Name: Vivid Color Detail LoRa
Rating: 4.98 (322 reviews)
Author: hinablue

sexual situations

physical violence

disturbing

male nudity

extremist

hanging

hate symbols

nazi party

revealing clothes

weapon violence

female swimwear or underwear

male swimwear or underwear

partial nudity

white supremacy

adult toys

graphic male nudity

illustrated explicit nudity

nudity

self injury

graphic violence or gore

graphic female nudity

corpses

wide hips

convenient censoring

peeing

oral invitation

emaciated bodies

exposed female nipple

blowjob

female nudity

suggestive

sexual activity

sexual intent

undressed

male underwear

female swimwear

genitals

female underwear

thick thighs

breasts out

strapless leotard

vore

bestiality

breast out

one breast out

huge breasts

gigantic breasts

huge butt

covered nipples

hair over breasts

no panties

sitting on face

anal

dildo riding

downblouse

oral

porn

futanari

hentai

nude

lingerie

sexy

nsfw

bukkake

cumshot

cumdrip

cum in pussy

cum on face

cum on hair

cum on body

cum on tongue

cum on hands

cum in mouth

cum on pussy

eat_cum

fellatio

implied fellatio

after fellatio

triple fellatio

autofellatio

pov fellatio

fucked silly

presenting ass

presenting pussy

spreading legs

spread legs

swimwear

TRPCError

<h3 id="heading-358">更多訊息請參考每個模型版本內的 About this Version.</h3><h3 id="heading-359">For information about each version of the model, please refer to About this Version for each model version.</h3><h3 id="heading-360">各モデルのバージョンについては、各モデルのバージョンについてを参照してください。</h3><h3 id="heading-361">각 모델 버전에 대한 자세한 내용은 각 모델 버전에 대한 이 버전 정보를 참조하세요.</h3><hr />Support me on Ko-fi <a target="_blank" rel="ugc" href="https://ko-fi.com/hinablue">https://ko-fi.com/hinablue</a>

FujiProPlusII 建議權重：0.3~1.0Recommend Weight: 0.3~1.0 這是使用複印法與分層訓練，利用自己的 FUJI ProPlusII 底片所拍攝的結果進行訓練的 Lora。 This is Lora trained with the results of my own FUJI Pro400H film using the copy method and layered training.

fujiProPlusII_v1.0

VividColorDetail v3.0/V3.0-LCM這是重新訓練過的模型，並且融合 v2.0 的特徵，並針對細節特徵作增強，根據權重強度會影響人體動作、服裝或背景干擾，但是對於臉部的特徵干擾較微弱。建議的權重：真實：0.3 ~ 0.9動漫：0.3 ~ 0.7對於 LCM 版本，採樣器：LCM, DPM++ SDE KarrasCFG: 1.8 ~ 4.0Steps: 6 ~ 16This is a re-trained model and incorporates features from v2.0 with enhancements for detailed features, depending on the weight strengths that affect human movement, clothing or background interference, but less so for facial features.Suggested weights:Realistic: 0.3 ~ 0.9Anime: 0.3 ~ 0.7For LCM version,Sampler: LCM, DPM++ SDE KarrasCFG: 1.8 ~ 4.0Steps: 6 ~ 16これは再トレーニングされたモデルであり、v2.0の特徴を組み込み、人の動き、衣服、背景の干渉に影響する重みの強さに応じて、詳細な特徴を強化しています。推奨される重みリアリスティック: 0.3 ~ 0.9アニメ： 0.3 ~ 0.7LCMバージョンの場合，サンプラー： LCM、DPM++ SDE KarrasCFG: 1.8 ~ 4.0ステップ 6 ~ 16이 모델은 재훈련된 모델이며, 사람의 움직임, 옷 또는 배경 간섭에 영향을 미치는 가중치에 따라 세부적인 특징에 대한 개선 사항과 함께 v2.0의 기능을 통합하지만 얼굴 특징에 대해서는 그렇지 않습니다.권장 가중치:사실적: 0.3 ~ 0.9애니메이션: 0.3 ~ 0.7LCM 버전용,샘플러: LCM, DPM++ SDE KarrasCFG: 1.8 ~ 4.0스텝 6 ~ 16

v3.0-LCM

v3.0

VividColorDetail v2.0這是基於 v1.0 重新訓練過的模型，特性與 v1.0 沒有太大差異，不過增強的強度稍微降低，對於細節的描寫部分略微增強。建議的 weight 在 0.3 ~ 0.7 之間。This is a re-trained model based on v1.0, the characteristics are not too different from v1.0, but the strength of the enhancement is slightly reduced, and the portrayal of details is slightly enhanced.The recommended weight is between 0.3 ~ 0.7.v1.0をベースに再トレーニングしたモデルで、特徴はv1.0とあまり変わらないが、強調の強さが若干弱まり、細部の描写が若干強化されている。推奨ウェイトは0.3～0.7です。v1.0을 기반으로 재 훈련 된 모델로 특성은 v1.0과 크게 다르지 않지만 강화 강도가 약간 감소하고 디테일 묘사가 약간 강화되었습니다.권장 체중은 0.3 ~ 0.7 사이입니다.

