Download
1 variant available
The FLUX.1 [dev] Model is licensed by Black Forest Labs. Inc. under the FLUX.1 [dev] Non-Commercial License. Copyright Black Forest Labs. Inc.
IN NO EVENT SHALL BLACK FOREST LABS, INC. BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.
I wouldn't say this is better or worse than the v2 but more like a different version of it, but I'm releasing it in case anyone wants to give it a try.
I'm releasing this separately from the main caucasian men lora because it's a bit different.
This needs more strength than the actual v2, but it depends on the image, I'd say start at 0.7-0.9. You should also be more descriptive of what the man looks like.
There are 2 main reasons I made this:
more diverse outputs
work better with other loras
This may output:
worse anatomy
less handsome men than the actual v2
In the sample images id say the generated images are mostly 1-3 chosen out of every 3-6 images. This should work better with other loras than the actual v2. The reason this can be worse at anatomy is because technically im pretty sure its undertrained. I don't recommend using low CFG but it can output nice images every so often.
And thank you for the support on the actual v2!