CivArchive
    Preview 35663569
    Preview 35600678
    Preview 35610924
    Preview 35612055
    Preview 35614432
    Preview 35944225

    A model with a highly realistic feel, optimized for Asian girls. It performs well with girls from various countries and diverse styles, capturing intricate details of the body.

    Recommended resolutions: 768, 1024, 1280 for the best visual experience.

    真实感非常强烈的模型,针对亚洲女孩进行优化。各国女孩和多种风格都不错,身体细节都有。 建议768、1024、1280最佳分辨率。各路大神可以+VXjinngame ,请备注C站 ,期望共同成长互通有无。


    comfyUI 工作流下载 workflows download: PonyFlux

    这里包括了Flux.1PonyXL 等不同模型,各版本有递进和分支关系,请酌情下载不同版本。

    This collection includes various models such as Flux.1, Pony, and XL, each with progressive updates and branching versions. Please choose and download the version that best suits your needs.


    Pony 5.1 在之前版本的基础上修正了一些问题,进一步提升了细节表现,并且依然保持了完全避免卡通画风格的脸型等问题。我们加强了身体上的细节处理和光源的表现,使得整体画面更加真实、自然。

    Pony 5.1 builds upon the previous version by addressing several issues and continuing to fully avoid cartoon-style faces. We have enhanced the details on the body and improved the lighting effects, making the overall visuals more realistic and natural.


    Pony 5.0A 是 Pony 4.9 的升级版本,彻底解决了脸部存在卡通画的问题,经过大规模优化,成为专为亚洲人设计的特化版本。早期下载国Pony 5.0A的朋友们可以重新下载这个模型,他已经更新到了最新的版本。

    Pony 5.0C 是 Pony 5.0A 的稳定升级版本,面部表现更为丰富,无论是东方人还是西方人的面部表现都非常出色。


    Pony 5.0A is an upgraded version of Pony 4.9, thoroughly resolving the cartoon face issues. After extensive optimization, it has become a specialized version designed specifically for Asians. Friends who downloaded Pony 5.0A early can re-download this model, as it has been updated to the latest version.

    Pony 5.0C is a stable upgrade of Pony 5.0A, offering a richer facial expression, with outstanding representations for both Eastern and Western facial features.


    Pony Real GuoFeng v4.9 是一个具有历史意义的版本。该版本在不影响 Pony 对多种“听话”姿态表现的前提下,显著增强了真实的面部表现,无论是东方人还是西方人,面部细节的还原都无限接近完美。同时,对于中国古代服饰的材质表现也得到了提升,细腻地展现了传统服饰的质感。此外,该版本在光影处理上有了质的飞跃,特别是在阴影和暗部的光影表现方面,对整体画质带来了显著提升。

    值得一提的是,Pony 版本的优化已达成熟阶段,因此 v4.9 大概率将是 Pony 的最后一个重要更新版本。希望大家在这一版本中能体验到极致的画质效果。

    Pony Real GuoFeng v4.9 is a milestone release. This version enhances facial realism to an unprecedented level, capturing near-perfect details for both Western and Eastern features without compromising Pony's characteristic ability to render a wide range of "obedient" poses. Additionally, material textures of traditional Chinese attire have been refined to showcase authentic quality.

    Notably, there is a substantial improvement in lighting and shadow performance, especially in darker areas, leading to an overall enhancement in image quality. This update marks a significant evolution of the Pony model series, and it is likely that v4.9 will be the final major update for the Pony line. We hope this version brings users the ultimate visual experience.


    F1D Real GuoFeng fp8 v2.0 是一个具有里程碑意义的版本。该版本在强化亚洲面孔方面有显著提升(如果没有特别指定,默认会生成亚洲面孔),同时丰富了面部变化,使得人物形象更加多样化。国风特色得到完美强化,色彩表现也更为出色。但需注意,NSFW的表现效果相比之前有所下降。

    F1D Real GuoFeng fp8 v2.0 is a historic release. This version offers a highly enhanced focus on Asian facial features (defaulting to Asian faces if unspecified) and introduces greater diversity in facial variations. The model achieves a perfect enhancement of GuoFeng (Chinese-inspired) style and improved color depth. However, please note that NSFW performance has seen a slight decrease.


