Run online:https://www.runninghub.ai/post/2028302502973677570?inviteCode=rh-v1331

Welcome to join our Discord channel for discussion, or contact me to collaborate on custom LoRA builds: https://discord.gg/yVAVa43mWk

LoRA can significantly improve Klein consistency without any cue words. Video tutorial: https://youtu.be/JXMbbbdfnSg

----- 2026/4/17 V2 version update ----

This time, I systematically break down how to train the Klein model, including dataset creation strategies and a detailed training tutorial: https://youtu.be/j6dqOekUQ8c

Cloud training — sign up to get two free 3-hour RTX 5090 vouchers: https://studio.aigate.cc/images/993593021914284032?channel=R6P1L7N3J

1. Significantly resolved the color cast issue.

2. Fixed the issue of images appearing dirty due to excessive detail additions in V1.

3. Reduced the issue of overly high saturation in images generated by Klein.

👁 微信图片_20260416102506_62226_893
👁 2
👁 1
👁 3

👁 ComfyUI_temp_ujgpj_00001_
👁 ComfyUI_temp_jxsxr_00001_
👁 ComfyUI_temp_cirom_00017_

---

👁 1-(4)

👁 13acf8f94c75e9ef96615868da6f1f9f

👁 ComfyUI_temp_ntuda_00011_

👁 ComfyUI_temp_honxz_00002_

👁 ComfyUI_temp_svpzc_00008_

👁 ComfyUI_temp_zdsuk_00001_

👁 ComfyUI_temp_zdsuk_00008_
👁 ComfyUI_temp_zdsuk_00005_

Base model

black-forest-labs/FLUX.2-klein-9B

(103)