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+VX:jinngame ,请备注C站 ,期望共同成长互通有无。
comfyUI 工作流下载 workflows download: Pony 、Flux

这里包括了Flux.1、Pony、XL 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 v1.0和Flux_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:
>= 24G 显存:下载fp16版本。
12-16G 显存:下载fp8版本。
< 12G 显存:pony GuoFeng v4.3 or GuoFeng XL v1.5
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:
>= 24G VRAM: Download the fp16 version.
12-16G VRAM: Download the fp8 version.
< 12G VRAM:pony GuoFeng v4.3 or GuoFeng XL v1.5
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
Version Description:
Cartoon Hanfu Genshin Version is a brand-new branch, based on version 7.4 with extensive training on cartoon data. It includes excellent Hanfu elements and unique Genshin elements. You can use it to create richer cartoon images, including both SFW and NSFW content. The trigger words for various Genshin characters are as follows:
旅行者女----------------lumine\(genshin impact\),
旅行者男----------------aether\(genshin impact\),
派蒙--------------------PAIMON\(genshin impact\),
冰-迪奥娜---------------DIONA\(genshin impact\),
冰-菲米尼---------------FREMINET\(genshin impact\),
冰-甘雨-----------------GANYU\(genshin impact\),
冰-凯亚-----------------KAEYA\(genshin impact\),
冰-莱依拉---------------LAYLA\(genshin impact\),
冰-罗莎莉亚------------ROSARIA\(genshin impact\),
冰-七七-----------------QIQI\(genshin impact\),
冰-申鹤-----------------SHENHE\(genshin impact\),
冰-神里绫华------------KAMISATO AYAKA\(genshin impact\),
冰-优菈-----------------EULA\(genshin impact\),
冰-重云-----------------CHONGYUN\(genshin impact\),
冰-夏洛蒂---------------charlotte\(genshin impact\),
冰-莱欧斯利------------WRIOTHESLEY\(genshin impact\),
草-艾尔海森------------ALHAITHAM\(genshin impact\),
草-柯莱------------------COLLEI\(genshin impact\),
草-纳西妲---------------NAHIDA\(genshin impact\),
草-绮良良---------------KIRARA\(genshin impact\),
草-提纳里---------------TIGHNARI\(genshin impact\),
草-瑶瑶-----------------YAOYAO\(genshin impact\),
风-珐露珊---------------FARUZAN\(genshin impact\),
风-枫原万叶-------------KAEDEHARA KAZUHA\(genshin impact\),
风-琳妮特---------------LYNETTE\(genshin impact\),
风-流浪者 散兵--------- scaramouche\(genshin impact\),
风-鹿野院平藏----------SHIKANOIN HEIZOU\(genshin impact\),
风-琴-------------------JEAN\(genshin impact\),
风-砂糖-----------------SUCROSE\(genshin impact\),
风-温迪-----------------VENTI\(genshin impact\),
风-魈-------------------XIAO\(genshin impact\),
风-早柚-----------------SAYU\(genshin impact\),
火-安柏-----------------AMBER\(genshin impact\),
火-班尼特---------------BENNETT\(genshin impact\),
火-迪卢克---------------DILUC\(genshin impact\),
火-迪西娅---------------DEHYA\(genshin impact\),
火-胡桃---------------- HU TAO\(genshin impact\),
火-可莉-----------------KLEE\(genshin impact\),
火-林尼-----------------LYNEY\(genshin impact\),
火-托马---------------- THOMA\(genshin impact\),
火-香菱--------------- XIANGLING\(genshin impact\),
火-宵宫---------------- YOIMIYA\(genshin impact\),
火-辛焱---------------- XINYAN\(genshin impact\),
火-烟绯---------------- YANFEI\(genshin impact\),
雷-八重神子------------YAE MIKO\(genshin impact\),
雷-北斗---------------- BEIDOU\(genshin impact\),
雷-菲谢尔-------------- FISCHL\(genshin impact\),
雷-九条裟罗----------- KUJO SARA\(genshin impact\),
雷-久岐忍--------------KUKI SHINOBU\(genshin impact\),
雷-刻晴--------------- KEQING\(genshin impact\),
雷-雷电将军----------- RAIDEN SHOGUN\(genshin impact\),
雷-雷泽--------------- RAZOR\(genshin impact\),
雷-丽莎--------------- LISA\(genshin impact\),
雷-赛诺--------------- CYNO\(genshin impact\),
水-芙宁娜-------------FURINA\(genshin impact\),
水-芭芭拉------------- BARBARA\(genshin impact\),
水-公子 达达利亚----- TARTAGLiA\(genshin impact\),
水-坎蒂丝------------- CANDACE\(genshin impact\),
水-莫娜--------------- MONA\(genshin impact\),
水-妮露--------------- NILOU\(genshin impact\),
水-珊瑚宫心海-------- SANGONOMIYA KOKOMI\(genshin impact\),
水-神里绫人---------- KAMISATO AYATO\(genshin impact\),
水-行秋-------------- XINGQIU\(genshin impact\),
水-夜兰---------------YELAN\(genshin impact\),
水-那维莱特-----------NEUVILLETTE\(genshin impact\),
岩-娜维娅-------------NAVIA\(genshin impact\),
岩-阿贝多------------ ALBEDO\(genshin impact\),
岩-荒泷一斗---------- ARATAKI ITTO\(genshin impact\),
岩-凝光--------------- NING GUANG\(genshin impact\),
岩-诺艾尔------------- NOELLE\(genshin impact\),
岩-五郎--------------- GOROU\(genshin impact\),
岩-云堇--------------- YUN JIN\(genshin impact\),
岩-钟离--------------- ZHONGLI\(genshin impact\),
FAQ
Comments (17)
Will this got a sd3 version?
