Ray Z image base Artshoot - v2 nsfw

Ray Z image base Artshoot

CHECKPOINT
Original


Updated:

Ray Z image base Artshoot by RAY3780 on Tensor.Art
Ray Z image base Artshoot by RAY3780 on Tensor.Art
Ray Z image base Artshoot by RAY3780 on Tensor.Art
Ray Z image base Artshoot by RAY3780 on Tensor.Art
Ray Z image base Artshoot by RAY3780 on Tensor.Art
Ray Z image base Artshoot by RAY3780 on Tensor.Art
Ray Z image base Artshoot by RAY3780 on Tensor.Art
Ray Z image base Artshoot by RAY3780 on Tensor.Art
Ray Z image base Artshoot by RAY3780 on Tensor.Art
Ray Z image base Artshoot by RAY3780 on Tensor.Art
Ray Z image base Artshoot by RAY3780 on Tensor.Art
Ray Z image base Artshoot by RAY3780 on Tensor.Art
Ray Z image base Artshoot by RAY3780 on Tensor.Art
Ray Z image base Artshoot by RAY3780 on Tensor.Art
Ray Z image base Artshoot by RAY3780 on Tensor.Art

v1 is a fully SFW checkpoint! No NSFW content!

It features significant aesthetic upgrades with a unique artistic style of its own, and it works universally across all art styles and functional generation scenarios.

It feels like I’m the only one in the community who still hasn’t given up on Z Image Base.

v1 SFW检查点!仅有原版Base级别的NSFW内容!

美学方面提升很大,同时又有自己的风格。能影响到所有的风格和功能。

感觉现在整个社区只有我还在没有放弃Z image base。

v2 adds NSFW functionality to the existing features, and it's exclusive.

v2在原有的基础上添加NSFW功能,而且是独家。

v2:Maintaining the same style and diversity as the SFW version, unlocking NSFW content, I will no longer attempt to create SFW checkpoints. Integrating with LoRa acceleration, it will continue to maintain its artistry and diversity, balancing speed and quality. It will lean towards poster-style compositions; those who dislike inexplicable text can add: no text, no logo.

v2:保持和sfw版一样的风格和多样性,解锁nsfw内容,我再也不尝试制作sfw检查点了。以集成加速lora,一如既往的保持艺术性和多样性,兼顾速度和质量。会比较倾向海报构图,不喜欢莫名其妙文字的可以加上:no text,no logo。

Recommended Params

Steps: 8–20,CFG Scale: 1–2,Samplers: heunpp2 / Euler a / Seeds_3 / DDIM,Schedulers: beat / linear_quadratic / ddim_uniform,Upscaler: 4x-UltraSharp

Personal Optimal Settings:10 steps, 1.5 CFG, heunpp2 + beat, with 4x-UltraSharp upscaler

This ZIB checkpoint has been my daily driver for the past two months. I simply adore ZIB outstanding diversity and prompt adherence — strengths that ZIT simply does not possess.

This checkpoint is integrated with speed-optimized LoRA. While generation speed is greatly improved, it comes at the cost of reduced general LoRA compatibility. Using external LoRAs will lead to degraded image quality and unsatisfactory results.

这是我这两个月一直在用的ZIB检查点,我就是单纯的喜欢ZIB的多样性和提示词准确度这些ZIT没有的优点。

这个检查点因为合并了加速lora,速度提升的同时也对lora的兼容性有影响。使用其他lora只会得到更差的结果。

Note that this checkpoint does not merge the LORA code with the end version. Using the end version of LORA will yield better results. A unique tensor version will be iterated upon in the future for everyone to use.

注意,这个检查点融合的不是end版本的lora。使用end版本的lora效果会更好。以后会迭代一个tensor独家的pro版本供大家使用。

Version Detail

Z-Image
Recommended Params Steps: 8-20 | CFG Scale: 1-2 | Samplers: heunpp2 / Euler a / Seeds_3 / ddim | Schedulers: beat / linear_quadratic / ddim_uniform | Upscaler: 4x-UtraSharp My go-to settings for it: 10 steps, 1.5 CFG, heunpp2 + beat + Upscaler: 4x-UtraSharp

Project Permissions

Reprinting is strictly prohibited

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated contents

  • Use on generation services

  • Sell this model or merges

Related Posts