GDP_PonyXL - v1.0
推薦提示詞
score_9, score_8_up, score_7_up, (score_9:1.1), (score_8:1.1), from side, a woman in a tight black and white striped short sweater dress, glasses, arched back, sexy, light brown hair, dark brown eyes, athletic body, narrow waist, sleeveless, depth of field, classroom, knee up, leaning forward
score_9, score_8_up, score_7_up, (score_9:1.1), (score_8:1.1)
推薦反向提示詞
score_6, score_5, score_4, child, kid, childish, childlike, loli, extra arms, extra limbs, extra hands, muted colors, (monochrome:1.1), (greyscale:1.1), (black and white:1.1), 3d, censored, signature, watermark, username
score_6, score_5, score_4, child, kid, childish, childlike, loli, extra arms, extra limbs, extra hands, disfigured, deformed, muted colors, (monochrome:1.1), (greyscale:1.1), (black and white:1.1), 3d, pony, (worst quality, low quality:1.4), easynegative, asian, FastNegativeV2, rfneg
推薦參數
samplers
steps
cfg
clip skip
resolution
vae
other models
推薦高解析度參數
denoising strength
提示
Consult the descriptions on the three merged models (Godiva, Dr. Pibb PonyXL, Pony FaeTality) to get the best results.
Use negative prompt terms to exclude younger subjects, such as child, kid, childish, childlike, loli.
Including score_ tags in the positive prompt helps improve output quality.
創作者贊助
Real Dream - an amazing model worth checking out.
Zonkey - Realism provides great realism with a bit of a unique flair.
v1.1 更新:
我嘗試通過以不同權重合併更多現實主義模型,為我原本的模型帶來更多現實感。這似乎有點違背原先追求插畫/漫畫風的初衷,但我隨心所欲。這個版本比原版更有效響應 realistic, photorealistic, detailed,但預設仍保持較不現實的外觀。不過,
我仍偏愛 v1.0。
以下是相同種子,相同提示詞的圖片範例,版本標於提示中:
示例貼文 比較兩個版本。


查看範例提示詞,盡情嘗試吧!
加入混合的額外模型包括這些精彩的合併:
Real Dream 本身就是一款驚人的模型,務必查看!
Zonkey - Realism 帶來極佳的現實感,也帶有一點……獨特韻味,別錯過!
以下是混合中包含的其他優秀模型。
描述
我喜歡創作更偏向插畫/漫畫風格,但比標準Pony更現實的圖片。
非常現實的Pony模型似乎對我想創造的風格需要更多提示,我也不想要原版Pony加上十個Lora那樣的樣貌。
所以,我將三個非常棒的Pony模型合併(這比我想像的更簡單,認真說,我在YouTube上花了大約10分鐘學會基本方法)。
這是三個優秀的PonyXL模型的合併:
主要模型是一款卓越的現實主義模型,Godiva。此模型能產生絕佳圖像,請務必查看!
Godiva 接著與酷炫的Dr. Pibb PonyXL 模型合併。我非常喜歡這個檢查點!
之後,再和另一款出色模型Pony 🦄FaeTality.合併。
我強烈建議參考上述三個模型的描述,以獲得最佳效果。
參數
采樣器:Euler A
步數:20 - 30
CFG:5 - 7
VAE:sdxl_vae
Clip Skip:2
提示詞
我注意到Godiva特別偏向描繪比我感興趣對象更年輕的主題。我通常在負面提示詞中加入:
child, kid, childish, childlike, loli, 我會在正面提示詞中加入 score_ 標籤。範例提示詞如下:
score_9, score_8_up, score_7_up, (score_9:1.1), (score_8:1.1),
from side,
a woman in a tight black and white striped short sweater dress, glasses,
arched back, sexy, light brown hair, dark brown eyes, athletic body, narrow waist, sleeveless, depth of field, classroom,
knee up, leaning forward,
Negative prompt:
score_6, score_5, score_4, child, kid, childish, childlike, loli, extra arms, extra limbs, extra hands, muted colors, (monochrome:1.1), (greyscale:1.1), (black and white:1.1), 3d, censored, signature, watermark, username,





