Young woman wearing a white tank top with a peace sign and jean shorts, taking a selfie with an iPhone on a sunny California beach sidewalk with palm trees in the background.
Yellow 1990s style taxi cab driving through a busy New York City street under a bright blue sky on a sunny day.

Recommended Prompts

bad quality,jpg,grain

portrait photo of a german man outside a night club, morning, 1990, tuxedo, suit, <lora:badquality_v02:1> bad quality

Recommended Negative Prompts

(depth of field)

black and white, (depth of field)

Recommended Parameters

samplers

DPM++ 2M Karras, Euler a

steps

20 - 30

cfg

4.5 - 7

resolution

1344x768, 680x1024

other models

thinkdiffusionxl_v10 (a21c9949ef), sd_xl_base_1.0 (31e35c80fc)

Tips

Use prompts containing 'bad quality, jpg, grain' to enhance the organic, degraded effect.

Include '(depth of field)' as a negative prompt to significantly improve the realism look.

The v02 version of the model works better and can function with minimal prompt input.

Version Highlights

I actually cant remember what extra I did, but I know this is trained on a bunch of extra crappy pics. Works better than v01.

as title says, this is designed to mess up the image in the pursuit of realism. It's intended tol break your whitebalance, add grain, and blur and other organic things Ai avoids usually.

Help it along with some "bad quality, jpg, grain" type prompts.
(depth of field) in the negative helps a LOT for the look

Updated with a v02 that works a bit better. Can even function with minimal prompt help now.

Previous
Dungeons & Dreamscapes - v1.0 Krea
Next
Vixon's Illustrious Styles - Wires and Trees - illust

Model Details

Model type

LORA

Base model

SDXL 1.0

Model version

v2.0

Model hash

af79e4b272

Trained words

badquality
low quality

Discussion

Please log in to leave a comment.

Model Collection - Bad Quality Lora | SDXL

Images by Bad Quality Lora | SDXL - v2.0

amateur Images

bad quality Images

phone Images

style Images