PLEASE NOTE - ALL MY CELEBRITY LORAS WILL BE DELETED (BY MYSELF) BY THE END OF JUNE 2024.
NOTE - This model was trained at 512px x 640px. Consequently it rarely 'doubles up' when using the popular 512px x 768px format.
Natively-trained LoRA of British actress Stephanie Beacham, a popular face on TV and in movies in the UK in the 1970s and 1980s - when she also became a major US soap star in Dynasty.
This replaces the previous checkpoint that I made available for this personality.
This model was trained to a native 512x640px resolution. This means that generations that use a standard 512x768px format are less likely to get duplicated heads and mangled limbs.
This model is quite resilient and fairly disentangled. You can really slide along the CFG scale a long way before nasty artifacts come in, and it's amenable to changes of style and clothing, hair color, etc.
Uses 61 ref images and 1989 (real) reg images, trained for 1,120 steps at a batch size of 1, for 4 epochs.
I generally use these models in complex workflows, inpainting faces after initial T2Is, and using ControlNet extensively. So if you're hoping for one-click prompt magic, my models aren't data-curated with this in mind, but rather as tools for traditional workflows that use Photoshop and other older methods.
This model is very likely to produce ????? renderings unless counter-prompted.
Trained from scratch in Kohya. NATIVE FORMAT IS 512x640px. IF YOU USE 512x512px, YOU ARE CUTTING OFF THE NATIVE FORMAT.
1. Dieses Modell dient nur Lernzwecken. Urheber- und Auslegungsrechte liegen beim Originalautor.
2. Bist du der Originalautor eines Modells, kontaktiere uns bitte zur Authentifizierung über unsere offiziellen Kanäle. Wir schützen die Rechte aller Schöpfer. Hier klicken, um es zu verifizieren.
