI-XL.

V-Pred versions work better on v-pred model. If you don't know what it means - read checkpoint description. If not explicitly stated - 99% it is eps prediction version.

V-pred related specifics:

V0.5 - just slap it on with weight 1.5 makes image better.

V1.0 - slightly alters image giving more details. Weird interaction that I found - it darkens dark. V-pred NOOB-AI is first SDXL model that I see that can make really dark imagery. ESPECIALLY with short prompts, like 1girl, dark, night. If you are feeling that that is not what you want - just be more descriptive. describe face, vlothes and you won't get those black on black silhouettes anymore. Btw that applies to the NOOBvp1 itself too. See example here: https://civitai.com/images/47951726

On the upside it can darken stuff that base model has issues with darkening, like some poses.

V1.0

Merged with custom flat color lora, recommended weight is 1. Slightly alters image, especially with no prompts like 1girl.

V0.5

Weight range -6 - +6

I recommend using 1-2.