Verified: a year 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.
I actually only trained this lora for myself, but since I like it,
I would like to make it available to you as well.
The Lora is not perfect, but it does the job. Maybe I will work on a 2nd version if there is interest.
Works best with portraits.
Trained on 82 photos for 16 epochs.
_______________________________________________________________________________________________
Recommended Settings:
Distilled CFG Scale:
2-3.5
Sampling method and Schedule type:
I personally use DEIS/Beta.
You have to decide for yourself if other combinations deliver better results.
Steps:
30
Resolution/Aspect Ratio:
The Lora is trained on 1:1 aspect ratio.
You will have to test if other aspect ratios work.
Lora Weight:
1-1.3
But it depends on your own taste.
Trigger:
No trigger.
But you can use sentences like
“The photograph is taken with a ring light, which creates a soft, even lighting effect around her face, highlighting her features.”
to strengthen the effect.
_______________________________________________________________________________________________
I would be very grateful if you could leave me your feedback here
and post pictures with your results. I would really appreciate it if you guys would leave me a small Buzz tip here so I can train more Loras.