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 01

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 fmlygyssn01 in your prompt.

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

Prompt Examples

Here are some prompt examples:

"fmlygyssn01, A white dog lounges comfortably on a plush purple sofa, one paw."

"fmlygyssn01, A plump individual in a red button-up shirt is centrally framed, hands."

"fmlygyssn01, A child in a blue cap and red shirt walks along a."

"fmlygyssn01, A white dog with a red collar and a yellow tag sits."

"fmlygyssn01, A family of four is seated closely together on a purple couch."

"fmlygyssn01, A person with blonde hair and an orange cap stands in front."

"fmlygyssn01, A white dog with a red collar sits at a pink table."

"fmlygyssn01, A white, bipedal dog stands upright on a bathroom counter, looking at."

"fmlygyssn01, A family of four, including a large man in a white shirt."

"fmlygyssn01, A person in green pants and a white shirt lies face-down on."

"fmlygyssn01, A white, cartoonish dog with a large black nose and red collar."

"fmlygyssn01, A family of four is seated in a small blue boat labeled."

"fmlygyssn01, A small child in a red backpack stands at an airport check-in."

"fmlygyssn01, A man in a brown suit and yellow tie stands on a."

"fmlygyssn01, Two older men in suits sit side-by-side at a desk, each wearing."

"fmlygyssn01, A rotund man with glasses sits on a purple couch, holding a."

"fmlygyssn01, A blonde woman in a blue top is driving a red convertible."

"fmlygyssn01, A white dog with a black nose and a black collar featuring."

"fmlygyssn01, Inside a red vehicle, a woman with red hair and a green."

"fmlygyssn01, A tall, beige prison building with “JAIL” prominently displayed on its facade."

Training

• Base model: Krea 2 (trained on Raw)
• Type: Style LoRA
• Dataset: 291 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.