home models images videos posts articles bounties challenges events updates shop

Flat Colour Anime

Name: Flat Colour Anime
Rating: 5 (1863 reviews)
Author: CrasH

1.9k

22k

577.4k

775

Updated: Jul 9, 2025

style

anime flat colors flat color styles

Verified: a year ago

SafeTensor

Details

Type	LoRA
Stats	4,417 476.9k 62.7k
Reviews	Overwhelmingly Positive (618)
Published	Jan 26, 2024
Base Model	SDXL 1.0
Training	Steps: 6,980 Epochs: 25
Usage Tips	Strength: 1
Trigger Words	fca style
Hash	AutoV2 DE4C7C9B71

1 File

About this version

Anime Flat Color XL

Update 2.0!

v2 trained completely from scratch on the SDXL base model for maximum compatibility with other models (works great on Juggernaut XL and Anime Art Diffusion). The training set was increased from 80 images to 350 and trained over a much longer period.

The trigger words have also been changed from "flat color" to "fca style" to avoid conflicts with existing training bias in some models which would really mess up the images.

An anime Lora trained on a modern flat color anime style. SD 1.5 has some really great flat color checkpoints (Flat Color 2D and Coloring Master Anime in particular), but SDXL has been lacking in this particularly style. This Lora aims to fill that hole. It was trained on a lot of images across a range of characters, clothing types, skin tones, hair and eye colours, and a load of other additions so it should have good flexibility.

Recommended weight: 1

Trigger word: fca style

default creator card background decoration

CrasH

Flat Colour Anime!

A vibrant anime style trained using a high quality dataset captioned in natural language. This is my labour of love and I'm constantly working on improving it.

Please consider following to be notified on updates to this style and many more interesting styles I create ❤️

I offer Lora commissions - please message me with your requests.

Style Lora - $20
Character Lora - $25

Important notes below! Please read

Keywords:

Check the version details on the right for the correct trigger words for your version. Currently these are:

"Flat colour anime style image showing" for Flux Dev and Schnell
"fca_style" for Pony
"fca style" for SDXL

If you don't use the keyword, you won't get the most out of the style.

Version Key:

✅ Current

⛔️ Deprecated

Select the relevant version for your model from the top.

Update notes for version 3.4:

Now available for both Flux Dev and Schnell
Longer training time with a lower learning rate
Trained at 1024px vs 512px
Improved dataset quality
Added regularisation images to the dataset