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...
Fonte do modelo
Descrição da fonte
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.
Fontes
1 fonteArtefatos de modelo
1 artefatolora-000001.TA_trained.safetensors
safetensors · FP16 · 448 MB · SHA-256 f2b595144e14…a948 · Civitai
BaixarTrechos de fonte
1 trechoSource context: 427 downloads · Type LORA · Base model Krea 2