Diffus
始める
モデル/Chroma - Random Illustration/Anime Mashup - v1.0

Chroma - Random Illustration/Anime Mashup - v1.0

TijuanaSlumlord
|
9/16/2025
|
10:34:43 PM
| Discussion|
0
A towering rocky cliff brightly colored with vibrant orange, red, and purple hues, topped by a small dark steampunk-style ship emitting smoke. Sparse twisted trees grow on the cliff with misty fog at the base, surrounded by reflective water and distant forested mountains under a soft gradient blue-white sky.
A sepia-toned monochromatic image featuring a large cracked circular structure with web-like patterns suspended above a narrow platform where a small solitary figure stands, highlighting scale and fragility.
A digital portrait of a young woman with teal braids and blue eyes, portrayed with oil painting textures and a distressed teal background.
A male cyberpunk cyborg character wearing a tattered orange hooded cloak and a red scarf stands in a neon-lit futuristic cityscape, featuring a mechanical left arm, glowing orange eye, and a large backpack with tubes.
Digital painting of a narrow urban alleyway viewed from a low angle featuring old weathered buildings with moss and vines, bright blue sky with fluffy clouds, colorful signs including a prominent orange 'CURRY' sign, and a large steel bridge spanning the alley in the distance.
Illustration of a black cat mid-jump with an angry expression, wide eyes, and open mouth showing sharp teeth, and a white cat on the ground looking up surprised with blue eyes, all against a beige background.

推奨ネガティブプロンプト

low quality

推奨パラメータ

samplers

DPM++ 2M_sgm_uniform

steps

20

cfg

3.5

clip skip

1

vae

ae_flux.safetensors

other models

Chroma_Flux1_S_Base\Chroma1-HD.safetensors (d446d9695d)

ヒント

Use the last part of prompts or interchange parts to let the model introduce randomness and creativity.

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
Real Dream - SDXL Pony 16
次の画像
not HL's AI slop styles [experimental garbage] - PSAIX
このモデルを使用

モデル詳細

モデルタイプ

LORA

ベースモデル

Other

モデルバージョン

v1.0

モデルハッシュ

13adf8d660

作成者

TijuanaSlumlord's avatar
TijuanaSlumlord

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 - v1.0」による画像

イラスト画像

スタイル画像