Prism 🌈 by Huggy
详情
下载文件 (1)
关于此版本
模型描述
💡 Search "huggy" to find all my models on site.
💡 Models are updated frequently, so be sure to check back and use the latest version.
💡 DO NOT MIXED USE Illustrious lora with SDXL / PONY / FLUX model.
📒 This lora does:
Bring "zoom blur", "chromatic aberration" and "black-and-white" effects to your works.
Create better male genitals.
📒 Usage Tips:
Works magically well with "Plant Milk 🌿 - Model Suite".
Set lora strength 0.8 or lower
For realistic styles, use DPM++ 2M Karras sampler
For expressive anime-style eyes, Euler tends to perform better
When using with other lora, set the other lora weights to 0.8 or lower
If Illustrious models produce stubborn 4-fingered hands, use a passive prompt like (5 fingers:1.7)
The Illustrious lora is not compatible with SDXL or Pony models
📒 Essential trigger words:
chromatic aberration
📒 Optional trigger words:
penis / small penis / saggy testicles / hairy / pubes
📒 Changes in V01E81:
Image count increased from 82 to 94
Repeats per image increased from 2 to 3
UNet learning rate raised from 0.0003 to 0.0004
Min SNR Gamma increased from 3 to 4
V01E81 was trained over 7,200 steps, this version delivers approximately 1.6× stronger chromatic aberration effects and improved generalization compared to previous versions.
V00E92 the initial version was trained using very slow "baking" settings recommended by Gemini. The result is noticeably underfitted, with very subtle effects.
📒 Cost Breakdown for This Lora:
1,100 Buzz – 90 high-resolution source file generations
3,600 Buzz – Training 2 rounds
3,900 Buzz – Testing
Total: 9,600 Buzz
🎉 This lora is part of my goal to create 100 lora.
📒 Mirroring
I’ve noticed a few sites, like Modelslab and yodayo, using bots to mirror my models. SeaArt in particular shows big numbers for downloads and generations.
I don’t mind if you mirror my models — sites like civitaiarchive have always done that.
I do mind if you block users from downloading the models and force them onto a paid online service.
I do mind if you claim copyright or give users ownership of the generations. These are open-source models, trained on open-source bases with limited-ownership data. No one — not even me — should claim copyright. Credit is all that’s needed.