ghost
Sign In

Dreamtime

34
290
1
Verified:
SafeTensor
Type
LoRA
Stats
290
Reviews
Published
May 4, 2023
Base Model
SD 1.5
Training
Epochs: 15
Trigger Words
dr34mt1m3
dr34mt1m3, abstract, man, woman, vehicle, animal, landscape, person
Hash
AutoV2
258DDB11D0

This is trained on materials that has a 'dot painting' style of art common to Indigenous Australian painting. It is a strong style and I have allowed the training to have an effect especially on human subjects that some people may not like. It is not intended for realistic images, and on people in particular you definitely won't get a natural looking result.

Samples made in REVanimated 1.22

I recommend a strength of 0.7-0.8 in REVanimated.

If you are combining with other loras reduce the strength accordingly.

Trained with clip skip 2

Main Trigger: dr34mt1m3

Using just the 'dr34mt1m3' trigger will apply the effect nicely to the main subject of the image the other triggers below can enhance or alter the effect.

Secondary trigger: abstract

If you add the trigger 'abstract' the effect will spread more from the main subject giving you a more well, abstract... image :D

Other useful triggers: man, woman, vehicle, animal, landscape, person

There will almost certainly be at least one revision to this model as there are things I wish it could do better and i'd like to shift the style a little more into the right color palette.

If you like it, please review it or;

squeeze me some carrot juice - https://ko-fi.com/bunnyviking

Reviews of AI learnin' stuff

https://www.youtube.com/channel/UCjXlRo9kik1YJYONdjz4kiw

This Lora is based on the KonyConi style and their excellent tutorial. Check out their work.