About 160 Civitai nodes for ComfyUI, image, video, audio, text, and training, with built-in model browsing.

Civitai Nodes for ComfyUI

Smarter defaults, pay-per-step pricing, new sample controls, and a Train Further button.

Training Updates

Your AI agent can use Civitai now: browse, generate, post, and engage through the new MCP server and gen skill.

Agents Welcome

<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/a143c5f8-aa73-4219-9576-074e1d85c597/width=525/a143c5f8-aa73-4219-9576-074e1d85c597.jpeg" />MJ MODE — a LoRA that recreates the signature MidJourney style: rich details, cinematic depth, vibrant colors, and atmospheric mood. It enhances any prompt with artistic complexity and dramatic flair, staying true to the recognizable MidJourney aesthetic. Recommended weight: v1 0.85. , v2 0.5-1

This new version of the MJ Mode LoRA was trained on a completely updated dataset to improve overall image quality, consistency, and visual style. The model now produces more refined details, cleaner compositions, better lighting, and a more polished aesthetic.Key improvements:<ul><li>Trained on a new dataset</li><li>Improved overall generation quality</li><li>Better detail refinement and image sharpness</li><li>More consistent style reproduction</li><li>Cleaner lighting, colors, and composition</li><li>Enhanced realism and visual balance</li></ul>

v2.0 ZIT EDITION

MJ MODE (Midjourney Style LoRA for Z-image)MJ MODE is a Midjourney-inspired style LoRA for Z-image, built to replicate that instantly recognizable MJ “wow” aesthetic: bold art direction, cinematic lighting, rich color harmony, crisp subject separation, and a polished, poster-ready finish. It pushes images toward stylized realism with dramatic atmosphere, clean compositions, and high visual impact—perfect for thumbnails, covers, promo visuals, and hero shots.What this style delivers<ul><li>Midjourney-like polish: strong art direction, clean shapes, premium finishing</li><li>Cinematic lighting: rim light, volumetric beams, dramatic highlights/shadows</li><li>Rich color harmony: saturated but controlled palettes, “grade-first” look</li><li>High clarity &amp; separation: clear silhouettes, depth, strong focal emphasis</li><li>Atmosphere on demand: haze, fog, clouds, glow accents, cinematic mood</li></ul>How to use<ul><li>LoRA weight: <code>0.3–1</code> </li><li>Helpful prompt phrases: “midjourney style, cinematic, dramatic lighting, volumetric haze, rich color grading, ultra polished, stylized realism, clean composition, high detail”</li></ul>Multi-LoRA usage (with other LoRAs)MJ MODE combines well with character/object LoRAs, but avoid overloading. Recommendation: keep the total sum of all LoRA weights at or below ~1.2 to prevent artifacts, identity drift, or an “overcooked” look.

v1.0 ZIT EDITION

v2.0

v1.0

MJ MODE

z-image_00093_.png

physical violence

weapon violence

wide hips

revealing clothes

thick thighs

downblouse

convenient censoring

huge breasts

pg-13

corpses

suggestive

oral invitation

pg13

sexy

sexual situations

male nudity

disturbing

male swimwear or underwear

female swimwear or underwear

partial nudity

undressed

female nudity

breasts out

exposed female nipple

breast out

lingerie

male underwear

hair over breasts

female swimwear

gigantic breasts

no panties

graphic violence or gore

covered nipples

huge butt

strapless leotard

sitting on face

emaciated bodies

one breast out

nsfw

female underwear

nude

graphic male nudity

adult toys

illustrated explicit nudity

nudity

graphic female nudity

hentai

futanari

porn

sexual intent

genitals

peeing

vore

oral

sexual activity

anal

blowjob

dildo riding

incest

hanging

hate symbols

nazi party

white supremacy

diapers

scat

self injury

hate speech

urine

extremist

child on child

latex clothing

swimwear

bukkake

fellatio

cumshot

implied fellatio

eat_cum

cumdrip

cum in pussy

cum on face

after fellatio

cum on hair

cum on body

cum on tongue

cum on hands

cum in mouth

triple fellatio

autofellatio

fucked silly

cum on pussy