<h3 id="please-donate-buzz-for-flux-lora-training-!-4rx4r8wzh">Please Donate Buzz for FLUX Lora Training !</h3><h3 id="flux-v1.0-:-zztpanuvm">FLUX v1.0 :</h3>Trained on FLUX dev with 100 photos of Mila Kunis with detailed GPT-4 captions. Tested on FLUX <a target="_blank" rel="ugc" href="http://1.dev">1.dev</a> (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:Mila_Kunis_FLUX_v1-000040:1&gt;<h3 id="v2.0-:-sezdjdvua">v2.0 :</h3>Trained on Juggernaut X with 200 photos of Mila Kunis. Tested on Juggernaut X, Juggernaut v7, RealismEngine 2, RealVisXL3, AlbedoBaseV2! Use with keyword : "mxkunis" . 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}, mxkunis, &lt;lora:mikunis_juggerX_xl_1_wocap_merger_52_139_05_05-mxkunis:1&gt;Negative : ugly, deformed, airbrushed, photoshop, rendered, (multiple people), child<h3 id="v1.0-:-9r291ntdx">v1.0 :</h3>Lora trained on 200 images of Mila Kunis trained on SDXL 1.0 base model. Recommended lora strength on ComfyUi is 0.9-1.1.

Mila Kunis Face (FLUX + SDXL)

Please Donate Buzz for FLUX Lora Training !FLUX v1.0 :Trained on FLUX dev with 100 photos of Mila Kunis 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:Mila_Kunis_FLUX_v1-000040:1&gt;

Files with SHA256: e3159ed849795e5a59e7df9a6b2e4ff51ea98861a0add48480840097babaaaf9