High Quality Dreambooth (JP repo) trained model of the 1980s television star, Alf. Created using 20 HQ images from the TV show and promos.

Trigger with "Alf 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 and to limit clones/doubles from appearing. 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). Note: I've also been uploading updated versions to some of these models after posting the pure checkpoint first. If after extracting to LoRA the generated LoRA holds up well then I will try to add those as alternate versions.

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).