Verified: 3 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.
Dark & Eerie 1.0 FLUX.1
This LoRA enhances portraits with an unsettling aesthetic and a touch of darkness. It replaces the standard FLUX face with a more ethereal look, and provides a wider range of "edgy" haircuts and alt-fashion styles. The style spans from the uncanny to the eerie, culminating in horror.
For optimal results, use long, descriptive prompts, as shorter ones may reduce its effectiveness.
Trigger Word: bsflash_eerie.
If you're using DrawThings, simply drop example images onto the canvas to generate the exact image with the corresponding metadata.
Settings:
- LoRA Weight: 0.6 - 0.8 beyond 0.8 the images introduces more grain.
- Sampler: DDIM Trailing* / DPM++2M Trailing* / Euler A Trailing* or DPM++2M AYS.
*Trailing is similar to the Uniform scheduler in case you don't have it.
- Steps: 50 with enabled TeaCache: 4-48, 0.30, 8 to speed up the generation.
- Text Guidance / CFG: 2 - 2.8
- Shift: depending on the output size. For 896x1152px = 3,12
Comparison (Style Prompt):
Comparison (Generic Prompt):
Sampler Examples: