Pionyrka F1
Last Update：2024-10-14 06:24:00
Search History
Explore
FAILED
Home
Special content provided by the community
Special content provided by the community
FAILED
Inspiration
Share Your Brilliant Creations
Share Your Brilliant Creations
FAILED
AI Apps
Free and High-quality AI App
Free and High-quality AI App
FAILED
AI Characters
Immersive AI Character Interaction
Immersive AI Character Interaction
FAILED
Models
Various Powerful AI Models
Various Powerful AI Models
FAILED
AI Video
Create Videos Using AI with Ease
Create Videos Using AI with Ease
FAILED
LoRA Training
Customize Your AI Model Style
Customize Your AI Model Style
FAILED
ComfyUI
Simplify Your AI Creation Process
Simplify Your AI Creation Process
FAILED
AI Audio
Generate Realistic Audio Content Using AI Magic
Generate Realistic Audio Content Using AI Magic
Swift AI
Train
Official
Community
Flux Image to Image
Flux Image to Image
Flux Text to Image (Speed-Enhanced)
Flux Text to Image (Speed-Enhanced)
Anime to Real
Anime to Real
AI Muscle Generator
AI Muscle Generator
Ghibli AI Image Generator
Ghibli AI Image Generator
AI Breast Expansion
AI Breast Expansion
AI Bikini Generator
AI Bikini Generator
The first version. Seems to be working well at strenght 0.7 - 1.0, no triggers needed, just use generic words like shirt, skirt, neckerchief and specify colors or other detailed attributes. During training was also specified sequence "Czech schoolgirl uniform", so it makes some impact too. Pictures can be generated at 2Mpx directly without any upscaling. Compatibility with other LoRas is surprisingly good, much better than in SDXL (tested several dozens of celebrities/faces). Tested on DEV fp16 only and to fit in 24GB VRAM with some other LoRa it requires to be merged first (see the merged version with details).