| --- |
| license: apache-2.0 |
| base_model: |
| - black-forest-labs/FLUX.2-klein-9B |
| pipeline_tag: image-to-image |
| tags: |
| - lora |
| library_name: diffusers |
| --- |
| 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](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](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. |
|
|
|  |
|  |
|  |
|  |
|
|
|  |
|  |
|  |
|
|
| -------- |
|  |
|
|
|  |
|
|
|  |
|
|
|  |
|
|
|
|
|  |
|
|
|  |
|
|
|  |
|  |
