Diffus
Inicio
Afiliado
Precios
SD3
API
Modelos
Galería
Empezar
modelos/MJanime_Flux_LoRa_v3_Final - MJanime_Flux_LoRa_v3final

MJanime_Flux_LoRa_v3_Final - MJanime_Flux_LoRa_v3final

Stan_Katayama
|
8/8/2025
|
11:16:23 PM
| Discussion
Hand drawn anime portrait of a young woman screaming with a determined expression, featuring dominant black and red colors and crayon stroke textures.
Anime style male character with long flowing black hair and intense green eyes delivering a powerful punch surrounded by dynamic water splashes.
A lone raven-haired huntress clad in tattered Victorian clothing wields a beast-scarred glaive, standing amidst crumbling tombstones enveloped in swirling fog and gloomy skies.
Anthro fox wearing a suit and red tie holding a sign that reads 'DOUBLE DIPPING TEXT CONTEST AND BUZZ BEG FOR TWICE THE PROFIT' in a playful, rounded font, oil painting style.
A figure in a sleek, armored futuristic spacesuit with glowing red circuitry walks through a frozen alien wasteland with a wrecked starship in the background under a dark sky lit by red stars.
Close-up of an Abyssal Flame Beast with obsidian-black cracked skin glowing with magma veins, fiery molten lava fur, glowing amber eyes, black twisted horns, and dynamic smoke and embers on a dark background.
Surreal portrait of a woman surrounded by a swirling vortex of orange and white floating petals with fish eye lens distortion and a dark, cinematic background.
Dynamic portrait of a cosmic bride mid-spin wearing a flowing nebula gown with galaxy patterns and glowing cosmic energy against a celestial sky with twin moons and auroras.
A cyborg woman in a sleek mechanical suit floats asleep in a glowing cryogenic chamber filled with luminous liquid, connected to monitors displaying her vital signs.

Prompts Negativos Recomendados

Bad hands, mutated hands, poorly detailed hands

Parámetros Recomendados

samplers

deis simple, euler beta, euler simple

steps

40

cfg

3.5 - 5

resolution

1152x1536

other models

flux1-dev-fp8 (1be961341b)

Consejos

Load LoRa models in fp16 for better performance.

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

Playing with strength values at 0.5 or 0.6 can generate more realistic images.

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! 😊

Colaborador

Stan_Katayama avatar

Stan_Katayama

Anterior
0x00F_Ashley-Wood - V1
Siguiente
G0zeNA | Shiiro's Styles - v1.0
Usar este modelo

Detalles del Modelo

Tipo de modelo

LORA

Modelo base

Flux.1 D

Versión del modelo

MJanime_Flux_LoRa_v3final

Hash del modelo

e9ede91ef2

Palabras entrenadas

Anime style

Creador

Stan_Katayama's avatar
Stan_Katayama

Discusión

Por favor log in para dejar un comentario.

Imágenes por MJanime_Flux_LoRa_v3_Final - MJanime_Flux_LoRa_v3final

Hand drawn anime portrait of a young woman screaming with a determined expression, featuring dominant black and red colors and crayon stroke textures.
Close-up of an Abyssal Flame Beast with obsidian-black cracked skin glowing with magma veins, fiery molten lava fur, glowing amber eyes, black twisted horns, and dynamic smoke and embers on a dark background.
Anime style male character with long flowing black hair and intense green eyes delivering a powerful punch surrounded by dynamic water splashes.
Surreal portrait of a woman surrounded by a swirling vortex of orange and white floating petals with fish eye lens distortion and a dark, cinematic background.
A lone raven-haired huntress clad in tattered Victorian clothing wields a beast-scarred glaive, standing amidst crumbling tombstones enveloped in swirling fog and gloomy skies.
Dynamic portrait of a cosmic bride mid-spin wearing a flowing nebula gown with galaxy patterns and glowing cosmic energy against a celestial sky with twin moons and auroras.
Anthro fox wearing a suit and red tie holding a sign that reads 'DOUBLE DIPPING TEXT CONTEST AND BUZZ BEG FOR TWICE THE PROFIT' in a playful, rounded font, oil painting style.
A cyborg woman in a sleek mechanical suit floats asleep in a glowing cryogenic chamber filled with luminous liquid, connected to monitors displaying her vital signs.
A figure in a sleek, armored futuristic spacesuit with glowing red circuitry walks through a frozen alien wasteland with a wrecked starship in the background under a dark sky lit by red stars.