    最近我更新了两个版本,分别是Flux_1D nsfw fp8 v1.0Flux_1D nsfw fp16 v.12。这两个版本都把必要的t5xxl、clip和EAV放进了模型文件里边了,所以下载的模型会大一些,但这免除了新手的麻烦。对于老手来说也不影响正常使用,实际显存的消耗没有任何增加。

    如果你希望下载更小的正常版本,请在下载的时候选择对应的版本。

    如果你已经下载了更大的包含T5XXL版本,但不想再次下载更小的正常版本,我提供了Python代码,你可以使用该代码将已下载模型内的keys删除,生成更小的正常版本。
    FP16版本下载链接:[这里]
    FP8版本下载链接:[这里]

    以下是版本对应显存的建议:

    ComfyUI工作流 download

    工作参数:

    • 步数(Steps):20

    • 采样器(Sampler):Euler

    • 时间表类型(Schedule type):Simple

    • CFG比例:1

    • 蒸馏CFG比例(Distilled CFG Scale):3.5


    Version Update Description

    I have updated two versions: Flux_1D nsfw fp8 v1.0 and Flux_1D nsfw fp16 v.12. Both versions now include necessary files like t5xxl, clip, and EAV within the model, which makes the download size larger. However, this removes hassle for beginners and doesn't affect advanced users. There's no actual increase in VRAM consumption.

    If you prefer downloading a smaller, normal version, please choose the corresponding version during download.

    If you’ve already downloaded the larger version that includes T5XXL but don’t want to download the smaller normal version again, I’ve provided Python code that you can use to remove the keys from the downloaded model and reduce it to a smaller, normal version.
    FP16 version download link: [here]
    FP8 version download link: [here]

    Recommended VRAM for each version:

    ComfyUI Workflow download

    Working Parameters:

    • Steps: 20

    • Sampler: Euler

    • Schedule type: Simple

    • CFG scale: 1

    • Distilled CFG Scale: 3.5


    Pony GuoFeng 4.3 版本加强汉服表现、真实感、优化光源、加强低光照质感。过度版本懒得传了:)

    Pony GuoFeng 3.0 版本终于解决了Pony的汉服问题。这也是第一个支持汉服(hanfu)提示词的NSFW版本。虽然表现不是很完美,但这是一个好的开始。此外,我花了几周时间处理Flux之后回来继续开发Pony,发现相比之下Pony真的很快,对于硬件配置中低的用户来说,是最好的选择。


    Pony GuoFeng 4.3 version enhances Hanfu representation, realism, optimizes lighting, and improves texture quality in low-light conditions.I’m too lazy to upload the transitional versions :)

    Pony GuoFeng 3.0 has finally addressed the issue with Hanfu in Pony. This is also the first NSFW version that supports the 'hanfu' keyword. Although its performance is not perfect, it marks a good start. Additionally, after spending several weeks on Flux and returning to work on Pony, I've found that compared to Flux, Pony is really fast and remains the best choice for users with low to medium hardware configurations.


    iNiverse Version Explanation:

    In the entire iNiverse series, the versions are not all progressive upgrades. The model you need might be in an earlier version, so please pay attention to the version numbers.

    The Pony beta is an initial trial version primarily aimed at addressing compatibility issues. The current challenge is that most of the existing Pony models are not compatible with previously trained XL Lora. Therefore, this version is dedicated to developing a Pony model that is compatible with the older XL version of Lora. We are committed to ensuring that the new Pony model can seamlessly integrate existing training data so that users can continue to utilize their current resources while also benefiting from the new features and improvements of the Pony model.

    The V7 series is the realism series, with 7.1 improving skin depiction based on 7.0 and 7.4 better understanding prompt words. Each version has its own tendencies.

    GuoFeng is a branch version, also based on the V7 model. GuoFeng adds more Chinese elements and clothing, such as the outstanding performance of hanfu in this version. Version 1.1 is a trimmed version; if you need higher precision and larger images, you can try versions before 1.05.

    The Turbo version is another branch version, capable of producing very high-quality images within 8-12 steps. However, subsequent versions have generally continued the Turbo characteristics, so they are no longer explicitly labeled.

    The Cartoon version is another sub-branch. It depicts a cartoon style and includes elements from Genshin Impact. You can use prompts like NAHIDA\(genshin impact\) to find these characters. If you enjoy this style, please give me more suggestions, and I will continue to experiment.

