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. I diritti dei modelli ripubblicati appartengono ai creatori originali.
2. I creatori originali che desiderano reclamare il proprio modello devono contattare il personale di SeaArt AI tramite canali ufficiali. Clicca per rivendicare
