Update README.md

README.md

@@ -116,10 +116,6 @@ widget:
 
 ## Model description
 
-<h3 id="please-donate-buzz-for-flux-lora-training-!-vq7s06dv5"><span style="color:rgb(250, 176, 5)">Please Donate Buzz for FLUX Lora Training !</span></h3><p></p><h3 id="flux-v1.0-:-4tnvxu24x"><strong><u>FLUX v1.0 :</u></strong></h3><p><strong>I will post an improved version soon, but since I already spent 3000 Buzz on this I might as well post it.</strong></p><p></p><p>Trained on FLUX.1 [dev] with 175 photos of <strong><span style="color:rgb(250, 176, 5)">Emma Watson with detailed GPT-4 captions</span></strong>. <strong><span style="color:rgb(76, 110, 245)">Tested on FLUX </span></strong><a target="_blank" rel="ugc" href="http://1.dev"><strong><span style="color:rgb(76, 110, 245)">1.dev</span></strong></a><strong><span style="color:rgb(76, 110, 245)"> (full) and FLUX fp8 and FLUX nf4 !</span></strong> Use around strength <strong>0.8-1.2</strong>.<span style="color:rgb(250, 82, 82)"> No keywords needed!</span> Distilled CFG around 1-4 and CFG 1.0 (without negative prompt). Clipskip 1. Can be used for example as follows:</p><p></p><p><strong><span style="color:rgb(130, 201, 30)">Positive</span></strong><span style="color:rgb(130, 201, 30)"> : {Artstyle, Character and scene description in usual FLUX fashion}, &lt;lora:Emma_Watson-000052:1&gt;</span></p><p></p><h3 id="v3.0-:-uxqrnglxw"><strong><u>v3.0 :</u></strong></h3><p>Trained on Juggernaut X with 175 photos of <strong>Emma Watson </strong>with an improved Lora training method for better likeness and flexibility.<span style="color:rgb(76, 110, 245)"> </span><strong><span style="color:rgb(76, 110, 245)">Tested on Juggernaut X, Juggernaut v7, RealismEngine 2, RealVisXL3 and AlbedoBaseV2!</span></strong> <strong><span style="color:rgb(250, 82, 82)">Use with keyword : "</span><em><span style="color:rgb(250, 82, 82)">emxwtsn</span></em><span style="color:rgb(250, 82, 82)">"</span> </strong>. Use around strength 1.0. CFG 5.0-7.0. Clipskip 1. Can be used for example as follows:</p><p></p><p><strong><span style="color:rgb(130, 201, 30)">Positive</span></strong><span style="color:rgb(130, 201, 30)"> : {Artstyle}, {Character and scene description}, emxwtsn, &lt;lora:emwatson_juggerX_xl_2_standard_wocap-emxwtsn-000089:1.0&gt;</span></p><p></p><p><strong><span style="color:rgb(230, 73, 128)">Negative</span></strong><span style="color:rgb(230, 73, 128)"> : ugly, deformed, airbrushed, photoshop, rendered, (multiple people), child</span></p><p></p><h3 id="v2.0-:-isabn7c5m"><strong><u>v2.0 :</u></strong></h3><p>Lora trained on 150 selected images of Emma Watson between 2010 and 2017 with more variety, captioned by GPT4-V and trained with an improved Lora model for improved flexibility and likeness. Recommended weight is again <strong>0.9-1.1</strong>.</p><p></p><h3 id="v1.0-and-v1.1-:-jlythyfxn"><strong><u>v1.0 and v1.1 :</u></strong></h3><p>Lora trained on 200 images of Emma Watson between 2010 and 2017 trained on the SDXL 1.0 base model. Recommended weight for <strong>ComfyUi </strong>is <strong>0.9-1.1</strong>.</p><p></p>
-
-
-
 ## Download model
 
 Weights for this model are available in Safetensors format.