Verified: 2 months ago
SafeTensor
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.
What Is It?
This LoRA is trained to provide a close up, realistic face photography detail to your image generations. It has been tested with standard 1girl prompts but not tested with NSFW, or groups. It may lean towards eastern european features. Note that it pulls back from "perfect model" faces and goes for something more natural and less exaggerated.
Sample (left with lora, right without)
stylized studio portrait, of an androgynous person with sharp features and a slicked-back wet-look hairstyle, their expression is neutral and intense, in a high-key studio with a pure white, seamless cyc wall, hard, direct flash creating a bold, fashion-forward look with crisp shadows, high contrast, tack sharp, psxfacecc
How To
All generations in the samples are used with this LoRA applied by itself, and a face detail node. Generated using euler/beta @ 32 steps OR res_2s/bong_tangent @ 20 steps.
Suggested Weight: 0.4-1.0
Training Notes
Trained with 32 uncaptioned images at 768, 1024. No effort was made to train NSFW concepts.
While I have been able to use this in with no keyword applied at all, psxfacecc will help enforce the LoRA.