The Juice is in the description below
Tips to use:
Use LoRA weight between 0.6-0.8
To summon her use the trigger Tags plus following tags: 1girl, solo, long hair, black hair, red eyes, necktie, very long hair, looking at viewer, gloves, breasts
We used one of Meina's model to generate the images.
If you have any questions feel free to ask!
Hope you guys like it! ❤️
You can ask for character LoRAs on our patreon page. Consider supporting us. 😘
Description
FAQ
Comments (14)
how does it come i have to use tags such a necktie and gloves but the pictures in the showcase have her wear anything. also what model did you use? i used this lora and she didn't look like that.
As always, the model is in the description. As for the tags, its just a guideline. If you want her to wear something else be creative and tag it the way you like it. Did you use it correctly, check log on SD console, did it find the lora, did you used the recommended tags?
tried it and yeah the lora works fine for me so far.
@kuehndavid830 Great! I though you meant the character didn't look like how our showcase looks. The style is not consistent on our end either. With some prompts it has flat colors with nice outlines, and with others its completely different.
hmmm, it worked in pixai but not on sd on abyssmix. gives me deformed anomalies
@kuehndavid830 I dont know, maybe it could be because of high upscale ratio or just too big image size in general?
@Pikkiwynn got it to work with the same model you used, one last question, i can't seem to get a boy with akame in the image. it's always just her even when i tag 1boy and even with (()). tried to scale it down to 0.7 aswell.
@kuehndavid830 Our loras should work with different loras and not just the one we used. We suggest to use the weight around 0.7. If you want someone other that her try to low even further maybe 0.5-0.6. But the boy's hair color and style will most likely match Akame's.
@Pikkiwynn i don't mean different loras but just let's her her and a random boy
@kuehndavid830 I dont know if its possible, sorry. We never tried it.
@Pikkiwynn @Pikkiwynn nvm it was the model i used, great lora and thanks for the help
could you maybe get a prompt that you used to make one of these images or share one that you know works i cant get anything close to what you have in quality, ive used the guidelines
Prompt: suggested tags + model call words + lora + background. We don't have anything specific, we always do images this way.
very nice, but hope can draw the new lora model with Chelsea (if you have free time).
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.