Updated: Aug 11, 2024
styleVerified: 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.
This lora was trained on Pop art painting styles, to bring more vibrant colors and a painterly effect. It also does some nice vector style black lines.
Because flux is so new, this is a beta lora. I have noticed that t5 text encoder messes with it a bit. If prompted for realism, it fights the lora style and burns out the image. Looking into the cause of this, but in the meantime; no trigger word is necessary. I would just prompt for the style and steer clear of realism.
Make sure to use "Lora Loader Model Only" and use with Flux "Dev" model.
I find depending on the prompt it starts working at 0.8 and cooks at 3/3.5
If you find out any better info on this- feel free to reach out!
Big shoutout to Ostris for his awesome work with this training script!
-Syntax