CivArchive
    Preview 19397704
    Preview 19397693
    Preview 19408711
    Preview 19408749
    Preview 19982384

    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 (22)

    telunyangJul 12, 2024· 2 reactions
    CivitAI

    The style of the images generated by this model is great; the characters look very appealing and cute.

    JinnGames
    Author
    Jul 12, 2024

    thanks

    Isabellas_Glass_EyeJul 12, 2024· 1 reaction
    CivitAI

    The Sandman: Death - Cosplay using latest update - Thank You Jinn! Great model and consistent updates! https://youtu.be/HYajyFQRCZE

    Gianni1900Jul 13, 2024· 12 reactions
    CivitAI

    It is VERY slow compared to other models. It takes around 8x longer to render an image than the default SD1.5 model.
    Plus it doesn't work with any LoRA or VAE I had at all.
    Definitely NOT worth a 6.9gig download.

    JinnGames
    Author
    Jul 13, 2024· 7 reactions

    Thank you for your feedback and I appreciate your candid comments. It seems there might be some confusion regarding the compatibility and performance of the Pony V1.1 XL-Lora Compatible model. Firstly, it’s important to clarify that this model is specifically compatible with XL version Loras, not with those from SD1.5. This might explain the issues you are facing with LoRA and VAE compatibility. Regarding the performance, this model indeed requires more computational resources compared to SD1.5, due to its enhanced capabilities and the advanced technologies it incorporates. It’s designed to offer higher quality and more detailed outputs, which inevitably takes longer processing times. If the performance is a critical issue for you, it might be worthwhile to consider upgrading your hardware. However, if you prefer the quicker render times of SD1.5 and it meets your needs, staying with SD1.5 is also a perfectly valid choice. Thank you once again for trying out the model, and I hope this clarifies some of your concerns.

    karetaiJul 14, 2024· 4 reactions

    @Gianni1900 I think you might want to read up on SDXL vs SD1.5 model differences (and 2.0/2.1, which is also different but was ignored mostly by the community). SD1.5 and SDXL are not the same. Think of it like say having a Playstation 3, and then upgrading to a Playstation 5.

    SDXL is a newer, larger base (foundational) model, with much greater VRAM and processing requirements - at least 6GB, but ideally a 3070/4070+ GPU with 8-12GB of VRAM if you want generation in any reasonable time. 1.5 was trained at 512x512 with a smaller language ability, SDXL was trained at 1024x1024 and has a more capable language ability.

    LoRAs, VAEs etc. from 1.5 are not compatible with SDXL models, SDXL needs new trained LoRAs and VAEs.

    niwo439Jul 22, 2024· 2 reactions

    @JinnGames I am impressed that you are responding so polite to criticism, this is a very rare gift these days!

    Isabellas_Glass_EyeJul 13, 2024· 1 reaction
    CivitAI

    Made using enhancements from 1.4 - Motoko Kusanagi Cosplay - I could not get the same results with 1.5. Take a look. https://youtu.be/41yQVNBhbKE

    1.5 - I kept getting random background shots and it would erase my model at times while touching up in my workflows. I love 1.4! Still working with 1.5!

    juliusdru394Jul 15, 2024· 1 reaction
    CivitAI

    Maybe you can help me with colors? I don't know what I am doing wrong, but colors are always mixed throughout entire picture... For example I type (blue eyes), (white sweater), (yellow pants), (white sneakers) and out of 50 pictures, I got only 6 images with the correct outfit... When I tried the same prompt with other checkpoints, the results were much better, and more than half of the images had correct outfits... How should I type colors in your checkpoint? Also, colors are mixed not only on clothes, but it adds these colors to background, furniture and everything else

    JinnGames
    Author
    Jul 15, 2024

    Thank you for your further inquiry. Indeed, in the SDXL model, it may not be feasible to specify colors separately for each part in the prompts as they can interfere with each other. A possible solution is to try using local repainting techniques.

    Local repainting can help you control the colors in specific areas more precisely without affecting other parts of the image. After generating a base image, you can specify particular areas for color modification, which can better prevent unwanted color contamination.

    If you need guidance on how to proceed specifically, I can provide more detailed steps or examples. I hope this information is helpful to you!

    juliusdru394Jul 15, 2024

    @JinnGames I would really appreciate your help! I wrote you a private message and will be waiting for your reply

    JinnGames
    Author
    Jul 15, 2024

    @juliusdru394 Thank you for your patience. To better assist you with controlling the color output, I conducted a series of tests and recommend that you use my latest model, Pony v1.1. In this version, I tested nine consecutive images, each satisfying the required features with 100% accuracy.

    I suggest using the following detailed prompts: “score_9, score_8_up, score_7_up, 18 year old cute girl, RAW photography, professional grade, (sutocking beautiful, cure lovely, shy, implicit, perseverance), (blue eyes), (white sweater), (yellow pants), (white sneakers)”. You can view these sample images in the Gallery for a visual understanding.

    I hope this model meets your needs, and if you have any other questions or need further assistance, feel free to contact me!

    Isabellas_Glass_EyeJul 18, 2024· 1 reaction
    CivitAI

    Was able to get the new model working! Check it out here! Carnage/Symbiote bodypainting cosplay ----> https://youtu.be/c9W2YmIsMwU

    sarashinaiJul 21, 2024· 1 reaction
    CivitAI

    The respect for Pony/danbooru prompting seems to be a little off (in comparison to cyberrealisticpony, for example). Should this be fully compatible?

    sarashinaiAug 21, 2024

    Pony_real_v2.0 is really nailing it with image quality and tag compliance. Kudos!

    encassionJul 22, 2024· 1 reaction
    CivitAI

    Still loving this model. It keeps improving and I highly recommend it. One thing all models lack is training for Jan Saudek's photography and art style. If you add that to the training data then it would be unique, as no other model I've tried can do art by Jan Saudek.

    Just a selfish request :)

    lost_moonJul 28, 2024

    It looks like as if it lacks skin details

    zoesixxxAug 1, 2024
    CivitAI

    Using Pony V1.1 XL-Lora Comp - I like the results so far but it feels like it's a bit random if a LoRa will work or not, for both SDXL and Pony.

    vicautAug 15, 2024· 4 reactions
    CivitAI

    I hope you merge this model with Flux. This would be probably the best SFW & NSFW model.

    JinnGames
    Author
    Aug 16, 2024

    👌😒

    ovisionAug 20, 2024· 2 reactions
    CivitAI

    The best model! Simple and clear prompt words can generate very charming and lovely Chinese women.

    JinnGames
    Author
    Aug 21, 2024

    Thank you for your praise and positive feedback! I am delighted to hear that you've successfully generated charming images of Chinese women with simple and clear prompts. We will continue to work hard to ensure that the model provides high-quality and diverse visual outputs. If you have any suggestions or need further assistance, please feel free to contact us!

    Checkpoint
    Pony

    Details

    Downloads
    8,985
    Platform
    CivitAI
    Platform Status
    Available
    Created
    7/11/2024
    Updated
    5/18/2026
    Deleted
    -

    Available On (1 platform)

    Same model published on other platforms. May have additional downloads or version variants.