Type | |
Stats | 181 21 |
Reviews | (13) |
Published | Sep 19, 2023 |
Base Model | |
Training | Steps: 1,656 Epochs: 2 |
Trigger Words | 4runner1 |
Hash | AutoV2 C020F513A1 |
This model was trained on only 1984-1985 images at 1024x1024. 92 images of a variety of vehicles and one modified vehicle. No regularization images were used.
How to use
Add LoRA in prompt, then use the trigger keyword.
Additionally, look in showcase images for examples.
Recommended Weight: 0.8 (lowering will make it hybridize with newer 4runners)
Trigger: 4runner1
Helper: see the examples prompts, but in general you can vary the color of components (body, topper, wheels, grill, bumper) with some fiddling. Also, lifted vehicles can be generated with lifted, modified. The following view tags were used in training although it might be hard to generate images with these specific views: 'quartering away view', 'quartering in view', 'front view', 'rear view', 'side view'.
Additional: seems to work well with other base models, but I didn't spend much time playing with this.