Night Sky YOZORA Model ——“For ultimate image quality and large image size（>1536 x 1024）”

add Prompt plz，thanks

Would be really cool if you could add more examples with prompts :3

No advantages other than the largest size

This is a great model but also really big in filesize. I'd like to see a LORA 320 without VAE, for greater flexibility.

how to solve CUDA out of memory problem when generating with high resolution 1280+

请问有什么推荐的vae吗？裁剪后的版本集成了vae，那么在webui的设置里面，是要把vae选项设置成【无】吗

did you merge Yoneyama Mai LoRA to this?

求一个米山舞lora的基础sd模型，可以出钱，q3406167979

Hello, very good. Your model wanted to know how you do it. Do you have a link where you learned from? Thank you very much.

Why are all the images I load coming out pixelated?

amazing!

it's hard to use

我在本地部署的sd内，选项一切换至这个模型，浏览器就报错，同时软件本体闪退，有大佬能救一救吗

有没有大佬帮忙看看为啥一直报错阿

NansException: A tensor with all NaNs was produced in Unet. This could be either because there's not enough precision to represent the picture, or because your video card does not support half type. Try setting the "Upcast cross attention layer to float32" option in Settings > Stable Diffusion or using the --no-half commandline argument to fix this. Use --disable-nan-check commandline argument to disable this check.

how much clip skip should I use

为什么我图片稍微一开大点就直接炸了？详情可以看看我下面发的图

大大的关键词真的绝了！！！ai菩萨！！！

为什么下载的模型文件用不了，显示文件名14459，文件类型是.File，已经放在modles\stable diffusion里了

过于绚丽，身上长衣渲染成乞丐装，撕得一条条。XD

woc大佬

vae文件放在models\Stable-diffusion 或models\vae 文件夹都可以吗？跑图能不能不手动选择这个vae，不然换几次模型可能就忘了哪个对应哪个了

太难跑了，12g显存稍微开高一点就爆显存，分辨率低了又很模糊，

大佬有没有国内的平台账号或者粉丝群呀？想请教一些模型使用的方法 太喜欢模型的画风了 但是无人讨论（哭）

origin pruned 差别大吗？8 千兆字节.... 我的硬盘要哭了 😂

CLIP有错误，要修复才行

nightSkyYOZORAStyle_yozoraV1PurnedFp16.safetensors

Hashes:

AUTOV2: 4b118b2d1b

AUTOV1: 94245290

tensor([[ 0, 0, 1, 2, 3, 5, 5, 6, 7, 9, 10, 10, 11, 12, 13, 15, 15, 16, 18, 18, 20, 20, 21, 22, 23, 25, 25, 26, 27, 28, 30, 31, 31, 32, 33, 35, 36, 36, 37, 38, 40, 40, 41, 42, 43, 45, 45, 46, 47, 48, 50, 50, 51, 52, 53, 55, 55, 57, 57, 58, 60, 60, 62, 62, 63, 64, 65, 67, 67, 68, 70, 70, 72, 72, 73, 75, 75]])

Type: torch.int64

Wrong CLIP indexes: [1, 2, 3, 4, 6, 7, 8, 11, 12, 13, 14, 16, 17, 19, 21, 22, 23, 24, 26, 27, 28, 29, 32, 33, 34, 37, 38, 39, 41, 42, 43, 44, 46, 47, 48, 49, 51, 52, 53, 54, 56, 58, 59, 61, 63, 64, 65, 66, 68, 69, 71, 73, 74, 76]

It is recommended to fix this checkpoint.

What a gorgeous original style! Just a delight for the eyes! Wonderful, thanks!