Please Donate Buzz for FLUX Lora Training !

FLUX v1.0 :

Test with 16/16 for network alpha/dimension and very large dataset and portrait style images. Works best with images around resolution 896x1152 px.

Trained on FLUX.1 [dev] with 200 photos of Sadie Sink with detailed GPT-4 captions. Tested on FLUX 1.D (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:Sadie_Sink_FLUX_v1_r1-000052:1.0>

SDXL v3.0 :

Trained on Juggernaut X with 212 photos of Sadie Sink with an improved Lora training method for better likeness and flexibility. Tested on Juggernaut X, Juggernaut v7, RealismEngine 2, RealVisXL3, AlbedoBaseV2 and SDXXXL 3! Use with keyword : "saxsnk" . Use around strength 1.0. CFG 5.0-7.0. Clipskip 1. Can be used for example as follows:

Positive : {Artstyle}, {Character and scene description}, saxsnk, <lora:sasink_juggerX_xl_2_st-saxsnk-000088:1>

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

SDXL v2.0 :

Lora of actress Sadie Sink Trained on 220 images that are better selected and with an improved Lora model to increase flexibility and likeness. Lora strength should be between 0.9-1.2, but you should test it out with your preferred model and circumstance.

SDXL v1.0 :

Lora trained on 220 images of Sadie Sink trained on the SDXL 1.0 base model. The recommended Lora strength on ComfyUi is 0.9-1.1.