日本的元旦即为新年,新年到来时,许多日本人会穿着传统的和服去寺庙或神殿,庙殿中的钟敲响108下,意味着每个人在新的一年中都有108个心愿,听钟声还会净化人们的心灵。
庙殿会给每一个来访的人一张白色的纸条,纸条上的话启示你在新的一年中将发生什么样的事,人们看过后会将这些白色纸条挂在庙殿旁边的树上。
由于刚过完元旦,所以现在P站上一大堆新年贺图,所以我今天收集了一波我喜欢的,训练了这个lora。
lora兼容性还可以,建议权重0.8。不需要触发词
推荐的tag:
(masterpiece:1.2),best quality,PIXIV,
这里写你想要的内容
<lora:happy new year_20240102112354-000018:0.8>,
Negative prompt: EasyNegative,badhandsv5-neg,Subtitles,word,
Steps: 32, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 2884139861, Size: 768x512, Model hash: e3cc8bda53, Model: 0.5(含羞草hansv12v2-half) + 0.5(cetusMix_Whalefall2), VAE hash: ab33ad55c6, VAE: YOZORA.vae.pt, Denoising strength: 0.5, Clip skip: 2, Hires upscale: 2, Hires steps: 12, Hires upscaler: R-ESRGAN 4x+, Lora hashes: "happy new year_20240102112354-000018: bda4a91e1f57", TI hashes: "EasyNegative: 66a7279a88dd, badhandsv5-neg: aa7651be154c", Version: v1.6.0-2-g4afaaf8a
大模型我推荐用cetus或者ghost加上YOZORA的vae以达到最佳效果(下方推荐),其他的常见常见二次元模型也均可。
感谢大家的下载使用,如果喜欢的话欢迎关注我,我的bilibili pixiv ID均为chosen鲷,欢迎大家关注我的频道https://space.bilibili.com/3867754?spm_id_from=333.1007.0.0,https://www.pixiv.net/users/40911695 谢谢。
The following content is from Google Translate
New Year's Day in Japan is known as "Gantan" and when it arrives, many Japanese people wear traditional kimono and visit temples or shrines. The bells in the temple are rung 108 times, symbolizing the 108 wishes that each person has for the new year. The sound of the bells also purifies people's hearts.
The temple gives each visitor a white piece of paper with words written on it, indicating what will happen to them in the new year. After reading it, people hang these white papers on trees next to the temple.
Since New Year's Day has just passed, there are a lot of New Year greeting images on P-site, so I collected some that I like today and trained Lora with them.
Lora's compatibility is pretty good, I suggest using a weight of 0.8. No trigger word is required.
Recommended tags:
(masterpiece:1.2), best quality, PIXIV,
Write whatever content you want here.
<lora:happy new year_20240102112354-000018:0.8>, Negative prompt: EasyNegative, badhandsv5-neg, Subtitles, word, Steps: 32, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 2884139861, Size: 768x512, Model hash: e3cc8bda53, Model: 0.5(含羞草hansv12v2-half) + 0.5(cetusMix_Whalefall2), VAE hash: ab33ad55c6, VAE: YOZORA.vae.pt, Denoising strength: 0.5, Clip skip: 2, Hires upscale: 2, Hires steps: 12, Hires upscaler: R-ESRGAN 4x+, Lora hashes: "happy new year_20240102112354-000018: bda4a91e1f57", TI hashes: "EasyNegative: 66a7279a88dd, badhandsv5-neg: aa7651be154c", Version: v1.6.0-2-g4afaaf8a
For the large model, I recommend using cetus or ghost combined with YOZORA's VAE for the best results (recommended below). Other common anime-style models can also be used.
Thank you all for downloading and using it. If you like it, feel free to follow me on Bilibili and Pixiv. My IDs are both chosen鲷. Please check out my channels: https://space.bilibili.com/3867754?spm_id_from=333.1007.0.0, https://www.pixiv.net/users/40911695 Thank you.