Another example of this model at work in this photoshoot. It is truly a dynamic model especially with inpainting and correction for photos taken IRL. https://youtu.be/wYkRbzZYhMU
This time bringing Hera back. Before long I will create the entire cause behind the Trojan War! Once again! I love this model! Check it out in action! https://youtu.be/fJ88Lx6peLQ
Worked great for 2 days, all of the sudden, without a restart or any change, it only generates red people for me. Like, the person is always red, no matter the prompt. There is no error, nothing, and every other model works fine. Im rather new to this, so maybe I am doing something wrong? Hopefully someone can help me out! :)
I had the whole image go red sometimes, turned out to be my long negative prompts, so I reduced some of those and no problems since.
Thank you for reaching out. I'm sorry to hear that you're experiencing this issue. It sounds quite unusual, especially since it started happening without any changes or restarts. One thing you could try is switching the VAE. My model comes with an embedded VAE, so making sure that the correct VAE is being used might resolve the issue. Alternatively, you could try using the AUTO setting for the VAE to see if that helps. If none of these steps work, please let me know. I'm here to help and will do my best to find a solution for you.
@JinnGames I was able to get the "red people" too today by having the negative prompt significantly longer than the positive one.
@JinnGames I have tried now to completly delete the negative prompts, which made no difference. Also the VAE is set on default (model) and not changeable as it seems. I've also updated all my drivers, but nothing seems to work. Other models still work, no matter the negative prompt or preset. Thank you so far for the quick answers! I really like this model and would love to have it work again, it had great results for me!
Hi ! Congrats and thanks for your astounding Iniverse checkpoints ;-)
Am I the only one to experience problems with hands rendering (non kidding XD ) on the "real 7.1" version ?
Textual inversion tools like "badhands" could do anything for this?
Thank you for your kind words and support! I'm glad you are enjoying the Iniverse checkpoints. Regarding the hand rendering issue in the "real 7.1" version, you're not alone—hand rendering can be a common challenge. Using textual inversion tools like "badhands" can indeed help improve the results. It might not completely eliminate the problem, but it can certainly make a noticeable difference. In subsequent versions, the hand rendering has been improved, but 7.1 has a unique style. If you particularly enjoy the near-realistic effect of 7.1, I don't have a perfect solution for the hand issue at the moment. However, I may consider updating the 7.1 style in future versions. Please stay tuned for my updates as I continue to experiment with more styles and versions. I apologize for any shortcomings and appreciate your understanding. Feel free to reach out if you have any other questions or need further assistance. I'm here to help! Best regards,
I apologize for the confusion in my previous message. I realized I made a mistake. The 7.1 version is not an isolated version; the isolated version I referred to is actually 7.2. If you like the 7.1 version, you can directly try 7.4 or 7.5. These versions have improvements in hand rendering. Thank you for your understanding, and please let me know if you have any further questions or need assistance.
@JinnGames Thank you very much for these really detailed and helpful answers... version 7.5 installed ;-)
@JinnGames are your answers ai-generated? :D
iNiverse Mix is the model I choose over 145 others I've downloaded, 99% of the time. It handles everything very well. I tried to do more abstract images and it didn't work, but after I applied a prompt weight of 3.0 it did an amazing job. The perceived weakness turned out to be merely a weight issue.
If I had any advice on what to train future versions for it would be vagina training, and unusual poses other than regular portrait, but that is an even smaller issue for me since there isn't too many reasons for me to do nudes.
I still use the iNiverse models almost exclusively since the results are just amazing.
Thank you so much for your detailed feedback and kind words! I'm thrilled to hear that iNiverse Mix is your go-to model and that it handles most tasks very well for you. It's great to know that increasing the prompt weight to 3.0 helped with the abstract images. I'll definitely keep this in mind for future improvements. Regarding your suggestion about training for specific details and unusual poses, I appreciate the advice. However, gathering a large amount of realistic data for these aspects can be challenging and sensitive. I will do my best to consider your suggestions in future versions. Thank you for your continued support and for choosing iNiverse models almost exclusively. If you have any more suggestions or need further assistance, please feel free to reach out.
Holli Would? https://youtu.be/PY23bVjhSxQ
Paired this with Vixon's Pony Toon Styles to create Ramona Flowers inspired Cosplay Photoshoot. Turned out pretty good. I have a few other Loras on as well. This model handles those well. https://youtu.be/DMwBQiPk-Qk - Check it out if you are curious.




