モデル/Chroma - Random Illustration/Anime Mashup - v2.0

Chroma - Random Illustration/Anime Mashup - v2.0

|
10/10/2025
|
9:56:20 AM
| Discussion|
0
Close-up profile of a woman with long flowing hair wearing round reflective sunglasses showing vibrant multicolored reflections, set against a grayscale face and colorful floral background in Retro 80s Vaporwave style.
A massive rusted spacecraft stands partially buried in a rocky desert landscape under a hazy orange sky with subtle lens flares, depicted in a Retro 80s Vaporwave style.
Close-up of a female kurobot cyborg wearing a ceremonial kimono armor decorated with golden mosaic patterns and geometric motifs, featuring a translucent, glitching faceplate and a dark-turquoise hood with gilded spirals against a golden fractal background.
Whimsical steampunk village with steep gabled wooden buildings and mechanical gears, shown in wide curved perspective from a fisheye lens viewpoint.
Solitary figure standing near a large pile of ashes with a massive sun setting in the background, creating a melancholic and minimalist atmosphere.

推奨パラメータ

samplers

DPM++ 2M_sgm_uniform, DPM++ 2M_beta

steps

20 - 25

cfg

3 - 3.5

clip skip

1

vae

ae_flux.safetensors

other models

Chroma_Flux1_S_Base\Chroma1-HD.safetensors (d446d9695d)

ヒント

Using partial or interchanged prompts can allow the model to creatively fill gaps and produce random variations.

バージョンのハイライト

More pics

Got bored while training and preparing more demanding models. Went through all my training images, trying to match pictures with the same theme but always realistic, illustration, anime and general colorful high resolution stuff.

Went to work and forgot to switch to another model that takes longer, now this one is pretty overtrained and i set it so it overrides the previous lora.

In some cases i just used the last part of the prompts or intechanged them with each other to let Chroma take the wheel, fill the gaps and to create a bit of randomness.

Pretty sure will find some use for it here and there.

前の画像
Vanillaware Style PonyXL - v0.1
次の画像
Hyper Detailed Illustration - v1.0

モデル詳細

モデルタイプ

LORA

ベースモデル

Chroma

モデルバージョン

v2.0

モデルハッシュ

5e56bc8b3e

ディスカッション

コメントを残すには log in してください。

「Chroma - Random Illustration/Anime Mashup - v2.0」による画像

クロマ画像

イラスト画像

スタイル画像