Sign In

Kurodahana (British/Japanese Instagram model) (FLUX + SDXL)

81
1.4k
33
Type
LoRA
Stats
334
0
Reviews
Published
Sep 5, 2024
Base Model
Flux.1 D
Training
Steps: 3,700
Epochs: 37
Usage Tips
Clip Skip: 1
Strength: 1
Hash
AutoV2
08D53C5832
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.

Please Donate Buzz for FLUX Lora Training !

FLUX v2.0 :

Trained on FLUX.1 [dev] with 200 photos of Influencer Hana Kuroda (@kurodahana). 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:Kuhana_FLUX_v1-000037:1>

FLUX v1.0 :

Trained on FLUX.1 [dev] with 130 photos of Influencer Hana Kuroda (@kurodahana). 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:kuhana_wocap_flux_1_standard-000038:1>

SDXL v3.0 :

Trained on Juggernaut X with 220 photos of Hana Kuroda (@kurodahana) . Tested on Juggernaut X, Juggernaut v7, RealismEngine 2, RealVisXL3, AlbedoBaseV2! Use with keyword : "kuxhna" . Use around strength 1.0-1.1. CFG 5.0-7.0. Clipskip 1. Can be used for example as follows:

Positive : {Artstyle}, {Character and scene description}, kuxhna, <lora:kuhana_juggerX_xl_2_wocap_merger_77_121_132_02_05_03-kuxhna:1.05>

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

SDXL v2.0:

Lora retrained on the 200 images with a improved Lora training process to achieve better likeness for more varied circumstances. Lora strength ComfyUi is 1.1 and for Automatic1111 it is 1.2 for maximum likeness. For flexibility keep closer to 1.0.

SDXL v1.0:

Lora trained on 200 images of Half british, half japanese Instagram model Hana Kuroda (kurodahana). The Lora strength is quite high for ComfyUi at 1.0-1.2.