<h3 id="confused-about-the-different-model-versions-check-the-'about-this-version'-on-the-right-sidebar-for-more-information.-3qmgqfz9m">Confused about the different model versions? Check the 'About this version' on the right sidebar for more information.</h3>This is just a quick release that we did since Flux + SD3.5 is taking such a long time (but we are working on it!)Hopefully this satisfies those furry desires.Take care!<h2 id="model-info-pp0xrn2yp">Model Info</h2>Chroma XL is an experimental model that is a partial merge + train of the brilliant NoobAI-XL (NAI-XL) model by L_A_X and their team, NoobAI is based off of Illustrious. All credit to the model goes to him.The model only needs low CFG and low step count. Making it highly versatile over a wide range of consumer hardware.We thank L_A_X and their team for his fantastic efforts in creating this model!<h2 id="recommended-settings-d75zgax6j">Recommended Settings</h2>We recommend using the following settings with the model for best results.<ul><li>Resolution: 1024x1024</li><li>Steps: 8-12</li><li>CFG Guidance: 1.7-3.0</li><li>Sampler: Euler A</li><li>Scheduler: beta</li></ul>The model utilises the low guidance and steps. It's advised to keep your step count as well as your guidance low, whilst you may increase the step count if you choose to do so, there is a clear point of diminishing returns, therefore we recommend you to follow our recommended values here.It is strongly recommended to use an ancestral sampler (e.g. Euler a) with beta schedule, the noise injection in ancestral sampler is absolutely needed to prevent over saturation.<h2 id="usage-instructions-qzekfuaei">Usage Instructions</h2>All the sample images have their workflow included within them. It’s recommended to download those images and use that workflow in ComfyUI.For all other clients, just run it as you would with any other SDXL model.<h2 id="strengths-and-weaknesses-xj4afzbu9">Strengths &amp; Weaknesses</h2>During our evaluations of the model, we find the following strengths and weaknesses in the model.Strengths<ul><li>High-level understanding of danbooru and e6 tags.</li><li>Relatively good anatomy compared to previous models.</li><li>Good understanding of many booru concepts, especially ones related to anime and furry.</li><li>Ability to do duo quite coherently, especially compared to prior models.</li><li>Ability to do high quality backgrounds.</li></ul>Weaknesses<ul><li>Non-existent natural language capabilities (don’t even try to use it).</li><li>Slightly incompatibility with SDXL model extensions, such as ControlNet but give it a go.</li><li>Characters that are in the distance tend to become extremely blurry.</li><li>The whole model has sort of a burned in ‘haze’ which can cause upscaling to look extremely pixelated.</li><li>Can look overcooked sometimes.</li></ul><h2 id="prompting-and-tips-qnvdk8hj1">Prompting &amp; Tips</h2>The model has next to no knowledge of natural language so you should exclusively use tags with this one.It’s recommended to go over the guidelines provided within the base models CivitAI page here.<a target="_blank" rel="ugc" href="https://civarchive.com/models/833294?modelVersionId=998979">https://civarchive.com/models/833294?modelVersionId=998979</a>The model was trained with artist tags.It’s recommended to always include <code>solo</code>, <code>duo</code>, <code>trio</code>, etc. Since not adding any of those tags results in a very unpleasant amalgamation of them.<h2 id="credits-h2ywc90mr">Credits</h2>This model was merged + trained by the Horizon Team.All credit for the base model goes to L_A_X and their team.<a target="_blank" rel="ugc" href="https://civarchive.com/models/833294?modelVersionId=998979">https://civarchive.com/models/833294?modelVersionId=998979</a><h2 id="contact-us-6spvxed5t">Contact Us</h2>You can reach us at our Discord server!<a target="_blank" rel="ugc" href="https://discord.gg/3GZHQTEEJq">https://discord.gg/3GZHQTEEJq</a>

ChromaXL Mix

Files with SHA256: 2dd126b6c62aa231a5a271a3ec9a14acc68050af098ed6c401b1ac44577ffb32