Name: Vivid Color Detail LoRa - SDXL/PDXL/SD1.5
Rating: 5 (781 reviews)
Author: hinablue

We had an outage July 5th where users were not compensated, a fix has gone out.

July 5th Compensation

Krea 2 LoRA training is 50% off, and we're running a Krea 2 Training Contest with 1.8 million Buzz in prizes across four LoRA categories.

⚡ Krea 2 Training Contest + 50% Off Training

<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>

這是一個基於 215c 混合訓練的 Slide Lora，可接受權重為 <code>-1 ~ 1</code> ，請自行斟酌使用。This is a Slider Lora based on 215c hybrid training, the acceptable weight is <code>-1 ~ 1</code> , please use it at your discretion.これは 215c ハイブリッドトレーニングに基づいたLoraです。許容重量は <code>-1 ~ 1</code> です。ご判断でご使用ください。215c 하이브리드 트레이닝을 기반으로 한 로라이며, 허용중량은 <code>-1 ~ 1</code> 이므로 본인의 판단에 따라 사용하시기 바랍니다.

IDidSurgeryAlong_x215c

這是一個基於 225c 混合訓練的 Slide Lora，可接受權重為 <code>-0.7 ~ 1</code> ，請自行斟酌使用。This is a Slider Lora based on 225c hybrid training, the acceptable weight is <code>-0.7 ~ 1</code> , please use it at your discretion.これは 225c ハイブリッドトレーニングに基づいたLoraです。許容重量は <code>-0.7 ~ 1</code> です。ご判断でご使用ください。225c 하이브리드 트레이닝을 기반으로 한 로라이며, 허용중량은 <code>-0.7 ~ 1</code> 이므로 본인의 판단에 따라 사용하시기 바랍니다.

IDidSurgeryAlong_x255c

用於變更畫面彩度的 Lora，可接受的權重範圍為 <code>-1.5</code> ~ <code>1.5</code> 之間。Lora is used to change the color saturation of the image. The acceptable weight range is between <code>-1.5</code> and <code>1.5</code>.Lora は画像の彩度を変更するために使用されます。許容される重みの範囲は <code>-1.5</code> ～ <code>1.5</code> です。Lora 는 이미지의 채도를 변경하는 데 사용됩니다. 허용 가능한 가중치 범위는 <code>-1.5</code> 와 <code>1.5</code> 사이입니다.

colorStylishSlider_v1

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.