Verified: 9 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.
This LoRA is trained on 60 realistic images (photos) of the outfit. It is not trained on faces, but female bodies. It is possible, on a limited basis, to create stylized images using this LoRA or to use it on men. Both could be tricky (men more difficult than style) and may need some parameter tuning and luck. The same rule applies when using additional other LoRAs. The base color of the outfit is black, but it is easily possible to prompt it in other colors (sometimes even multiple colors and/or patterns work).
In my tests, this LoRA delivered fairly stable results. The prompt “latex outfit” is sufficient. However, it may be helpful to expand the prompt with more detailed descriptions (such as "pentagram," "cutouts," "buckles," etc.) if some details are missing or poorly rendered.
All preview images were rendered with Euler / Simple / 25 steps in Forge WebUI. Different Distilled CFG Scale settings were used (mainly 0, 5 or 10).
Have fun!
Ava Cadava