<h1 id="trained-on-illustrious-xl.-bn5c9m7yv">Trained on <a target="_blank" rel="ugc" href="https://civarchive.com/models/795765?modelVersionId=889818">Illustrious-XL</a>.</h1><h1 id="tobikara3:-7rnoix66n">tobikara3:</h1><a target="_blank" rel="ugc" href="https://x.com/tobikara3">https://x.com/tobikara3</a>Prompt :<pre><code>masterpiece, best quality, amazing quality, t061k4r43, </code></pre>Optional Prompt :<pre><code>2024, 2023, </code></pre>Negative Prompt :<pre><code>bad quality, worst quality, worst detail, sketch, censor, </code></pre>optional negative prompt :<pre><code>(monochrome, greyscale), signature, url, artis tname, username, watermark, text, English text,</code></pre>From a request. Most of the training pictures are black and white, so there is no corresponding negative prompt, so it is difficult to avoid black and white pictures.

Tobikara3 Style [Illustrious]

{ "engine": "kohya", "unetLR": 1, "clipSkip": 2, "loraType": "lora", "keepTokens": 1, "networkDim": 32, "numRepeats": 2, "resolution": 1984, "lrScheduler": "cosine", "minSnrGamma": 5, "noiseOffset": 0.1, "targetSteps": 3949, "enableBucket": true, "networkAlpha": 16, "optimizerType": "Prodigy", "textEncoderLR": 1, "maxTrainEpochs": 22, "shuffleCaption": true, "trainBatchSize": 4, "flipAugmentation": false, "lrSchedulerNumCycles": 3}

tobikara3_IL_1.safetensors

v1.0

<h1 id="trained-on-illustrious-xl.-bn5c9m7yv">Trained on <a target="_blank" rel="ugc" href="https://civitai.com/models/795765?modelVersionId=889818">Illustrious-XL</a>.</h1><h1 id="tobikara3:-7rnoix66n">tobikara3:</h1><a target="_blank" rel="ugc" href="https://x.com/tobikara3">https://x.com/tobikara3</a>Prompt :<pre><code>masterpiece, best quality, amazing quality, t061k4r43, </code></pre>Optional Prompt :<pre><code>2024, 2023, </code></pre>Negative Prompt :<pre><code>bad quality, worst quality, worst detail, sketch, censor, </code></pre>optional negative prompt :<pre><code>(monochrome, greyscale), signature, url, artis tname, username, watermark, text, English text,</code></pre>From a request. Most of the training pictures are black and white, so there is no corresponding negative prompt, so it is difficult to avoid black and white pictures.

&lt;p&gt;{&lt;/p&gt;&lt;p&gt;  &#34;engine&#34;: &#34;kohya&#34;,&lt;/p&gt;&lt;p&gt;  &#34;unetLR&#34;: 1,&lt;/p&gt;&lt;p&gt;  &#34;clipSkip&#34;: 2,&lt;/p&gt;&lt;p&gt;  &#34;loraType&#34;: &#34;lora&#34;,&lt;/p&gt;&lt;p&gt;  &#34;keepTokens&#34;: 1,&lt;/p&gt;&lt;p&gt;  &#34;networkDim&#34;: 32,&lt;/p&gt;&lt;p&gt;  &#34;numRepeats&#34;: 2,&lt;/p&gt;&lt;p&gt;  &#34;resolution&#34;: 1984,&lt;/p&gt;&lt;p&gt;  &#34;lrScheduler&#34;: &#34;cosine&#34;,&lt;/p&gt;&lt;p&gt;  &#34;minSnrGamma&#34;: 5,&lt;/p&gt;&lt;p&gt;  &#34;noiseOffset&#34;: 0.1,&lt;/p&gt;&lt;p&gt;  &#34;targetSteps&#34;: 3949,&lt;/p&gt;&lt;p&gt;  &#34;enableBucket&#34;: true,&lt;/p&gt;&lt;p&gt;  &#34;networkAlpha&#34;: 16,&lt;/p&gt;&lt;p&gt;  &#34;optimizerType&#34;: &#34;Prodigy&#34;,&lt;/p&gt;&lt;p&gt;  &#34;textEncoderLR&#34;: 1,&lt;/p&gt;&lt;p&gt;  &#34;maxTrainEpochs&#34;: 22,&lt;/p&gt;&lt;p&gt;  &#34;shuffleCaption&#34;: true,&lt;/p&gt;&lt;p&gt;  &#34;trainBatchSize&#34;: 4,&lt;/p&gt;&lt;p&gt;  &#34;flipAugmentation&#34;: false,&lt;/p&gt;&lt;p&gt;  &#34;lrSchedulerNumCycles&#34;: 3&lt;/p&gt;&lt;p&gt;}&lt;/p&gt;

Trained on <a target="_blank" rel="ugc" href="https://civitai.com/models/795765?modelVersionId=889818">Illustrious-XL</a>.tobikara3

Files with SHA256: ed069d1a6935768ae94ddd390e2153ad00cfc80dc0e5d705bddddadd7e4ac73d