Donald ????? Jr. - (HQ Dreambooth Trained)

High Quality Dreambooth (JP's 24gb repo) trained checkpoint model of Donald ????? Jr created using hi-resolution images of the influencer from social media, cameo, and recent news media.

Why a full checkpoint/2GB model for 1 subject?

Simply because the trained checkpoint gives you the best quality to start w/. LoRAs are fantastic for lots of things, but for human likenesses they don't match up to Dreambooth trained checkpoints. I train with Dreambooth and then extract a LoRA from that if needed.

"I need a LoRA for my workflow!"

It's easy to extract a LoRA from an SD checkpoint on your own if you prefer a LoRA for your workflow. For instance you can use the Auto1111 extension "Supermerger" to extract a LoRA. That said, LoRA will not match the quality of the original Dreambooth model (loss incurred). The full 7gb v1.5 checkpoint was the base this model was trained on (necessary have/download if you do decide to extract a LoRA)

Trigger with "Donaldtrumpjr 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. Trained locally using JP's repo (24gb VRAM req / arguably the best for likenesses).

Some samples images were generated w/ Controlnet for initial guidance and thus won't be reproducible exactly with only metadata (don't think Civitai lists whether or not CN was used).