Ray Klein 9B BFS 编辑强化 - FP8 v3 nsfw

Ray Klein 9B BFS 编辑强化

CHECKPOINT
Original - TenStar Fund


Updated:

Ray Klein 9B BFS 编辑强化 by RAY3780 on Tensor.Art
Ray Klein 9B BFS 编辑强化 by RAY3780 on Tensor.Art
Ray Klein 9B BFS 编辑强化 by RAY3780 on Tensor.Art
Ray Klein 9B BFS 编辑强化 by RAY3780 on Tensor.Art
Ray Klein 9B BFS 编辑强化 by RAY3780 on Tensor.Art
Ray Klein 9B BFS 编辑强化 by RAY3780 on Tensor.Art
Ray Klein 9B BFS 编辑强化 by RAY3780 on Tensor.Art
Ray Klein 9B BFS 编辑强化 by RAY3780 on Tensor.Art
Ray Klein 9B BFS 编辑强化 by RAY3780 on Tensor.Art
Ray Klein 9B BFS 编辑强化 by RAY3780 on Tensor.Art
Ray Klein 9B BFS 编辑强化 by RAY3780 on Tensor.Art
Ray Klein 9B BFS 编辑强化 by RAY3780 on Tensor.Art
Ray Klein 9B BFS 编辑强化 by RAY3780 on Tensor.Art
Ray Klein 9B BFS 编辑强化 by RAY3780 on Tensor.Art
Ray Klein 9B BFS 编辑强化 by RAY3780 on Tensor.Art
Ray Klein 9B BFS 编辑强化 by RAY3780 on Tensor.Art
Ray Klein 9B BFS 编辑强化 by RAY3780 on Tensor.Art
Ray Klein 9B BFS 编辑强化 by RAY3780 on Tensor.Art
Ray Klein 9B BFS 编辑强化 by RAY3780 on Tensor.Art
Ray Klein 9B BFS 编辑强化 by RAY3780 on Tensor.Art

Based on Flux.2 Klein 9B Distilled, the editing functions have been enhanced. It incorporates my own image-trained editing-oriented Lokr and BFS face-swapping enhancement with Realtime fine-tuning, primarily focusing on adjustments to the editing capabilities.

基于Flux.2 klein 9B Distilled,编辑功能强化,融合了我自己使用对图训练的编辑型lokr和BFS换脸强化+Realtime微调,主要是针对编辑功能做出调整。

Set up : Euler + simple, 4-12 step, cfg1-2.5,

文生图-T2I:Euler + simple, 4-10步,cfg1-1.5,编辑-E2I:Euler + simple, 4-12步,cfg1.5-2,

Resolution : 832x1216 for 1024x1536, upscaling : 1280x1920 or 1536x2240。

No NSFW content has been added or beautified, allowing users to easily add their own Lora tools for compatibility. Distilled functionality remains effective, enabling image generation in four steps, saving time and computational effort.

并未美化和添加NSFW内容,方便大家自行添加所需的lora配合使用。distilled依然有效,可以4步出图,节省大家的时间和算力。

Version Detail

FLUX_2_KLEIN_9B_DISTILLED
文生图-T2I:Euler + simple, 4-10步,cfg1-1.5, 编辑-E2I:Euler + simple, 4-12步,cfg1-2, V3 It retains enhanced edit as its core functionality with fully unlocked NSFW access. Capable of point-to-point per-pixel faithful replication of the source image, it delivers ultimate facial locking, anatomically stable limb rendering, and improved prompt comprehension. It corrects rendering errors and reduces AI hallucinations in non-referenced regions, and features expanded compatibility with 2D, illustration, and semi-realistic art styles. However, it is not recommended for use as a standalone text-to-image generation model. V3依然是强化编辑功能,NSFW以解锁。能点对点原像素级模仿原图,终极锁脸,稳定肢体,增加了对文本的理解能力,修正对无参考的部分的错误和AI幻想。增加对2D、插画、半写实类风格的兼容。但不建议当作生图模型来使用。

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