You can use sample images to get started with your own workflow.
My recommended CFG's are between 4-12
Lora weights 0.8 to 1.2
No trigger words
What's new in v2:
More traditional prompting (1.5 like)
Balance between illustration and realistic styles
Description
Initial release
FAQ
Comments (5)
C'mon man you can't leave the rest of us out, give us an sd1.5 version
The only big tiddy Lora model so far. Great work. When you try for realism at about 1.5 and higher it starts to go too anime. Big request would be to train it on more realism!
I'm using ComfyUI and it seems to generate anime every time regardless of Lora settings. Is there a way to stop this?
I don’t know why, but it seems the lora has no effect at all :(
Any help ?
Nice LoRA. Did your dataset contain 2d images? Faces get often distorted. I recommend cropping faces out or use Yolov8 to cover faces with white box.
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.