Midjourney LoRA!
Note: the Z-Image Turbo LoRA is compatible with BOTH models. Z-Image Base and Turbo.
BASE ONLY WORKS WITH BASE ONLY!
base only is recommended to run at 2048 X 2048
BASE VERSION HAS BEEN UPDATED TO A FURTHER TRAINED CHECKPOINT!
(I reuploaded a new version of the Base lora. my previous version was an unfinished early checkpoint save because my session was corrupted. i have since retrained the lora and it is now the full training session! redownload if you already did!)
RECOMMENDED STRENGTH:
0.2 - 0.8
adds the midjourney aesthetic to your generations. VERY well trained to be as close to Midjourney as possible.
Dataset: 1217 Images, various styles, angles, lighting, aesthetics, contrasting, subjects, etc. the dataset is DENSE.
WARNING: LORA IS STRONG. i recommend testing on 0.1 and working your way up to the desired strength per image.
Description
1217 image dataset of v7 midjourney images. a multitude of poses, angles, lighting, contrasting, subjects, etc. the lora is intense.
FAQ
Comments (11)
considering how new klein is, this lora is crazy!!!!
almost always an improvement over the base image!!!
thank you and keep up the good work dude
I really appreciate it! I did multiple runs until i found my settings for Klein LoRAs. Its a little different training than most models
@realrebelai doing gods work for us low vram folk
@fent67 i do it for my fellow calculator pcs! 🫶 i got some new heat coming soon as well. Something to IMAGINE if you know what i mean.... hint: its a grok dataset 🤣
Klein 9B coming?
Yes! just finishing training on all my datasets for the 4B model and ill start training the 9B immediately after. should be up before thursday!
Please make 9B Klein version😁🧑🏾🎓👍🏾
this is some epic level sheeet
Im the most slept on LoRA trainer there is 🫶🫡
Absolutely love this LORA, such a great fit for my Flux.2 Klein AIO workflow.. I added this in my workflow's "Suggested Resources" section.. and you got 200 buzz from me..
i appreciate the comment! i do my best to provide quality results for you guys!