https://discord.gg/TajBR2Dqdy is the link to discord, there are two channels, Chinese and English
QQ群：451450868（主群）
929721518备用群
v7 tensor onsite use linkT-illunai3 - v7 | Stable Diffusion Model - Checkpoint | Tensor.Art
v7国内线上出图平台T-illunai3 - v7 | Stable Diffusion Model - Checkpoint | Tensor.Art (tusiart.com)
This is a donation channel Thank you very much for your support！ All the funds will be used to purchase 5090d！Buy Tonade a Coffee. ko-fi.com/tonade - Ko-fi ❤️ Where creators get support from fans through donations, memberships, shop sales and more! The original 'Buy Me a Coffee' Page.
Tonade正在创作T-ponynai3模型作者，c站id：Tonade，现在是T-illunai3作者 | 爱发电 (ifdian.net) 这是国内爱发电的链接，感谢捐赠支持！
NOOB 1.0版本 1000 单画师测试不可修改版 (qq.com)
可直接对照参考的画师提示词文档，可在illu系模型上完美使用，包括illunai-v7
NOOB 1.0版本 1000 单画师测试不可修改版 (qq.com)It can be directly compared with the reference artist's prompt word document and can be perfectly used on Illu models, including illunai-v7
v6推荐使用的提示词（懒人版）
Recommended prompt words for v6（Lazy version）
POSITIVE：best quality,amazing quality,very
aesthetic,absurdres,masterpiece,
NEGATIVE：bad feet,missing toes,extra toes,lowres,bad anatomy,bad hands,text,error,missing fingers,extra digit,fewer digits,cropped,worst quality,low quality,normal quality,jpeg artifacts,signature,watermark,username,blurry,4-koma,sketch,(bad:1.05),error,fewer,extra,missing,worst quality,jpeg artifacts,bad quality,watermark,unfinished,displeasing,chromatic aberration,signature,extra digits,artistic error,username,scan,abstract,(blurry, lowres, low quality:1.1),ugly,(big head, bad anatomy:1.05),artist name,(watermark:1.1),
v1只是一个初步进行微调的版本，但是效果好的惊人。在动漫绘画的领域比pony的微调效果要好上不少，肢体的正确率也十分可观。希望各位能多多测试一下这个微调。
基于illustrious-xl Illustrious-XL - v0.1 | Stable Diffusion XL Checkpoint | Civitai
V1 just a preliminary version with fine-tuning, but the results are surprisingly good. In the field of anime painting, the fine-tuning effect is much better than Pony's, and the accuracy of body movements is also considerable. I hope everyone can test this fine-tuning and give some comments about it.
base on illustrious-xl Illustrious-XL - v0.1 | Stable Diffusion XL Checkpoint | Civitai
训练须知：
v1版本使用了100张经过筛选的高质量的使用nai3生成的图片，以及画风相近的一些公开素材作为姿势的补充，训练使用了prodigy算法进行训练。illustrious模型的女性素材很多，导致了模型会比较难以生成男性的图像，而且某些时候需要一些比较复杂的提示词才能生成目标图像，这将在之后的更多训练集的版本尝试进行一些改善。
Training instructions:
The v1 version used 100 high-quality images generated using Nai3 that had been filtered, as well as some publicly available materials with similar art styles as pose supplements. The training was conducted using the "prodigy" to train. The illustrious model has a lot of female materials, which makes it difficult for the model to generate male images, and sometimes requires some complex prompt words to generate target images. This will be improved in more training set versions in the future.
在v4中，我使用了600张由nai3生成的风格图片作为默认画风的训练，这一步是基于illustrious模型的，然后我用模型融合的方法在这一fine-tuning后的模型上加入了一些noob的模型成分，以来平衡illu的一些缺失的语义和识别prompt的能力。
In v4, I used 600 style images generated by nai3 as the default art style for training. This step was based on the illustrious model, and then I added some noob model components to this fine tuned model using model fusion to balance some of Illu's missing semantics and prompt recognition ability.
