Type | |
Stats | 736 |
Reviews | (137) |
Published | Jun 1, 2023 |
Base Model | |
Trigger Words | d3fr0 |
Hash | AutoV2 37A152D36D |
Hello again!
Time to bring you another style LORA but a bit different than my previous ones.
This LORA main purpose is to aim to create ice, frozen, cryogenic, etc. in an easy way but it can create diverse styles on your characters or on your prompt. Is NOT designed (again) for landscapes, it's an style adapter/changer.
HOW TO USE IT :
- This time the token "d3fr0" is not necessary since the LORA will work even without it.
- This LORA works even at high values such as 1.3-1.6 due to how it was trained.
- If you feel the ice, freezing, spikes or the "inhuman" appeareance is too high consider to use 0.7-0.8. However if you feel the prompt needs more freeze you can go to 1.3 without problems and 1.5-16 in specific situations.
- The main purpose was to use like "<lora:name:value> portrait/side portrait/fullbody + man/male/woman/female + d3fr0 style but once again you can add a lot in the prompt but the effect tends to go down so if that happens in long and descriptive prompts, try to rise the strenght.
- Even you can use negatives, using negatives feels like you're not getting entire style of the LORA (although fix some things at some seeds).
- Recommended models: I tested with Ghostmix, Colorful, Dreamshaper 3..32, Faetastic, Rev Animated, Dark Sushi Mix... it should work on every model since it's 1.5 based.
THIS LORA IS NOT DESIGNED FOR:
- Landscaping, scenearios, background and anything that it's not icy related.
IMPORTANT!
I wrote an article here and it's like my finetunning diary for the ones interested with releases upcoming, trainings done, exclusive patreon models previews, personal thoughts, etc. So if you want to see what I'm planning or what I'm into, feel free to take a look.
Enjoy and have fun and thanks as always for all your support in our patreon