modelos/NAI / Flux1. D - The Edgy Mech - NAI - v3.0

NAI / Flux1. D - The Edgy Mech - NAI - v3.0

|
7/29/2025
|
11:03:49 AM
| Discussion|
0
Futuristic sci-fi cityscape at night under dark blue light, featuring snowflakes, glowing windows, and moody digital urban environment.
Blonde woman with mechanical arms wearing a white and black armored bodysuit, holding a gun in a dark, abandoned alley with glowing lights behind her.
Hyperrealistic dark surreal portrait of a figure wearing a shiny black plague doctor mask and an old, high collar cyberpunk samurai jacket with a large linen cape, set against a detailed monochrome spacescape with dark-amber highlights and a crimson gradient background.
Cyberpunk girl wearing a black hood and gas mask with red eyes, mechanical elements on hood, on a yellow background
Close-up of a hyper-realistic cybernetic creature with glowing blue eyes and detailed mechanical armor, showcasing intricate wires, panels, and robotic elements.
A young woman with short black hair and blue eyes, dressed in a black cloak, lying close and caressing a wolf at sunset with windmills and orange-purple clouds in the background.
A monochrome female warrior with a long braided ponytail and red glowing eyes stands among numerous skulls and swords, holding a glowing red sword and wearing red gloves and thigh-highs.
A young doomer girl with short black bob hair and black hoodie walking a black dog on a dirt road during an autumn sunset with orange and purple clouds in an eastern European suburban setting.
Photorealistic depiction of a seductive woman with wolf cut hairstyle, black leather armor adorned with glowing red runes, immersed in swirling liquid metal magic with vivid red accents against a black background.
A realistic albino woman with long white hair and a backless white gown stands in crimson liquid dripping from her hands against a dark background with dramatic lighting.
A dark armored knight clutching a glowing red sword with a cracked and weathered white armor, set against a soft, abstract light background.

Prompts Negativos Recomendados

nsfw, naked, man

Parámetros Recomendados

samplers

Euler

steps

45

cfg

3.5 - 5.5

clip skip

2

resolution

768x1280

vae

fixFP16ErrorsSDXLLowerMemoryUse_v10.safetensors

other models

- iLL - the_edgy_mech_V3.0-step00016000 (29e2fda35d93), 2dn_illustV1 (880d712e87), hassakuXLIllustrious_v13StyleB (5a5b23fadd)

Consejos

Quality depends heavily on the checkpoint used; avoid overtrained checkpoints that produce only high-quality images to prevent disappointing results.

Flux.1 D model generation and training can be slow; patience is needed.

The model uses a combination of natural language and tagged prompts for generation.

Aspectos Destacados de la Versión

  • More Pictures, more training

Well, it does something, that's for sure. A lot of known mecha junk floating in the internet combined with my hardcore Photoshop skills and stuff i've made and rendered in 3D ( the non AI generated and not circulating in the internetz kind of shit )

  • Trained on NoobAI

  • No fucking clue what is considered Illustrious or NoobAI

  • Combination of natural language and tags

  • Good luck

Extremely depending of the checkpoint used, 'cause every checkpoint that isn't overtrained to produce only the most high quality images will most likely make you cry.

Just as i side note. Every model, be it Illustrious, NoobAi or Pony is based on SDXL 1.0. Just because something is trained on a dedicated model doesn't mean it has no influence to a certain degree.


Flux.1 D

Ehrm, i'll give up. Way to much time spend on it and Flux just takes to long in every regard, be it generating or training. The good thing though, was able to change a few settings in Kohya and i hope the weird horizontal "streaks" that my other Flux LoRas produced sometimes are gone.

Maybe someone that is using Flux more often and isn't so out of the loop as i'm has more luck.


v3.0

  • Added few more pictures with a different design i couldn't finish last time. Should be done for now, no more point in doing more.

Anterior
Atomix Flux GGUF - Q8
Siguiente
epiCPhotoGasm - V4 - One 4 All

Detalles del Modelo

Tipo de modelo

LORA

Modelo base

NoobAI

Versión del modelo

NAI - v3.0

Hash del modelo

37b730d950

Discusión

Por favor log in para dejar un comentario.

Imágenes por NAI / Flux1. D - The Edgy Mech - NAI - v3.0

Imágenes con concept

Imágenes con dystopian

Imágenes con industrial

Imágenes con mecha

Imágenes con robot