Updated: Aug 5, 2024
characterVerified: 10 months ago
SafeTensor
Type | |
Stats | 169 587 44 |
Reviews | (25) |
Published | Aug 5, 2024 |
Base Model | |
Training | Steps: 500 Epochs: 10 |
Usage Tips | Clip Skip: 1 |
Hash | AutoV2 B39B3AC199 |
Created on Civitai
In txt2img, you will only get low quality results due to the training data's quality being bad.
Please use img2img without the LoRA to fix the quality issue.
You can't get the same quality in just one generation.
My workflow:
txt2img for base image.
img2img + 2x upscale without the lora to fix glitches.
img2img + 2x upscale with the lora to enhance details.