Please Donate Buzz for FLUX Lora Training !
FLUX v.3 (Daenerys Season 1) :
Trained on FLUX.1 [dev] with 220 photos of Daenerys Targaryen from Game of Thrones Season 1. Tested on FLUX 1.dev (full) and FLUX fp8 and FLUX nf4 ! Use with word "blonde" ! Use around strength 0.8-1.2. Distilled CFG 3.5 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},blonde,<lora:Daenerys_Emilia_Clarke_Season_1_FLUX_v2_merger_21_65_04_06:1>
FLUX v.2 (Daenerys Season 1 & 2) :
Trained on FLUX.1 [dev] with 70 photos of Daenerys Targaryen from Game of Thrones Season 1 & 2). Tested on FLUX 1.dev (full) and FLUX fp8 and FLUX nf4 ! Use with word "blonde" ! Use around strength 0.8-1.2. Distilled CFG 3.5 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},blonde,<lora:Emilia_Clarke_Daenerys_FLUX_v2_merger_43_58_04_06:1.1>
FLUX v.1 (Clarke + Daenerys) :
Trained on FLUX.1 [dev] with 80 photos of Emilia Clarke (as herself and specifically as Daenerys frm Seasons 1 and 2). Tested on FLUX 1.dev (full) and FLUX fp8 and FLUX nf4 ! Use with trigger words : "emxclarke" or "emxclarke as daenerys" ! Use around strength 0.8-1.2. Distilled CFG 3.5 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},{instead of a woman etc. use trigger word "emxclarke" or "emxclarke as daenerys"}, <lora:Emilia_clarke_and_daenerys_FLUX_epoch_49:1>
SDXL v2.0 :
Trained on Juggernaut X with 320 photos of Emilia Clarke . Tested on Juggernaut X, Juggernaut v7, RealismEngine 2, RealVisXL3 and AlbedoBaseV2 ! Use with keyword : "emxclrke" . Use around strength 1.0-1.2. CFG 5.0-7.0. Clipskip 1. Can be used for example as follows:
Positive : {Artstyle}, {Character and scene description}, emxclrke, <lora:emclarke_juggerX_xl_2_st_wocap-emxclrke-000025:1.1>
Negative : ugly, deformed, airbrushed, photoshop, rendered, (multiple people), child, mouth open, overexposed
SDXL v1.0:
Lora trained on 320 images of Emilia Clarke. The recommended ComfyUi Lora strength is 0.9-1.1.