Joe Rogan (Dreambooth trained LoRA)

Name: Joe Rogan (Dreambooth trained LoRA)
Rating: 5 (2 reviews)
Author: DSlater

148

Updated: Apr 17, 2024

celebrity

sports influencer podcaster joe rogan ufc

05767-_lora_Joe Rogan - Trigger w Joerogan Person_.7_joerogan person buying a barbie doll at toys r us.png

05728-_lora_Joe Rogan - Trigger w Joerogan Person_1_Closeup of joerogan person wearing a yellow Pikachu costume and making a shocked f.png

05816-_lora_Joe Rogan - Trigger w Joerogan Person_1_joerogan person taking a selfie on top of the eiffel tower around sunset. Golden h.png

05682-_lora_Joe Rogan - Trigger w Joerogan Person_1_ joerogan person, Film footage, in a science fiction film directed by darren arono.png

05696-_lora_Joe Rogan - Trigger w Joerogan Person_1_ joerogan person, Film footage, in a film noir film directed by zhang yimou ,, A c.png

05747-_lora_Joe Rogan - Trigger w Joerogan Person_.7_Photograph of joerogan person punching a robot with psychological problems in the.png

05680-_lora_Joe Rogan - Trigger w Joerogan Person_1_ joerogan person, Film footage, in a documentary film directed by sofia coppola ,,.png

05814-_lora_Joe Rogan - Trigger w Joerogan Person_1_joerogan person taking a selfie on top of the eiffel tower around sunset. Golden h.png

05726-_lora_Joe Rogan - Trigger w Joerogan Person_1_Closeup of joerogan person wearing a yellow Pikachu costume and making a shocked f.png

05743-_lora_Joe Rogan - Trigger w Joerogan Person_.7_Closeup of joerogan person punching a robot with psychological problems in the fa.png

Download (288.11 MB)

Verified: a year ago

SafeTensor

Details

Type	LoRA
Stats	148
Reviews	Positive (3)
Published	Aug 15, 2023
Base Model	SD 1.4
Training	Steps: 2,500
Trigger Words	Joerogan Person
Hash	AutoV2 1E63D78589

1 File

About this version

default creator card background decoration

DSlater

This resource is intended to reproduce the likeness of a real person. Out of respect for this individual and in accordance with our Content Rules, only work-safe images and non-commercial use is permitted.

If you are this person or a legal representative of this person, and would like to request the removal of this resource, you can do so here.

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.