Mashle style LoRA
Making models can be expensive. Do you like what I do? Consider supporting me on Patreon 🅿️ or feel free to buy me a coffee ☕
Should work fine at around weight 1-1.3 on AnyLoRA ckpt. Use mashle to increase fidelity. You can also use face mark to control the Magic Mark.
Remember this is a style LoRA. To make characters accurately you need other networks too (but it can get pretty close with accurate descriptions).
How to use LoRA's in auto1111:
Update webui (use
git pulllike here or redownload it)Copy the file to
stable-diffusion-webui/models/loraSelect your LoRA like in this video
Make sure to change the weight (by default it's
:1which is usually too high)
Description
FAQ
Comments (4)
Can it generate cream puffs?
very likely if the base model can.
Can you make pictures of Creed diskenth from the Black Cat anime? please 💗
Hello. I have a question about making a LoRA training model for the anime character. When I reach the step: “Base Model for Training.” What is the appropriate custom model for any LoRA anime character? Knowing that I chose “anime sd1.5” and the results were bad and the pictures were not drawn carefully. Please
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.