VELVIA模型是采用高分辨率训练集以及新的打tag方法训练得到的LoRA模型。
更新内容：
照片训练集进行了重新筛选，不再使用正则化图像
训练集分辨率由512x704提升至640x960
采用了新的打tag方法与金字塔噪声
The VELVIA model is a LoRA model trained using a high-resolution dataset and a new tagging method.
Updates include:
The photo training dataset has been reselected, no longer using regularized images.
The training dataset's resolution has been increased from 512x704 to 640x960.
A new tagging method and pyramid noise has been adopted.
Input
Per image generation will cost 0.0047$
For premium plan image generation will cost 0.00$ i.e Free.
Output
Unknown content type
Related Models
Discover similar models you might be interested in
Lin Yuchun / Hayashi I-Jun - v3.0-ERO
WomenKickingMen - v1.0
Yuuta Kadowaki | Otonari no Tenshi-sama ni Itsunomanika Dame Ningen ni Sareteita Ken / The Angel Nex
Futanari-Style revic - v1re
girl like tangyuan feeding - SD 1.5
BallKickingModel - v1.0
Watermelon Print Bikini | Attire - v1.0
Hajime Aoyagi | Yowamushi Pedal / Yowapeda - sd1-v1.0-second-year
![[Clothing] Hair Bow Variation / - side_of_head-v1.0](https://images.modelslab.com/?Image=https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/68d7f848-bcc8-4bb5-bd6d-18a0751d7206/width=1024/3557748.jpeg)
[Clothing] Hair Bow Variation / - side_of_head-v1.0
Z Image Turbo
Hajime Aoyagi | Yowamushi Pedal / Yowapeda - sd1-v1.0-third-year
Nagi Umino | Kakkou no Iinazuke / A Couple of Cuckoos - sd1-v1.0