A red-skinned elf woman with short pointed ears and white hair sits in a flirty pose wearing gold Greek-style clothing, holding a ball of fire in her hand under a moonlit autumn night with glowing stars and falling leaves.
Close-up of a blindfolded woman with pale skin wearing a white robe decorated with gold and a gold-decorated veil, standing inside a church with stained glass windows in the background.
A giant brain suspended inside a green stasis tank filled with bubbling water, surrounded by tubes and cables inside a dimly lit military laboratory with scientists observing.
A hyper-realistic portrait of a young person with multicolored hair, golden-orange eyes, orange lipstick, and intricate golden earrings, captured in cinematic lighting.
満月の下、コウモリが飛ぶ幽霊村。馬にまたがる鎌を持った高い姿が不気味な雰囲気を漂わせる。
Stable Diffusionを使用して作成された長い金髪と赤い目の高校の制服を着たAI生成のアニメ少女。
光輪と小さな翼を持ち、ペンタグラムのネックレスをつけた赤い髪の少女が宇宙の背景に立っています。
雨の夜にランタンが輝く樹木に囲まれた邸宅のピクセルアート。
オーバーキャストの空の下、風になびく髪を持つ少女がビーチに立っている。
赤毛の眼鏡をかけた女の子がゲーミングチェアに座っている。
ピクセルアートスタイルで雨の日に大きな窓の後ろにいるオレンジの猫。
茶色の短髪の少女がバルコニーで都市の風景を眺め、朝の光の中でパリの建築を特徴としています。

推奨プロンプト

score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up, rating_safe, source_anime, 1girl

推奨ネガティブプロンプト

realistic,3d

realistic, 3d

推奨パラメータ

samplers

DPM++ 2M Karras

steps

20

cfg

7

resolution

768x1024, 1024x768

other models

Pony_DetailV2.0 (26ab1868ae7b), ponyDiffusionV6XL_v6StartWithThisOne (67ab2fd8ec)

ヒント

Avoid using "realistic" and "3d" negative prompts with V1 to prevent uncanny valley effects.

V2 version functions as expected; report any strange behavior for future updates.

バージョンのハイライト

Trained with the new and improved disentanglement method

much better at preserving the content of the original generation

クリエイタースポンサー

Speaking of training, training models is expensive and I run training on my own private server, if you like what I do, consider supporting the development here!

https://ko-fi.com/yolup

This model changes the level of detail

Detail tweakers aren't new, but here we go anyway. This model increases the number of intricate lines and the complexity of shading, essentially it is a realism LoRA, the higher the weight it is at, the more features will be present in the image with marginal impact on the composition.

Inspiration

I just noticed there wasn't a detail tweaker for Pony Diffusion XL yet and I decided it was prime time to train one. it was quite easy to train and only took about an hour because this is the first and only version I made, if there is an abundance of issues that I haven't recognized thus far, I will make updates, but as it stands it seems pretty good I think.

Donations

Speaking of training, training models is expensive and I run training on my own private server, if you like what I do, consider supporting the development here!

https://ko-fi.com/yolup

Key Benefits

  1. allows the alteration of details on a finely controlled level

  2. far more predictable than just prompting for "detailed" and praying to a deity of your choice

  3. allows for more extreme detail than would be possible with mere prompt weighting

Quirks

I would recommend putting "realistic" and "3d" in the negatives for V1 because V1 has a tendency to make some uncanny valley things at higher weights.

V2 seems to function exactly how I would want it to. if you encounter any strange behavior please let me know.

投稿者

前の画像
Ink Wash Fusion - v3.0
次の画像
DoubleExposure (SDXL+ PONY) - PONY

モデル詳細

モデルタイプ

LORA

ベースモデル

Pony

モデルバージョン

v2.0

モデルハッシュ

8a2e39a88f

作成者

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。

モデルコレクション - Pony Detail Tweaker

「Pony Detail Tweaker - v2.0」による画像

コンセプト画像

ディテール画像