Movable figure model_CKXL_EPS_1.0 发布公告
我们正式发布 Movable figure model_CKXL_EPS_1.0。
作为 Movable Figure Model 系列的全新分支版本,本次模型在结构上并非对 Ill-1.1 的小修小补,而是基于 CKXL 框架进行的完整重训与升级。
本版本的训练数据与概念体系已更新至 2025 年 9 月,在角色结构、动作表现与整体稳定性方面都有更系统的优化,兼顾易用性与可控性。
本次更新要点
CKXL 全新训练架构
基于 CKXL 重新训练,重新调校人物比例、姿态结构与整体可动性表现,使其更适合作为「可动人形 / 动态人物」基础模型使用。概念更新至 2025 年 9 月
模型知识与风格概念同步更新至 2025/09,对当下流行的服饰、姿势表现、审美趋势有更好的覆盖和适配。延续 EPS 系列风格与兼容性
在引入 CKXL 体系的同时,保持与 EPS 系列一贯的写实倾向和细节表现,方便已有工作流的无缝衔接与过渡。更高稳定性与细节表现
重点优化了人体结构稳定性、动作连贯性与局部细节(如关节衔接、肢体比例等),减少姿势崩坏、结构错位等问题的发生频率。
升级建议
对于已经在使用 Movable Figure Model EPS 系列进行动作草图、动态人物、分镜预演等创作的用户,建议尝试迁移至 Movable figure model_CKXL_EPS_1.0,以获得更稳定的人物结构表现与更丰富的当代概念支持。
感谢大家一直以来的支持与反馈,后续我们会在 CKXL_EPS_1.0 的基础上,继续迭代动作多样性、风格扩展与控制能力,敬请期待。
当然,如果你不希望通过 BUZZ 获取下载权限,也完全没有问题。你可以通过加入 Telegram 群组或 QQ 群组与我联系,我将直接提供其他方式让下载到模型,确保每位用户都能方便获取和使用。
It should be noted that since the training process is entirely funded by me and there is no sponsorship channel at present, the resources are relatively limited. In order to allow more people to experience the effect of Ill-1.1 as soon as possible, I will adopt a "first-come, first-served" system: users can obtain experience permissions through less BUZZ, so as to quickly feel the performance of the new version.
Of course, if you do not want to obtain download permissions through BUZZ, it is completely fine. You can contact me by joining the Telegram group or QQ group, and I will directly provide other ways to download the model to ensure that every user can easily obtain and use it.
⬅️点击加群QQ
Telegram: https://t.me/+abN4F_N7DKI2MzFl
☜ 请您赞助我 感谢支持 !Please sponsor me. Thank you for your support! 您的赞助将用于 GPU 费用与模型优化 All contributions go toward GPU costs and model improvements.
———————————————————————————————————————————————
Suggest drawing parameters
sampler:
Euler 30-35 steps
Euler a: 30 steps
cfg scale: 3.8-5
Resolution of portrait characters: 768x1280 920x1536 1024x1024 1024x1386 1152x1536
注意高清放大不要超过1.5倍
Note that high-definition magnification should not exceed 1.5 times
clip skip: 2
Positive Prompt:
,, ,masterpiece, best quality, absurdres, newest, very aesthetic, amazing quality,highres,sensitive, highres, ultra detailed, best anatomy, HDR, 8K, high detail RAW color art, high contrast, ,
Negative prompt:
lowres,(bad),bad feet,text,error,fewer,extra,missing,worst quality,jpeg artifacts,low quality,watermark,unfinished,displeasing,oldest,early,chromatic aberration,signature,artistic error,username,scan,[abstract],english text,
———————————————————————————————————————————————
新版本训练 优化了 画师串对PVC风格的影响 优化了肢体稳定 和语义理解 优化了在不同画师串下依然能保持PVC风格状态
————————————————————————————————————————————————
关于AI生成PVC手办的风险提示
尊敬的用户:
感谢您对我AI生成PVC手办模型的关注。为了避免有不法分子利用本模型AI技术生成PVC手办,并通过虚假宣传、欺骗等手段骗取用户定金。对此我郑重声明如下:
本模型仅用于AI生成技术学术交流我手办模型的AI技术仅用于生成PVC手办的设计图稿,并不涉及实物生产和销售。
请勿相信任何未经授权的销售:任何声称销售由本模型AI生成技术制作的PVC手办的行为均未获得授权,请广大用户提高警惕,谨防受骗。
风险提示:PVC手办的制作涉及多个环节,包括3D建模、材质选择、模具制作、注塑成型、上色等,每个环节都可能存在质量问题。请用户在购买PVC手办时务必选择正规渠道,仔细核对产品信息,并保留相关凭证。
维权建议:如您发现有商家利用本模型的AI技术进行欺诈行为,请及时向相关部门举报,并保留证据,以便追究其法律责任。其可通过AI-Generated Content Detection | Hive (hivemoderation.com) 这个网站鉴定图片是否为ai 生成
温馨提示
为了保障您的权益,建议您在购买PVC手办时注意以下几点:
选择正规渠道:尽量选择知名厂商或有良好口碑的商家进行购买。
查看产品信息:仔细核对产品材质、尺寸、制作工艺等信息,并查看高清图片。
索要发票:要求商家提供正规发票,以便日后维权。
保留聊天记录:与商家沟通时,建议保留聊天记录,以备不时之需。
使用Ai技术判断:遇到没有见过可疑的手办 最好通过AI-Generated Content Detection | Hive (hivemoderation.com)这个网站上传图片进行鉴定
免责声明
对于本模型对任何未经授权的第三方利用本模型AI技术进行的商业活动不承担任何责任。请用户自行甄别,谨慎购买。
———————————————————————————————————————
—————————
Model Usage Statement
1. You are not allowed to host this model and its derivative versions (such as fusion model versions) on websites/applications that plan to earn income or donate. If you need to use this model and its derivative versions for commercial purposes (such as generative services, selling images, using images for public publication on short video platforms, etc.), please contact me through the website
2. You are not allowed to directly sell images generated by this model, unless you have made sufficient manual modifications to the image so that it can be fully recognized as your personal work in a legal sense. If you violate this provision, all legal consequences resulting from it shall be borne by you personally, and I am not responsible.
3. You cannot use this model to intentionally create or share illegal or harmful content for dissemination and output. Please abide by public order and morality, and use this model for positive purposes.
This model does not contain any real-life material, image sources, or training codes from the internet. The model is only used for scientific research interest exchange
