Sign In

Family Guy Season 22 TV Series Lora Style

2

Updated: Oct 2, 2026

style

Loaded

Download

1 variant available

fp16 SafeTensor

family-guy-season-22.safetensors

Half precision, best balance • 218 MB

Verified:

Type
LoRA
Stats

51

2

14

Generation

Loaded

Reviews
Published

Oct 2, 2026

Base Model

Krea 2

Training
Steps: 2,000
Epochs: 3
Usage Tips
Strength: 1
Hash
AutoV2
3EFBD871C0
Trigger Words
fmlygyssn22
default creator card background decoration
Followers - 507

507

Likes - 4162

4.2K

portada.png

Premium character LoRAs

Original synthetic characters, bundles and AI tools are in my shop:

https://rkrra.com/civitai

Get the character LoRAs on Patreon: https://www.patreon.com/cw/RkRRa

Join the community on Discord: https://discord.gg/nB79wRNtMT

Family Guy Season 22

A style LoRA for Krea 2. Applies a consistent visual treatment without locking the subject matter.

⚠️ WARNING: faces are not perfect

This model does not always render faces perfectly. I trained it several times, but with this many LoRAs (22 seasons) I ended up giving up on getting the faces right every time. The overall style is good, but sometimes the faces come out a bit off.

I'm publishing it anyway because it is usable, it took a huge number of training hours and it would be a shame to throw it away. Just keep in mind that it is not a perfect model.

Recommended weight: 1.0 – 1.5. Adjust it to your taste and try higher weights too. Generate in wide 16:9: that is the format it works best in.

Usage

Include the trigger word fmlygyssn22 in your prompt.

Recommended weight: 1.0 – 1.5 (see the warning above).

Prompt Examples

Here are some prompt examples:

"fmlygyssn22, Four men are seated around a wooden table in a dimly lit."

"fmlygyssn22, A man in a dark suit and red tie stands at a."

"fmlygyssn22, A black bowling ball is captured mid-motion, colliding with a cluster of."

"fmlygyssn22, Three animated figures sit side by side on a brown couch in."

"fmlygyssn22, Two individuals sit at a dining table, one with a concerned expression."

"fmlygyssn22, A young boy sits in a large green beanbag chair, intently focused."

"fmlygyssn22, A family gathers around a long dining table laden with breakfast food—pancakes."

"fmlygyssn22, A woman with short red hair and a green shirt is pushing."

"fmlygyssn22, A family of four and a dog are seated around a dining."

"fmlygyssn22, A cheerful, rotund man in a striped teal shirt and dark shorts."

"fmlygyssn22, A large man in a white shirt and green pants stands with."

"fmlygyssn22, In a brightly lit indoor scene, two men are shaking hands in."

"fmlygyssn22, A woman with short red hair, wearing a green shirt and pushing."

"fmlygyssn22, A white, cartoon dog with a red collar and a yellow tag."

"fmlygyssn22, Three speech bubbles float above a school entrance, displaying gossip and commentary."

"fmlygyssn22, A white, cartoonish dog with large, expressive eyes and a wide-open mouth."

"fmlygyssn22, A woman with shoulder-length blonde hair and purple-tinted glasses sits on a."

"fmlygyssn22, A bald, round-faced child with wide, startled eyes and dark streaks running."

"fmlygyssn22, A white dog with a red collar sits in a booth at."

"fmlygyssn22, A bald, wide-eyed toddler in red overalls and a yellow shirt sits."

Training

  • Base model: Krea 2 (trained on Raw)
  • Type: Style LoRA
  • Dataset: 280 images
  • Steps: 2000
  • Network rank / alpha: 32 / 32
  • Learning rate: 0.0002
  • Optimizer: adamw8bit
  • Resolutions: 512 / 1024

Generation settings

Trained on Krea 2 Raw, and transfers to Krea 2 Turbo for faster generation.

  • Raw: ~30 steps, guidance 3.5
  • Turbo: ~8 steps, guidance 1.0

The preview images were generated with krea2_turbo_mxfp8.safetensors, at 8 steps, guidance 1, LoRA weight 1.5, in 16:9.