Downloads · 30 days
14
12% of all-time downloads
damnthatai/Pee-Wee_Herman_Doll_Flux
Pee-Wee_Herman_Doll_Flux is a text-to-image model from damnthatai. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as apache-2.0.
Downloads · 30 days
14
12% of all-time downloads
All-time downloads
116
Public
Repo size
44.1 MB
Likes
0
Public
Click a slice to open those files.
.safetensors39.8 MB · 90%
From the Hugging Face model README
This model is based on the Talking Pee-Wee Herman Doll from the late 80s.
It works best with the weight at 0.65 to be more creative with actions and settings. Higher weights (ex:0.8 - 1) can cause bring back some of the white walls and wood floors from the training data. You can increase the weight on upscaling to bring back some of the details of the doll. I avoided anything in the training data so it would be seen as doll size and trained it on the word "man" so it would be real life human size. All training data is of the doll with no actual photos of Paul Reubens as the character.
Trigger words:
P33W33D011, man in grey buttoned suit and pants with red bow tie and white shoes,
Other words from training:
frontal shot, side angled profile shot, side profile shot, close up, handkerchief in front pocket of suit,
You should use P33W33D011 to trigger the image generation.
You should use man in grey buttoned suit and pants with red bow tie and white shoes to trigger the image generation.
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.