models/MJanime_Flux_LoRa_v3_Final - MJanime_Flux_LoRa_v3final

MJanime_Flux_LoRa_v3_Final - MJanime_Flux_LoRa_v3final

7/27/2025

3:31:47 AM

Related Keywords & Tags

anime,anime style,flux.1 d,flux lora model,flux v2_15k,flux v2_final,flux v3.1,flux v3_final,lora,mjanime_flux_lora_v3_final,mjanime_flux_lora_v3final,stan_katayama,style

Silhouettes of people walking in a neon-lit cityscape with colorful gray tones and vibrant vertical light streaks in pink, orange, and blue.

Close-up of a menacing demon with glowing red eyes and sharp teeth, exhaling fire and steam while gripping an ornate dagger engraved with fiery patterns.

Close-up of a cinematic, detailed eye with fiery orange iris amidst a dynamic, rainy storm background.

A glowing, animated ball with expressive eyes sits on a fiery, molten surface with dramatic lighting and cinematic shadows.

A mysterious dark cat with glowing orange eyes holding a beer bottle in a cinematic, detailed, and sharply composed painting style.

A feral cat with fierce expression wielding a large chainsaw, rampaging through a fish market with fish flying around and a bright blue sky in the background.

A digital painting showing a glowing skeletal dragon head with icy blue hues and hollow eyes against a dark abstract background with rough and eerie texture details.

A group of cute kodama spirits posing awkwardly for a death-metal album cover in a magical forest, viewed from a low angle with dark, haunting figures in the background.

A whimsical moss-covered cottage with a thatched roof and stone chimney, surrounded by vibrant autumn foliage in a sunlit forest.

A baseball player in mid-swing hit in the face by a baseball, with a dramatic impact explosion and moody sky in a cinematic sports scene.

Intense anime portrait of a young woman screaming with wide eyes against a red and black background, hand drawn with crayon-like strokes.

Anime male character with long flowing black hair and intense green eyes, wearing a martial arts outfit, surrounded by dynamic water splashes, in mid-action delivering a powerful punch.

Recommended Negative Prompts

Bad hands, mutated hands, poorly detailed hands

Recommended Parameters

samplers

euler beta, deis simple, euler simple

steps

cfg

3.5 - 5

resolution

1152x1536

other models

flux1-dev-fp8 (1be961341b)

Tips

Load Lora models in fp16 if possible for better performance.

For a pronounced anime style, use a strength value between 0.90 and 1.30.

Try varying strength (e.g., 0.5 or 0.6) to obtain more realistic images.

The model was created with Ostris script available at https://github.com/ostris/ai-toolkit?tab=readme-ov-file#flux1-training

Hello everyone!

All models are exclusive to Civitai ! Anyone who publishes my models without my consent will be reported!

Trigger Word : Anime style

I highly recommend loading my lora models in fp16 if possible

Since Flux's anime style is a bit weak, I decided to tackle it for my first training of Flux LoRa model.

v3_Final : This version uses the same dataset as v3.1 but this time at 100 epoch against 16 before.

The poses are more dynamic and the characters more expressive

V3.1 : A new dataset of 330 images. Better selection so that characters look older if requested.
The overall quality is also much better

V2_Final : same as v2_15k, but the style is much more pronounced

v2_15k : This version has a dataset of 338 images against 112 for version 1.

This is not the final version of this v2, but I find this 15k steps version very interesting and rather stable.

This version was trained with the optimizer "prodigy" in rank 32

The style is there, but the final version will be very different!

V1 : I used for this 112 high quality images generated with MidJourney v6 in the --personalize style.

Be indulgent, this is a first try. If you zoom in a bit on the images the lines can appear a bit pixelated. But the style is pretty cool!

For a pronounced anime style, Sweet spot between 0.90 and 1.30

I recommend you to play with the strength to vary the pleasures for example at 0.5 or 0.6 by asking for a realistic image.

The model was created with Ostris script which you can find here :
https://github.com/ostris/ai-toolkit?tab=readme-ov-file#flux1-training

Have fun! 😊