The module already has VAE. Unless you have specific coloring requirements, it is recommended to use the VAE inside the module. Currently, personally recommend NoobAI ( 1.7, 1.9, 2.4, 2.8, 3.3) . If the FP32 upload fails multiple times, stop attempting to upload.Buy a Coffee for me☕️
Suggested: Txt2img 720p+ with Hires fix. Upscaler recommended Remacri setting to 1080p+.
Prompt Prefix:
masterpiece,best quality,perfect quality,absurdres,newest,very aesthetic,vibrant colorsNegative Prompt:
shiny skin, shiny clothing, worst quality, low quality, lowres, signature, username, logo, bad hands, mutated hands
V3.0, V2.9 Variant suggested: forge and use latent modifier integrated
Suggested Resources: Eyeful, adetailer, remacri, Face_finder
Simplified instructions for the standard guidelines of NoobAI
Character and artist tags Prompts achieve reliable performance when applied to NOOBAI CSV files with the Danbooru+e621 dataset exceeding 300 images in the official records. ( NoobAI huggingface csv).
The illustrious checkpoint pre-release beta version for testing must be used in accordance with the illustrious XL standard usage guidelines.This illustrious checkpoint is not stable, and the background sometimes disappears
Description
Fine-tune lighting and details.
FAQ
Comments (22)
Really good with the latest version (V1.7) Love using this model now!!! much better than (V1.5)
Loras work very well from the few i tried so far too!
V1.7 is a checkpoint that results from merging 1.5 with a bit of 1.6 and then optimizing it. I'm glad that someone likes it.
个人是比较喜欢1.7版但只有1.5版可以线上生图...除非civitai官方又大规模开放许多检查点线上生图让我的检查点再度挤进前200名，不然感觉1.7版或未来版本光靠下载量与按赞数不太可能在C站挤进前200名让他有生成的功能
How did you get online generation with under 1k downloads and such little exposure?
When the website briefly opened access to all checkpoints (for less than a week), the online image generation count for v1.5 exceeded 20,000, which might meet the platform’s designated threshold. Of course, I’m not an official representative, so I can’t confirm if my assumptions are accurate.
@ok_furry_image
太棒了! 666 很高兴你终于拿到了位置。
你值得拥有！这个模型比原版更好
@ok_furry_image 确保使用新的拍卖 安利!
非常好用！非常感谢！作为第一次使用类似模型的小白，这个模型真的满足了我很多的探索欲！另外想请问下，试过了您的例图，这个模型+lindong的Lora散瞳有什么好的解决方法吗？还是说是机能限制？
我的话是adetailer使用Eyeful或是Face finder来进行重绘，你可以试试看，如果你是线上生图可以试试Image-to-image Face fix，或用eye lora
@ok_furry_image 我这边自己试了好久，也基本解决这个问题啦！非常感谢！加上对pupils的限定词基本解决一大半了！
又可以在线生成了ohhh
使用画师提示词不生效呢？比如(takemoto arashi)生成出的图并没有使用
尝试把权重提高，如果还是觉得不理想你可能要训练他的lora。
我先随便用线上模式生成了一张(看起来需要在修改正负提词或增加一些2D化lora，因为光影不太像)：
https://civitai.com/posts/15529309
@ok_furry_image 谢谢回复，我再尝试一下我之前用的indigoXL画师权重一般只给到1.3左右，看来不同模型可能权重敏感度不太一样呢
@1056306511117 因为我没特别训练单一绘师的画风，是保留NoobAI自带的绘师tag
Абалдеть, какой проработанный рендер пошел. Круто!
Спасибо! Очень рад(а), что тебе понравилось! 😊
(Это переведено с помощью ИИ)
Absolutely love the model, definitely my favorite so far!
He is soooo soooo handsome 😍
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.