Recommended Parameters

samplers

Euler, DPM++ 2M

steps

20 - 35

cfg

3 - 4.5

Tips

Recommended at 0.8-1.2 strength for best results.

Describe the exact style of retro anime in detail to guide the model.

No specific trigger words needed.

Feel free to share images created with this LoRA.

Version Highlights

Init release

A small test to practice FLUX training which turned out to be pretty good. This LoRA captures the style of those pictures in retro anime style generated by midjourney.

Recommended at 0.8-1.2 strength.

There are no specific trigger words, so try to describe the exact style of retro anime you want to go for with detail and it will do the rest. (See the model images for examples, though you do not have to stick exactly with those)

If you find it cool or anything, please consider leaving a like, comment or other reaction!

Donations are massively appreciated!

Update plans: Making the grain/halftone much more controllable; Extending the dataset to not just MJ images; further extending versatility

Also feel free to post any images you create with it below, cause I'm really curious what people can get out of this LoRA ;)

Previous
SD XL - v1.0 VAE fix
Next
SDXL / Flux.1 D - Matte (Vanta)Black - Experiment - Flux.1 D v2.0

Model Details

Model type

LORA

Base model

Flux.1 D

Model version

v1.0

Model hash

8f43c31b6c

Discussion

Please log in to leave a comment.

Model Collection - Retro Anime Flux - Style