runnermopa.blogg.se

You should always check the creator notes of LoRAs you download.

In the description for Colorwater, I noticed the following instructions by the creator: Sometimes a weight of 1 can be overpowering, so experiment with lower values like 0.5 or 0.7. It does not matter where you put this in the prompt.

WEIGHT is how strong you want the LoRA to be. If you've copied a prompt from somewhere else the version/formatting might be slightly different. LORA-FILENAME is the filename of the LoRA model, without the file extension (eg.

You can also just write the LoRA keyphrase manually, using the format: You can use as many LoRAs in the same prompt as you want. It will show all the LoRAs in the folder stable-diffusion-webui/models/Lora (if you don't see anything, click the grey Refresh button).Ĭlick on the LoRA you want, and the LoRA keyphrase will be added to your prompt. I won't go into detail on NSFW LoRAs, but there are plenty on Civitai. - the problem with HuggingFace is LoRAs are treated the same as checkpoint models, so there's no easy way to find them.In this guide we'll cover some popular LoRAs you can download, how to use them, and how to train your own. The creator will usually tell you these keywords, if any, in the LoRA description. For example, with the Anime Lineart LoRA example above, you would want to imclude "lineart" in your prompt. To get the best results with LoRAs, sometimes you will need to enter specific keywords in your prompt. If you don't have a particular model in mind, try AnyLoRA checkpoint, a model created with the sole purpose of being neutral enough to work well with any LoRA. LoRA creators will usually let you know in their descriptions. However, some LoRAs are created with a specific model in mind, and will only work well for that model. You can use LoRAs with any Stable Diffusion model.