v2.0

fujiPro400H 這是使用複印法與分層訓練，利用自己的 FUJI Pro400H 底片所拍攝的結果進行訓練的 Lora。由於訓練結果並沒有加上噪點，僅將畫面風格彩度略微降低，並在處理過程中會略微丟失一點細節。 此 Lora 可以接受負值，他會將整體彩度提高。This is Lora trained with the results of my own FUJI Pro400H film using the copy method and layered training. Since no noise is added to the training results, only the chroma of the picture style is slightly reduced, and a little detail will be slightly lost during the processing.This Lora can accept negative values, and it will increase the overall chroma.

fujiPro400H_v1

VividColorDetail 這是一個實驗中嘗試製作的特製 Lora，用意在於強調光影、皮膚、背景以及動作的細節。 本身權重接受負數，你可以由 -1 到 1 之間調整，當然 0 代表不套用此 Lora。 由於是實驗作品，所以並不保證任何效果，請自行挑選喜歡的模型測試，推薦真實系列模型。 此 Lora 模型可以承受 CFG 最高約 15 左右，可以嘗試看看。 有關於修正動作這件事情，因為這個 Lora 模型是我融合了自己實驗的腿部模型，所以在腿部動作上可以約略修正一些奇怪動作。觸發詞可以使用以下這個關鍵字，來嘗試修正提示詞中的腿部動作。<pre><code>legs_dongpoloha</code></pre>This is a special Lora that I tried to make in an experiment. It is intended to emphasize the details of light and shadow, skin, background and movement. The weight itself accepts negative numbers, you can adjust it from -1 to 1, of course 0 means that this Lora will not be applied.Since it is an experimental work, it does not guarantee any effect. Please choose your favorite model for testing and recommend real series models.This Lora can withstand CFG up to about 15 or so, you can try it out.There is a matter of correcting the movement, because this Lora model is a leg model that I have fused with my own experiments, so some strange movements can be slightly corrected in the leg movement. Trigger words can use the following keyword to try to modify the leg movement in the prompt word.<pre><code>legs_dongpoloha</code></pre>これは、私が実験的に作ってみた特別な Lora である。光と影、肌、背景、動きのディテールを強調するためのものです。ウェイト自体はマイナスの数値を受け付けるので、-1から1まで調整することができる。実験的な作品ですので、効果を保証するものではありません。この Lora はCFG15程度まで耐えることができますので、試してみてください。この Lora モデルは、私自身の実験と融合させた脚のモデルですので、脚の動きに若干のおかしな動きが修正されることがあります。トリガーワードは、以下のキーワードを使って、プロンプトワードの脚の動きを修正してみることができる。<pre><code>legs_dongpoloha</code></pre>이것은 제가 실험에서 만들려고 시도한 특별한 Lora 입니다. 빛과 그림자, 피부, 배경 및 움직임의 세부 사항을 강조하기위한 것입니다.가중치 자체는 음수를 허용하고 -1에서 1까지 조정할 수 있으며, 물론 0은이 Lora 적용되지 않음을 의미합니다.실험적인 작품이므로 효과를 보장하지 않습니다. 테스트는 마음에 드는 모델을 선택해 실제 시리즈 모델을 추천 해 주시고,이 Lora 는 약 15 정도까지 CFG를 견딜 수 있으므로 시험 해보십시오.이 Lora 모델은 제가 직접 실험을 융합 한 다리 모델이기 때문에 다리 움직임에서 약간의 이상한 움직임이 약간 보정 될 수 있기 때문에 움직임을 보정하는 문제가 있습니다. 트리거 단어는 다음 키워드를 사용하여 프롬프트 단어에서 다리 움직임을 수정하려고 시도 할 수 있습니다.<pre><code>legs_dongpoloha</code></pre>

v1.0

Vivid Color Detail LoRa

Type	LoRA
Stats	676 1,147
Reviews	Very Positive (58)
Published	Mar 22, 2024
Base Model	SD 1.5
Training	Steps: 3,000 Epochs: 66
Usage Tips	Clip Skip: 1
Hash	AutoV2 19B200DDC2