Mangamaster_Anima / README.md
Ava2000's picture
Update README.md
2cd2262 verified
|
Raw
History Blame Contribute Delete
1.75 kB
---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- output:
url: images/00074-1436195028.png
text: masterpiece, best quality, amazing quality, lineart, thick lines,
parameters:
negative_prompt: >-
worst quality, low quality, score_1, score_2, score_3, bad hands, mutated
hands, extra fingers, missing fingers, extra digits, fewer digits, fused
fingers, deformed hands, poorly drawn hands, bad anatomy, deformed
fingers, hands with too many fingers, signature,
---
# Mangamaster Style - Anima
<Gallery />
## Model description
The style of Mangamaster.
I made this lora to try and reproduce the style of Mangamaster.
Prompting Anima
I trained this one extensively and found for myself that Euler A (normal) produces better results the ER SDE. It should work well without using the artist @mangamster tag, but it does help with rounding the face, and making it a bit more stable.
Trigger: mangamaster,
Quality tags: masterpiece, best quality, amazing quality, lineart, thick lines, (to get slightly better lines, but you can go without lineart and thick lines)
Negative: worst quality, low quality, score_1, score_2, score_3, bad hands, mutated hands, extra fingers, missing fingers, extra digits, fewer digits, fused fingers, deformed hands, poorly drawn hands, bad anatomy, deformed fingers, hands with too many fingers, signature, (I use this one personally)
Advised strength: 0.6-1.0
I use addetailer only for the eyes with a eye model on 0.3 strength and merge enabled.
## Trigger words
You should use `mangamaster` to trigger the image generation.
## Download model
[Download](/Ava2000/Mangamaster_Anima/tree/main) them in the Files & versions tab.