Sign In

Zavy's Cinematic Stills - SDXL

492

6k

47.6k

226

Verified:

SafeTensor

Type

LoRA

Stats

5,975

47.6k

2.2k

Reviews

Published

Mar 19, 2024

Base Model

SDXL 1.0

Training

Steps: 6,144
Epochs: 6

Usage Tips

Strength: 0.6

Trigger Words

zavy-cnmtc

Hash

AutoV2
70BA89566C
Chroma Chest
Zavy's Avatar

Zavy

Please consider joining my Patreon so I can keep most of my work available for everyone - I'll be releasing early access models there for a cheaper monthly fee than buying them here individually, and also will be providing exclusive models and more!

For business inquiries, commercial licensing, custom models, and consultations, please get in touch at [email protected] or [email protected]. You can also contact me here through CivitAI DM or join my Discord.


Introduction

This LoRA mimics the essence of a cinematic still. It typically produces a shallow depth of field, particularly when the subject, such as a person, is well-defined in the image. It furthermore offers lower contrast compared to SDXL finetunes (which often nearly burn their images), a distinct color range for shadows, and introduces a subtle haze. This results in a cinematic still that appears more natural and provides artists with greater flexibility for post-processing adjustments such as contrast manipulation, dehazing, texture enhancement, and saturation tuning.

Triggers

zavy-cnmtc

Zavy-cnmtc is a semi-required trigger. Consider using other terms, such as: atmospheric haze, cinematic still, dynamic lighting, movie screencap, moody, film. These will help enhance the LoRA's effect, otherwise you may get a pretty bland image.

Strength between 0.3 and 0.7.