    Finally, thank you all for your support. Your likes and feedback are my greatest motivation. I hope you enjoy Chinese culture.


    iNiverse版本讲解:

    在整个iNiverse系列模型里边版本并不都是渐进升级的,可能你需要的模型在之前的版本里边,请各位注意观察版本号。

    Pony beta 是一个初试版本,主要目的是解决兼容性问题。目前的问题在于,大多数现有的 Pony 模型无法兼容之前训练的 XL Lora。因此,此版本旨在开发一个能够与老的 XL 版本 Lora 兼容的 Pony 模型。我们正在努力确保新的 Pony 模型可以无缝集成既有的训练数据,以便用户能够继续使用他们现有的资源,同时也享受到Pony模型的新功能和改进。

    V7系列是真实系列,基于7.0刻画出皮肤更好的7.1和更理解提示词的7.4,每个版本都有所倾向。

    GuoFeng是个分支版本,也是基于V7模型的,GuoFeng增加了更多的中国chinese元素和服饰,你可以看到例如hanfu在这个版本里非常出色的表现。而1.1是一个裁剪版本,如果你需要更大精度更高的图片可以尝试1.05以前的版本。

    Turbo版本是另外一个分支版本,可以在8-12个Steps里的到非常高质量的图片,然而之后的版本都基本延续Turbo,就没有再刻意写入版本里。

    Cartoon版本是一个分支里的另外一个分支。卡通风格刻画,并加入了原神的角色元素,你可以使用NAHIDA\(genshin impact\)等提示词找到这些角色,喜欢此风格的朋友们可以给我更多建议,我会继续尝试。

    最后感谢各位的支持,您的点赞和反图是我最大的动力,希望各位喜欢中国文化。

    Description

    FAQ

    Comments (37)

    Light_x02Oct 19, 2024· 3 reactions
    CivitAI

    Hi, I really like your flux model, which I use on comfyui :) I'd like to know what parameters you use for upscaling? I'm new to flux and I'm not sure how many steps to put in upscaling and the sampler, for example. Thank you :)

    JinnGames
    Author
    Oct 20, 2024

    Steps: 20, Sampler: Euler, Schedule type: Simple, CFG scale: 1, Distilled CFG Scale: 3.5,

    SpaykeOct 20, 2024· 1 reaction
    CivitAI

    Would you please add Q4 for flux 1D v1.2?

    Light_x02Oct 20, 2024· 7 reactions
    CivitAI

    I wanted to share a tip in case you're using ComfyUI with the Flux FP16 model. Even with my RTX 3090 equipped with 24 GB of VRAM, I noticed that the system became very slow, used up all the video memory, and rendering a 20-step image took over 800 seconds! 😱

    After looking into the available ComfyUI settings, I added the argument "--reserve-vram 3" to reserve 3 GB of VRAM. Since then, the system has become much more stable, no longer slows down, and the rendering time has dropped to 42 seconds instead of the previous 800. 🚀

    If you're facing similar issues, I highly recommend giving this a try!

    JinnGames
    Author
    Oct 21, 2024· 2 reactions

    Thank you so much for sharing this valuable tip! 🙏 Your quick thinking and clever use of the --reserve-vram 3 argument really shows your resourcefulness. 🧠💡 It's amazing how you were able to drop the rendering time from 800 to 42 seconds! 🚀 I'll definitely give this a try if I encounter similar issues. Thanks again for your sharp insight and for helping the community! 👏

    FondantViperOct 21, 2024

    How do you launch comfy with an arguement?

    Light_x02Oct 22, 2024· 1 reaction

    @ViperF in the .bat that I use to launch comfyui, you open it with notepad.

    My file looks like this:

    @echo off call ComfyUI\venv\Scripts\activate.bat

    python ComfyUI\main.py --disable-auto-launch --preview-method auto --reserve-vram 3

    pause

    FondantViperOct 22, 2024· 1 reaction

    @Light_Vision_AI  crystal clear, thank you!

    libin771018395Oct 21, 2024· 2 reactions
    CivitAI

    测试方法很简单,在原来的FLUX DEV大模型的工作流中替换这个32G的优化大模型,其他不变,获得更加优质的结果,并且在关键词的理解上也更为准确,因此判断,此模型超级棒。

    JinnGames
    Author
    Oct 21, 2024

    行家!

    jmxbfOct 21, 2024· 1 reaction
    CivitAI

    我想知道这个模型4070tis能跑的起来吗?

