Flux2 Klein 9B Consistency
Welcome to join our Discord channel for discussion, or contact me to collaborate on custom LoRA builds:
Source du modèle
- Type
- LoRA
- Taille du fichier
- 316 MB
- Modèle de base
- black-forest-labs/FLUX.2-klein-9B
- Version
- vRevision 8df0c73
- Mis à jour
- 1 oct. 2026
- Éditeur
- @dx8152
- Téléchargements
- 46,4 k
- Paramètres
- 9B
- Tâches
- Image en image
- Source
- Hugging Face
Description de la source
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
-
Significantly resolved the color cast issue.
-
Fixed the issue of images appearing dirty due to excessive detail additions in V1.
-
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_
Sources
1 source
Sources
1 sourceVérifié 1 oct.
Artefacts du modèle
2 artefacts
Artefacts du modèle
2 artefactsFlux2-Klein-9B-consistency-V2.safetensors
safetensors · 316 MB · SHA-256 61db2017ce42…ff93 · Hugging Face
TéléchargerKlein-consistency.safetensors
safetensors · 316 MB · SHA-256 90a874e6931d…9d65 · Hugging Face
TéléchargerExtraits de sources
3 extraits
Extraits de sources
3 extraits--- 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.        --------   