Downloads · 30 days
17
29% of all-time downloads
Ava2000/Kome_VM500_Illustrious
Kome_VM500_Illustrious is a text-to-image model from Ava2000. Use it when you need an image from a text prompt. It is set up for diffusers.
Downloads · 30 days
17
29% of all-time downloads
All-time downloads
58
Public
Repo size
230 MB
Likes
1
Public
Click a slice to open those files.
.safetensors228 MB · 99%
From the Hugging Face model README
Kome (VM500) Style.
I made this lora to try and reproduce the style of Kome a.k.a VM500.
Trigger: vm500,
Advised strength: 0.7-0.9
Version 2: I made this one, because I found the first version I made for Illustrious lacking. Next to that I also did some research in finding the optimal training settings (for Civitai lora trainer) together with Claude (I send Claude out to find the best data sources) and the final result is spot on.
I used a slightly different bunch of quality tags: masterpiece, best quality, traditional media, sketch, jaggy lines, I also found that flat color helps to get a more manga/doujin feel.
For the negatives I use: text, long body, lowres, cropped, lowres, jpeg artifacts, (signature, artist name, watermark, username, english text, signature:1.4), simple background, conjoined, out of frame, out of frame, censored, bar censor,
I also use reForge with Adetailer (only the face model), CD Turner, FreeU and SelfAttentionGuidance (only for Illustrious), but they are not a must.
Download them in the Files & versions tab.