models/NAI / Flux1. D - The Edgy Mech - Flux.1 D - v2.0

NAI / Flux1. D - The Edgy Mech - Flux.1 D - v2.0

|
8/7/2025
|
4:17:17 AM
| Discussion|
0
Profile view of a half-robotic woman with blue glowing fibre-optic hair tangled with glowing wires, her face is broken and damaged, set against a dark background.
A cybernetic humanoid robot in a frosty environment with mechanical arms, cybernetic implants, and a glowing red circular eye with white frosted hair-like structures.
Digital painting of a red skeletal humanoid wearing a hooded cloak, featuring a menacing grin and mechanical details set against a dark futuristic background with red and blue lights.
Close-up of a decaying spiky plant head with rust-colored textured bark and sharp metallic spikes, surrounded by numerous dark insects flying against a smooth gray background.
Split image showing Akira Tendo with turquoise hair and an optimistic smile on a bright blue background, and Kanta Higurashi with black hair and a manic smirk holding a molotov on a red background, with cherry blossoms lining a road and a distant dystopian Tokyo skyline at twilight.

Recommended Parameters

samplers

Euler

steps

20 - 25

cfg

1 - 3

resolution

832x1216, 768x1280

other models

- Flux1 De-Distilled - the_edgy_mech_1.0 (c59ba28849a3), flux1CompactCLIPAnd_Flux1DevFp8 (363d9d476a), lyhAnime_korIl01 (2bf2c73654), lyhAnimeFlux_v4NijiFP8 (2abace2516)

Tips

Be aware that the quality heavily depends on the checkpoint used; poorly trained checkpoints may yield disappointing results.

Generation and training with Flux.1 D take a long time; patience is needed.

Flux.1 D is based on SDXL 1.0, so training on specialized models like Illustrious or NoobAI may still have influence from SDXL.

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.

Previous
Close-Up: People of Black (Test) - v2.0
Next
Better Days. [illustrious-XL] [ponyXL] (MERGE) - illu XL v0.1

Model Details

Model type

LORA

Base model

Flux.1 D

Model version

Flux.1 D - v2.0

Model hash

2e22203f8e

Discussion

Please log in to leave a comment.