modelli/NoobAI-XL Detailer - V-Pred1_V1

NoobAI-XL Detailer - V-Pred1_V1

7/2/2025

11:22:31 AM

Parole Chiave e Tag Correlati

concept,custom flat color lora,dark imagery,detailer,lora,noobai,noobai-xl,noobai-xl detailer,stable diffusion model,v-pred,v-pred1_v1,volnovik

A happy girl with green twintails wears opaque spiral glasses, a white shirt, red ribbon, and plaid skirt, captured mid-jump with arms raised and bent knees in a pop art style.

Silhouette of a girl with short hair and glowing pink eyes wearing ankle boots against a solid pink background.

Girl with pink braided hair wearing a yellow raincoat holding a transparent umbrella in light rain under dark sky, surprised expression looking up.

A girl with pink twin-tailed hair, wearing a baseball cap and black and beige casual outfit, holding a large detailed sword with a confident smirk, squatting in a dynamic pose.

A girl with white hair sleeping soundly on a wooden boat floating on a lake at midnight under a crescent moon with soft moonlight reflections on the water in Sinozick style.

Silhouetted angel figure floating against a soft pastel blue and purple sky, with glowing wings, star-shaped halo, and star details around.

Close-up portrait of a dark-skinned female elf with yellow eyes performing icekinesis with an outstretched icy hand against a snowy cityscape background.

A blonde woman in a purple dress sits at a wooden desk reading an open book in a warmly lit study room with an arched window and classic decor.

A Blood Witch kneeling within a glowing sacrificial circle surrounded by lit candles, with giant dark crimson dripping wings unfolding behind her in a shadowy gothic cathedral-like setting.

Portrait of a blonde-haired demon girl with black horns wearing a traditional sailor-style school uniform with a blue collar and red neckerchief, set against a yellow background.

Digital illustration of a female ballerina wearing a high-leg leopard print leotard and wide brim black hat, posing elegantly indoors with dramatic purple and black lighting.

A powerful dynamic pose of a girl with long black hair flowing dramatically, wearing a white bodysuit with black boots, red eyes intense and vivid orange and dark grey splattered background.

Prompt Consigliati

1girl, (himeyamato:0.9), aoi sakura \(seak5545\), (hyonee:1.1), (eversoul:0.9), achyue, (dishwasher1910:0.8), momoko \momopoco\, (nardack:0.8), (torino aqua:0.4), masterpiece, amazing quality, best quality, absurdres, very aesthetic, newest, very awa, sharp, crisp, 8k

Prompt Negativi Consigliati

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, twins, splatter, plump, leotard, wet, yellow skin, expressionless, steam, extra ears, (blurry background, bokeh:1.5), hair intakes, futanari, mosaic censoring, pixelated, school uniform, forehead jewel, half-closed eyes, cum, red eyeshadow, out of focus

Parametri Consigliati

samplers

DDPM, DPM++ SDE

steps

cfg

5.5

resolution

928x1232, 1856x2464

other models

NOOB_vp1_detailer_by_volnovik_v1 (da259df60e36), ponyv6_noobV1_2_adamW (72ea46a2b089), noobaiXLNAIXL_vPred10Version (ea349eeae8), NOOB_vp1_detailer_by_volnovik_v1 (4e49eed4cd05)

Parametri Consigliati per Alta Risoluzione

denoising strength

0.3 - 0.35

Suggerimenti

Use V-Pred V0.5 with weight 1.5 to enhance images.

V1.0 version darkens images, especially with short prompts like '1girl, dark, night'. Be more descriptive to avoid unwanted dark silhouettes.

Recommended weight range for V0.5 is -6 to +6, best to use 1-2.

V-Pred versions work best on the V-Pred model; check checkpoint description if unsure.

NoobAI-XL is capable of producing very dark imagery unmatched by base models.

Punti Salienti della Versione

This took waay more effort then it was supposed to. Ended up with tweaking OneTrainer to work with v-pred SDXL (thanks to guy from Discord for guiding me). But here it is:

Detailer V1, V0.5 merged with custom synthetic undertrained minimalist style lora. Please read main description for more info on specifics. Designed to be used with 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.