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.
Experimental, the goal was a better likeness of the body in training images as well as better face. I used a few more images than i normally do and the added photos were poses. Small disclaimer: the training images weren't the best I got lazy. I trained at a lower resolution than I normally do as well as used lower resolution photos. It can also be tricky to get him to smile.
I recommend a strength of 1. The trigger word is l4c4, sometimes it helps make an image better, other times it'll add an extra finger or object. I believe it just depends on the prompt.
I usually generate images on Fitfux with Euler.
This is not based on a real person. Based on an image I generated.