Downloads · 30 days
24
6% of all-time downloads
Andyx1976/woodland-bdu-flux1
woodland-bdu-flux1 is a text-to-image model from Andyx1976. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as unknown.
Downloads · 30 days
24
6% of all-time downloads
All-time downloads
382
Public
Repo size
176 MB
Likes
0
Public
Click a slice to open those files.
.safetensors172 MB · 98%
From the Hugging Face model README
The classic US Woodland Camouflage Battle Dress Uniform (BDU), in use from the 1980's to 2000's, with the iconic Woodland Camouflage pattern. On low LORA weights, about 0.5 you can apply the pattern to other clothes ("woodland camouflage" is part of the training even though not a trigger). On high weight (near 1) it will create a very good and realistic such BDU. With different poses and more complicated situations give it a bit of wriggle room (like 0.95 instead of 1).
The leg pockets work not always out correctly (as in the big baggy ones with 3 folds) , but i tried to address that in the dataset. Give it a few iterations.
As with all my uniforms (plain green uniform shirt, and German Bundeswehr Flecktarn camouflage BDU), it was trained with male examples.
The trigger is BDU. Add "With cap" to add the traditional matching cap. You may need to specify the boots ("With black combat boots"), else the subjects might be barefoot
As for the license, i never find the correct one in the list, the lora was trained with Flux dev, so it's that...
You should use bdu to trigger the image generation.
You should use with cap to trigger the image generation.
You should use woodland camouflage to trigger the image generation.
Download them in the Files & versions tab.