ModelListedExternal

Midjourney 7 Vibes

The Lora is trained on 100 images I generated using Midjourney 7. All images were captioned with joycaption-beta-en (natural language + English). Personally I'd rather not caption the images but I had to in order to...

Sourcecivitai.com/models/2421811

KindLORABase modelKrea 2VersionBgrade

Model source

Kind: LORA
File size: 448 MB
Base model: Krea 2
Version: v1.0
Updated: Sep 15, 2026
Downloads: 80
Source: Civitai

Source description

This is trained on over 100 images I made using Midjourney v7. If you are looking at the training details, it is not a mistake, I found the first epoch (20 repeats) to be the best. Not sure if there is a point making a Midjourney v8 lora as I'm not too impressed by it. This should work on Krea 2 Raw also, as this is what it was trained on. The first set of image use the lora.

Sources

1 source

CivitaiPrimaryVersion 3244685

civitai.com/models/2421811

Verified Aug 19

Model artifacts

1 artifact

lora-000001.TA_trained.safetensors

safetensors · FP16 · 448 MB · SHA-256 f2b595144e14…a948 · Civitai

Download

Source excerpts

1 excerpt

NoteAug 19civitai.com/models/2421811

Source context: 427 downloads · Type LORA · Base model Krea 2