Sign In

Taylor Hill (FLUX + SDXL)

53
669
15
Type
LoRA
Stats
188
0
Reviews
Published
Dec 4, 2024
Base Model
Flux.1 D
Training
Steps: 2,610
Epochs: 58
Usage Tips
Clip Skip: 1
Strength: 1
Hash
AutoV2
000B4AAA9D
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.

FLUX v1.0 :

Trained on FLUX dev with 90 photos of Model Taylor Hill with detailed captions. Tested on FLUX 1.dev (full) and FLUX fp8 and FLUX nf4 ! Use around strength 0.8-1.2. No keywords needed! Distilled CFG around 1-4 and CFG 1.0 (without negative prompt). Clipskip 1. Can be used for example as follows:

Positive : {Artstyle, Character and scene description in usual FLUX fashion},<lora:Taylor_Hill_FLUX_v1-000058:1>

SDXL v2.0 :

Trained on Juggernaut X with 230 photos of American Supermodel Taylor Hill. Tested on Juggernaut X, Juggernaut v7, RealismEngine 2, RealVisXL3, AlbedoBaseV2! Use with keyword : "tayxhll" . Use around strength 0.9-1.1. CFG 5.0-7.0. Clipskip 1. Can be used for example as follows:

Positive : {Artstyle}, {Character and scene description}, tayxhll, <lora:tayhill_juggerX_xl_1_wocap_merger_21_147_035_065-tayxhll:1>

Negative : ugly, deformed, airbrushed, photoshop, rendered, (multiple people), child


SDXL v1.0:

Lora trained on 290 photos of American Supermodel Taylor Hill. Lora strength should be between 0.8-1.2.