v6这个版本的模型进行了更好的画风调教，改善了大量的基于ntrv4的错误肢体和过拟合的画风，并调整了过细的线条，让整体的线条和效果更好，甚至配合画师提示词使用已经足以媲美nai3，在某些画面构图上已经超越了nai3
推荐使用的提示词都在例图里面，总体来说ntr模型系列的提示词都可以直接使用，这将是一个新的开始，往后会不断强化这个版本
This version v6 of the model has undergone better art style tuning, improving a large number of erroneous limbs and overfitting styles based on ntrv4, and adjusting overly fine lines to make the overall lines and effects better. Even when used in conjunction with artist prompts, it is already comparable to nai3 and has surpassed nai3 in some picture compositions、
The recommended prompt words are all in the example image. Overall, the prompt words of the ntr model series can be directly used, which will be a new beginning and will be continuously strengthened in the future
推荐使用质量词Recommend quality words
正面提示词
best quality,amazing quality,very aesthetic,absurdres,beast quality,masterpiece,artist:xxx
负面提示词
lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry,4-koma, sketch, (bad:1.05), error, fewer, extra, missing, worst quality, jpeg artifacts, bad quality, watermark, unfinished, displeasing, chromatic aberration, signature, extra digits, artistic error, username, scan, abstract, (blurry, lowres, low quality:1.1), ugly, (big head, bad anatomy:1.05), artist name, (watermark:1.1)
Recommend using quality words
Positive prompt words
best quality,amazing quality,very aesthetic,absurdres,masterpiece,artist:xxx
Negative prompt words
lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry,4-koma, sketch, (bad:1.05), error, fewer, extra, missing, worst quality, jpeg artifacts, bad quality, watermark, unfinished, displeasing, chromatic aberration, signature, extra digits, artistic error, username, scan, abstract, (blurry, lowres, low quality:1.1), ugly, (big head, bad anatomy:1.05), artist name, (watermark:1.1)
在线生成网址 online generation link: (340) T-illunai3 - v4 | Stable Diffusion Model - Checkpoint | Tensor.Art (tusiart.com)
ps: For some unknown reasons, my model cannot run online on Civitai, even after multiple applications, it is useless. Therefore, I uploaded it to this platform synchronously, and online generation of the model can also be done on it
出于一些未知的原因，我的模型无法在civitai上在线运行，即使多次申请都无济于事，所以我同步上传了这个平台，在上面同样可以进行该模型的在线生成
Description
这个版本是应评论区提出的nai3画风不足的问题，进行了权重重新调整的版本，这个版本将会更加贴近tpony自带的画风，在我的测试下，这个模型的构图冲击力会相比v6有所下降，但是线条会更加的圆润，基础画风也会更加贴近tpony，无需更多的画风提示词便能出较好的画风
This version addresses the issue of insufficient Nai3 art style raised in the comments section and has undergone weight adjustments. It will be more in line with the original art style of tpony. In my testing, the composition impact of this model will be reduced compared to v6, but the lines will be more rounded and the basic art style will be closer to tpony. There is no need for more art style prompts to produce a better art style
FAQ
Comments (20)
我加了手脚相关的lora和负面词，任然会生成多指多手
有点爱出水印，希望能改进一下
ngl i feel like v6 is a bit of a downgrade. v4 had this unique soft style that i adored, but v6 feels like any other model these days in terms of style.
Yes, this is due to the insufficient art style caused by my desire to preserve the composition of ntrv4. I will release a higher weighted version today
我非常感谢你对这个检查点的持续更新。你的 t-___nai3 系列是我最喜欢使用的检查点之一。
话虽如此，我觉得 t-illunai3 v6 牺牲了许多我喜欢 v4 以及你之前的 Pony 版本的特点。输出的风格发生了很大的变化，而风格正是我最看重的部分，也是我最喜欢这些模型的原因之一。我特别喜欢 t-illunai3 v4，因为它保持了一个与 t-ponynai3 v6.5 十分相似的风格偏向，而且不需要大量使用艺术家标签提示等方法。
此外，我注意到 v6 在物品的稳定性方面有所下降。尤其是那些长武器（比如跨越角色身后的武器）比在 v4 中更容易出现错误。
我仍然希望未来能有一个不包含 NoobAI 的版本的 t-____nai 系列模型，比如基于 RouWei 或 AkashicPulse 的后续版本。同样，我也有些遗憾地发现，你最近发布的 t-ntrnai3 似乎比之前的检查点对使用场景的限制更大了。
再次感谢你的辛勤工作和对用户反馈的考虑！
---
I appreciate your continued work on this checkpoint. Your t-___nai3 series are my favorite checkpoints to work with by far.
That said, t-illunai3 v6 compromises a lot of what I love about v4 and also your previous Pony version. The style of outputs is substantially changed which is my primary complaint which is the primary draw for me. I really liked that t-illunai3 v4 kept a style bias very similar to t-ponynai3 v6.5 without heavy artist tag prompting etc.
In addition, I've found that the stability of held items is compromised in v6. In particular, long weapons that cross behind the character have more errors than with v4.
I'm still hopeful that we will get a NoobAI free version of the t-____nai series of models like one based on RouWei or AkashicPulse downstream of it. Along the same lines, I'm a little disheartened that your recent t-ntrnai3 places greater restrictions on use cases as well compared to previous checkpoints from you.
Thank you again for your hard work and consideration.
Thank you very much for your reply. This version is mainly aimed at finding a balance point that can integrate the composition of ntrv4 and the art style of tpony. However, it seems that this balance point is too low, resulting in insufficient original art style of tpony. I will release a more closely related art style version today. Thank you very much for your long reply
@Tonade It's out of respect for you and your work that I write detailed feedback! <3
could you release your dataset? i'm interested in testing it out with other models
最新几个版本还是不太能出男生的样子，请问可以加些男生训练数据咩谢谢！
可以生成男孩子哦，权重稍微高一点就行，详见例图Image posted by Tonade (civitai.com)
@Tonade 好嘞我试试提高权重！
Holy crap; I haven't been keeping up with toon models much over the last few months but this is superb quality. Amazingly coherent, good comprehension, good adherence. Wtf? Damn. Well done.
Give RouWei a try, its immensely flexible without the negative prompt wordsoup requirement. It also has excellent style control.
两倍SD1.5，20亿样本优势虽然不能和FLUX120亿相比，但素材训练已经非常好了。