<h3 id="please-donate-buzz-for-flux-lora-training-!-n6rgvecz7">Please Donate Buzz for FLUX Lora Training !</h3><h3 id="flux-v1.0-:-9arajehay">FLUX v1.0 :</h3>Trained on FLUX.1 [dev] with 150 photos of Naomi Scott 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}, &lt;lora:Naomi_Scott_FLUX_v1-000031:1&gt;<h3 id="v2.0-:-w8hg46zci">v2.0 :</h3>Trained on Juggernaut X with 220 photos of Naomi Scott. Tested on Juggernaut X, Juggernaut v7, RealismEngine 2, RealVisXL3, AlbedoBaseV2! Use with keyword : "naxsctt" . 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}, naxsctt, &lt;lora:naoscott_juggerX_xl_1_wocap-naxsctt-000080:1&gt;Negative : ugly, deformed, airbrushed, photoshop, rendered, (multiple people), child<h3 id="-d43shgzip"></h3><h3 id="v1.0:-gjytpbb01">v1.0:</h3>Lora trained on 154 photos of Naomi Scott. Lora strength should be between 0.8-1.2.

Files with SHA256: 4de10680b6a6318fe470e218c3cc6a1ffbd044b1cecbd0e57be02f770a41378d