(Note on Rating: Got tagged w/ a 1 from someone who doesn't like the subject - meh - motivating)

High Quality Dreambooth (JP repo) trained model of the music sensation Ed Sheeran created using recent hi-resolution images via popular media.

Trigger with "Edsheeran 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).

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 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).

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).

(Note: Please don't give me a 1 cause you don't like the subject. The model is what it is. If you do decide to post a rating/review please at least download, try it, and then rate on the quality of the model. Thx!)

It's fun to see generations created w/ models I post - thanks in advance to anyone who shares what they make.