Verified: 2 years ago
SafeTensor
Type | |
Stats | 622 94 |
Reviews | (190) |
Published | Apr 28, 2023 |
Base Model | |
Training | Steps: 110 Epochs: 1 |
Trigger Words | <lora:disoptics_yiu_v12:0.85> |
Hash | AutoV2 7538F8CA64 |
How to use
To use it, you need to register <lora:disoptics_yiu_v12:0.85> in the prompt field. I recommend exactly this value of the LoRA weight, as it gives more variability.
It is recommended to write the following tokens: design, glass lines, CIFilters, distortion, refraction, simple composition.
Copy the prompta and parameters from the preview to this model — you will not lose.
What the model is suitable for
This model is needed to simulate forced displacement and refraction of light. She copes well with the tokens "man, "woman" and abstract objects.
I trained LoRA on the Deliberate_v2 model, so it's better to work with her in pairs.
Which model works best with
It is best to use the Deliberate_v2 model.