Dimensionism Detroit HH V1

CHECKPOINT
Original


Updated:

291
<p>This is not <strong>Normal Checkpoint Model</strong> <strong><em><span style="color:rgb(250, 82, 82)">(Tested and Experimented)</span></em></strong> and It is hard to use for you, you would get many problems with this my model.</p><p></p><hr /><p></p><p>You should carefully prompt, it is very hard to control, my recommends are you should use it with Right LoRA, or else you would un-normal results</p><p></p><p><strong><span style="color:rgb(34, 139, 230)">Model Info</span></strong>-------------------------------------------------</p><p><strong>Base Model:</strong> <span style="color:rgb(250, 82, 82)">SD.1.5</span></p><p><strong>Model used to train:</strong> <span style="color:rgb(250, 82, 82)">Beautiful Realistic Asia or BRA V5 (Tested)</span></p><p></p><p>Trained at <strong>Resolution 1024</strong>.</p><p><strong>Learning Rate 1e-6</strong>, <strong>Max Steps at 3500</strong>.</p><p>Optimization AdamW8Bit, LR Scheduler Cosine with Restart.</p><p><strong>VAE (Used to Train): None, Sampling Method: K_DPM_2</strong></p><p><strong>Clip Skip</strong>: <strong><span style="color:rgb(250, 82, 82)">2</span></strong> <em><span style="color:rgb(250, 82, 82)">(You should use Clip Skip 2)</span></em></p><p>[New NOTE: <em><span style="color:rgb(250, 82, 82)">Clip Skip 2 is not really meant to be good as my recommend because my Model is making many different to Clip Skip 1-5 - So No MEANS to any Clip Skip 1-5]</span></em></p><p></p><p>Number of Images used to train is about 100 Images (All not Normal Images)</p><p></p><p><strong>Activation Word</strong>: <strong><span style="color:rgb(250, 82, 82)">HighHumanion</span></strong>.</p><p>You can use this word (or Activation Word) in your prompt as following syntax: <strong>HighHumanion:<em><span style="color:rgb(250, 82, 82)">&lt;weight value herer&gt;</span></em></strong>,</p><p>and you would get nothing special thing, you can use this word or not, it will impact your prompt but as I said, I can't predict what happen!</p><p></p><hr /><p></p><p><strong>NOTE.</strong> Above Images is from<span style="color:rgb(121, 80, 242)"> </span><strong><span style="color:rgb(121, 80, 242)">SeaArt</span></strong>, you should use <em><span style="color:rgb(190, 75, 219)">Quality is High Quality</span></em>, but It would be not special, it is likely <strong>BRA V5</strong>, with High Quality, you would not too care about many problems.</p><p>For <em><span style="color:rgb(190, 75, 219)">Quality is Ultra High Quality</span></em> in <strong><span style="color:rgb(121, 80, 242)">SeaArt</span></strong>, it is very hard to predict Results, it can surprising or painful to you, so you should be carefully about Ultra High Quality.</p><p></p><p><strong>Guide:</strong> Don't try to use <strong>'HighHumanion:<em><span style="color:rgb(250, 82, 82)">&lt;weight value herer&gt;</span>'</em></strong><span style="color:rgb(250, 82, 82)"> </span>in your prompt<span style="color:rgb(250, 82, 82)"> </span>it can be hard to use and predict any result; You shouldn't use word <strong><em><span style="color:rgb(190, 75, 219)">'restore'</span></em></strong> such as <em><span style="color:rgb(190, 75, 219)">restore face</span></em>, it is hard to predict. However, it is hard to predict from any words in your prompt with my model, so don't too care about my this guide, it is still un-predictable</p><p></p><p>Hope you will enjoy it, So No Pain No Gain</p><p></p><hr /><p></p><p>You can post review posts with your impressive results, it is helpful to my Model</p>

Version Detail

SD 1.5

Project Permissions

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated contents

  • Use on generation services

  • Sell this model or merges

Comments

Related Posts

Describe the image you want to generate, then press Enter to send.