Type | |
Stats | 82 279 |
Reviews | (25) |
Published | Aug 3, 2024 |
Base Model | |
Training | Steps: 4,500 Epochs: 15 |
Usage Tips | Clip Skip: 2 Strength: 0.7 |
Trigger Words | ralph_wreckitralph |
Hash | AutoV2 CA6B8DDBDB |
I made Ralph from Wreck it Ralph. It's came from Wreck-it Ralph. He's big guy.
Trigger Word
ralph_wreckitralph
Supporting Trigger Word
In this model there's some trigger word that you can use for creating Ralph
//WORDS
ralph_wreckitralph --> main trigger
red shirt --> his signature red shirt
muscular --> muscular build
//NOTES
This LoRA is so strong, that realistic is not so realistic
Settings I used:
Sampling Method:
DPM++ 2M SDE Karras
DPM++ 2M Karras
CFG Steps: 5 - 4
Sampling Steps: 20
Resolution: 768x960
All of sample image that I use is based on 768x960 with HiRES + Fix applied and upscaled by 1.55x and denoising strength of 0.55 - 0.63 using sampler Latent. Then I upscaled the final image 4x by using ESRGAN-4x, R-ESRGAN 4x, and R-ESRGAN 4x Anime 6B upscaler depending what kind image that I handled.
No inpainting, regional prompter, controlNet I use in all my sample image. All of them were built in from SD Checkpoint + Text Embedding.
Weight: 0.5 - 0.8