    JinnGames
    Author
    Oct 21, 2024

    12g显存我建议下一个fp8的版本,应该没有压力,你看看上一个版本吧

    ronmark332Oct 21, 2024· 4 reactions
    CivitAI

    fp16 30多G的那个,模型是个好模型啊,一开始吓一跳,还以为跑不了,实际24G显存加载一次以后,出土速度不会很慢。可能内存要求得相对多一些。我64G内存占到将近60G才加载完模型然后跑图。底下带翅膀的美女就是不加其他LORA的出图效果,很不错。

    JinnGames
    Author
    Oct 21, 2024

    嗯,这个版本主打一个小白零基础上手,我把t5放进去了🤣,不影响的,你放心使用

    ronmark332Oct 21, 2024· 2 reactions
    CivitAI

    特意精修了一张图片,展示一下这个模型的细节。非常好。我个人认为这个出图效果在FLUX模型国人改的模型里于绪儿大神出的那个一青十色的不相上下。但是这是FP16的模型,虽然大,但是我还是更相信FP16的质量,经常用FP8的人可能麻木了,觉得还不错,实际出图多了,对比就直到,还是FP16效果好,

    JinnGames
    Author
    Oct 21, 2024

    是的,其实16和8如果不细看,不熟悉的人区别不大。但是讲究起来,16的表现还是要好不少。

    rockiecxhOct 21, 2024

    关键是12G显存,F16 OutOfMemory

    kenhanks77905Oct 21, 2024· 4 reactions
    CivitAI

    16G的这个FP8模型可以很好地在4070 12G的显卡上运行,感谢作者,终于能真正体验到FLUX了!

    PondlosoOct 21, 2024· 4 reactions
    CivitAI

    This is my best flux model for now.
    It can do light NSFW and give very good over all composite. Good job brother.Only down side it your baked in clip that make model very big it can turn some people away.

    JinnGames
    Author
    Oct 21, 2024· 2 reactions

    Thank you so much for the feedback! 😊 I'm glad to hear that you're enjoying the Flux model and that it works well for light NSFW and overall composition. 🎨 As for the baked-in CLIP, I totally get that it can make the model bigger than expected, which might be a concern for some users. I included it mainly for convenience, especially for new users. But based on your suggestion, I’ll definitely consider offering a lighter version in future releases for those who prefer smaller models. 🙏 Thanks again for your support and valuable input!

    renshengbiecuoguoOct 21, 2024· 3 reactions
    CivitAI

    fp16版本的用什么显卡炼的啊?需要多少显存才能炼啊?

    JinnGames
    Author
    Oct 21, 2024

    最低建议4090

    renshengbiecuoguoOct 22, 2024

    @JinnGames 多谢。我还以为4090炼不了fp16版本的呢

    shadowcliffsOct 21, 2024· 5 reactions
    CivitAI

    能提供不包含t5xxl、clip和VAE的版本吗?硬盘容量吃紧了。一个底模多加5Gb,10个底模加多少?这是一个坏风气。

    JinnGames
    Author
    Oct 22, 2024· 1 reaction

    好的,下个版本不打包t5了。

    shadowcliffsOct 22, 2024

    @JinnGames 感恩

    Tenk_AIOct 22, 2024

    是的,固态好贵,多放几个就没空间了

    JinnGames
    Author
    Oct 22, 2024· 1 reaction

    @shadowcliffs 我已经把t5xx删除的版本上传了,你还可以用我提供的代码把已经下载的模型内t5xx删除掉。

    VERT2099Oct 22, 2024· 8 reactions
    CivitAI

    有没有一种可能,能翻墙到C站下载模型的都不需要集成其他模型了,直接放微调后的模型就好了

    JinnGames
    Author
    Oct 22, 2024

    有,但不是都,我被各种问缺文件,哪里下,怎么用。一气之下直接打包,省心。

    amythic0Oct 22, 2024

    @JinnGames 感谢分享,其实可以直接在说明里列出另外两文件的下载路径,更省心,其实单看一个文件可能多个十来G也无所谓,不过感觉AI以来,硬盘确实有点吃紧,

    JinnGames
    Author
    Oct 22, 2024· 1 reaction

    @amythic0 我已经把t5xx删除的版本上传了,你还可以用我提供的代码把已经下载的模型内t5xx删除掉。

    yepeishengOct 22, 2024· 5 reactions
    CivitAI

    期待GGUF版本

    encassionOct 23, 2024· 3 reactions
    CivitAI

    I love XL v1.5, but I notice the quality is inconsistent. I have to start out at 80 steps and have to keep adjusting the steps, down, until I get to 20 steps as I go, to maintain quality. Then I have to restart my computer to reset it.

    It takes about 4 hours of generating images before I am forced to restart my computer.

    This is the only model I've used that behaves like this. Memory leak?

    encassionOct 27, 2024

    I fixed it by merging v1.5 with v1.1. It still shouldn't be doing it to begin with, but now it works.

    shiyugm2023860Oct 24, 2024· 4 reactions
    CivitAI

    怎么用代码加载这个模型,我只能加载lora模型

    JinnGames
    Author
    Oct 25, 2024

    什么代码加载?