<p>You can use two of my models for online generation on Tensor Art:<br /><a target="_blank" rel="ugc" href="https://tensor.art/models/849516334959261898">Illustrious version 3</a><br /><a target="_blank" rel="ugc" href="https://tensor.art/models/853746118608051226">NAI version</a><br /></p><h3 id="but-if-you-want-to-use-this-model-here-on-civit-then-consider-bidding-some-buzz-to-make-it-available-on-the-generator!i-will-bid-all-the-buzz-i-get-from-all-of-you-using-the-model!-(if-i-remember.)current-bid:-750-buzz-on-nai-v-pred">But if you want to use this model here on Civit, then consider bidding some <span style="color:rgb(250, 176, 5)">buzz</span> to make it available on the generator!<br /><span style="color:rgb(190, 75, 219)"><em>I will bid all the buzz I get from all of you using the model! (If I remember.)</em></span><br />Current bid:<span style="color:rgb(250, 176, 5)"> </span><span style="color:rgb(64, 192, 87)">750</span><span style="color:rgb(250, 176, 5)"> buzz </span>on<span style="color:rgb(250, 176, 5)"> </span><span style="color:rgb(250, 82, 82)">NAI V-Pred</span></h3><p></p><h1 id="noobai-version:">NoobAI version:</h1><p>I wanted to be part of the cool gang and hop on the NAI v-pred craze. Here's what I cooked up.<br /></p><p>As with any of these models, use Euler or Euler A samplers. Comfy user should use ModelSamplingDiscrete and set it to v-prediction. I'll add more info here as I continue to research but for now, resources.</p><p></p><p>You can find CSV files filled with tags the model understands <a target="_blank" rel="ugc" href="https://huggingface.co/datasets/Laxhar/noob-wiki/tree/main">here</a>. Both danbooru and e621. Which... just means prompting like you would an Illustrious model.<br /><br />Illustrious LoRA models can break contrast and saturation, but they should work. Please report any issues you find.<br /><br />ComfyUI users can use the example workflow <a target="_blank" rel="ugc" href="https://huggingface.co/Laxhar/noobai-XL-Vpred-0.5/blob/main/comfy_ui_workflow_sample.png">here</a>. Just drag the image into comfy to open the workflow.</p><p><a target="_blank" rel="ugc" href="https://civarchive.com/articles/8962/noobai-xl-quick-guide">General guide for using NoobAI models effectively.</a></p><p></p><h1 id="illustrious-version:">Illustrious version:</h1><p>Triple model merge. It's a first merge attempt, but it came out alright I'd say. Understands Danbooru and e621 tags.</p><p></p><p>It's an EPS model but it seems to work fine without EPS sampling, but I'd still recommend you use the correct settings for whichever tool you use. (ComfyUI/A1111/etc.)</p><p>I do not use A1111, but for ComfyUI you have to use the node ModelSamplingDiscrete or an equivalent custom node and set it to EPS sampling.</p><p></p><p>Use Euler A sampler, ~25-40 steps and ~4-8 guidance scale (CFG).</p><h2 id="positive-illustrious-prompts:"><span style="color:rgb(130, 201, 30)">Positive Illustrious prompts:</span></h2><pre><code>(subject, {1boy/1girl/2boys/2girls/etc.}, artist/style).

Describe image with natural language. {A portrait of ...}.

(tags, quality tags).</code></pre><h2 id="negative-illustrious-prompts:"><span style="color:rgb(250, 82, 82)">Negative Illustrious prompts:</span></h2><pre><code>bad quality, worst quality, worst detail, sketch, censor.</code></pre><p></p><h1 id="pony-version:">Pony version:</h1><p>Test model, I wanted to see if merging two of my favorite models would increase prompt adherence while still keeping its imagination.</p><p></p><p>It has a bit of a watermark problem, but they don't seem to be <em>too</em> intrusive and are usually easily fixed with a bit of inpainting.</p><p></p><h2 id="positive-pony-prompts:"><span style="color:rgb(130, 201, 30)">Positive Pony prompts:</span></h2><pre><code>score_9, score_8_up, score_7_up, rating_tag, BREAK</code></pre><h2 id="negative-pony-prompts:"><span style="color:rgb(250, 82, 82)">Negative Pony prompts:</span></h2><pre><code>score_6, score_5, score_4, etc.</code></pre><h3 id="but-please-experiment-i'd-love-to-hear-your-thoughts!">But please experiment, I'd love to hear your thoughts!</h3><p></p>

IndigoDreamXL

indigodreamxl_pony.safetensors

Pony

NAI V-Pred

Files with SHA256: 129f4335fa8fa202da973a22d8764eb8a9aa7b30428d89d2cb6004845a644a62