Type | |
Stats | 1,019 |
Reviews | (76) |
Published | May 27, 2023 |
Base Model | |
Training | Steps: 610 Epochs: 12 |
Hash | AutoV2 3C13D47419 |
Please check out my Ko-Fi page if you are interested in supporting me.
LoRA commissions open! -> Fiverr
This is a LoHa LoRA! You need the extension! Why? They do a lot better with multi-concepts.
I suggest using v1.15 at 38% for merges with Models if you want to do that.
No trigger word for LoHa version. Just call the LoHa at 0.5-1 weight, I recommend 0.75!
Theres 2 versions, the LoRA and the LoHa. I made the LoRA for merging with models. The LoRA version also have "Clay Mann" as a tag.
You can try color tags and they work quite well both in negatives or positives like: "grayscale", "monochrome" both make the image more vivid in negatives or make grayscale images in positives, "vivid colors", "flat colors" also helps with more colorful outputs.
Follow the steps in the Model Version notes to reproduce my images.
Sample images generated from Nothing model.
All negative embeds should be easy to find. and Prompts should be included in the sample images! Click the little icon in the bottom right to see it.
It was trained on 120 512x512 images scraped from the internet and 20 epochs using animefull_final.
Danbooru tags generated by Waifu Diffusion 1.4 Tagger and fine tuned for specific tags.