High Quality Dreambooth (JP's 24gb repo) trained LoRA of podcasting sensation Joe Rogan created using hi-resolution images of the influencer. Trained with Dreambooth and then the LoRA was extracted using the A1111 extension "Supermerger"
Trigger with "Joerogan Person"
(yes, put person also). Use "Hi-Res fix" with the settings you'd normally use for best results. Use prompt weighting and/or Controlnet to get maximum flexibility out of this likeness model.
Note on the Samples:
Some same images were generated using Control Net (particularly the 16x9 film style images). I don't think Civitai notes if Controlnet was used but you may not be able to reproduce some of the images due to that. (I often use canny w/ a random movie still for a % of the early steps to guide the image to do something interesting).
Note on the model:
Actually trained this ages ago before using this site (Nov '22). I'd prob use a better dataset if I were to redo it (microphone shows up on occasion), but for a LoRA seems to do really well holding the likeness.
Should work with any model based on SD1.4 or SD1.5. For best likeness use the original SD ckpt or safetensor.
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.
