<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/9d6acab0-509d-4db1-acba-91c592aa4e4c/width=525/9d6acab0-509d-4db1-acba-91c592aa4e4c.jpeg" /><h2 id="overview">👋 Overview</h2>LUMIERE is the spiritual successor to <a target="_blank" rel="ugc" href="https://civarchive.com/models/1691036/stelra">Stelra</a>, upgraded from SD 1.5 to SDXL 1.0, making it one of the most outstanding models capable of generating high-quality anime-style images.It has been merged with frequently used community models along with its own high-quality LoRA models through LUMIERE merging solution. <h3 id="disclaimer">Disclaimer</h3><ul><li>The LUMIERE model and any derivatives thereof may be used freely by users for their own creative purposes. However, all copyrights, legal responsibilities, and social or ethical consequences arising from any images, videos, or other outputs generated using this model remain solely with the user.</li><li>The creation and use of both SFW (Safe For Work) and NSFW (Not Safe For Work, including but not limited to sexually explicit, violent, gory, or otherwise disturbing content) outputs are entirely at the discretion of the user. The developer and distributor of this model bear no responsibility or obligation regarding such content.</li><li>By using this model, the user agrees to take full and exclusive responsibility for any legal disputes, social issues, infringement of third-party rights, defamation, or unlawful acts that may arise. The developer, distributor, and maintainer of this model accept no civil or criminal liability in any such cases.</li><li>The user must comply with all applicable laws and ethical standards in their jurisdiction when using this model. Any consequences resulting from violations of such laws or standards shall be borne solely by the user.</li><li>Under no circumstances shall the developer or distributor of this model be liable for any direct, indirect, incidental, special, or consequential damages arising out of the use or inability to use this model.</li><li>In principle, redistribution of this model by third parties is not permitted. However, if you clearly credit the original creator and notify them of the redistribution, it will not be considered an issue. (We are aware that secondary distribution is currently happening on platforms such as PixAI and modelslab, and we are addressing this matter.)</li><li>Merging this model with other models is allowed, but you must disclose which models have been merged. Detailed ratios or technical specifics are not required.</li><li>You may fine-tune or distill this model. However, you must clearly indicate that the LUMIERE model was used.</li></ul><hr /><h2 id="model-details">ℹ️ Model Details</h2><ul><li>Model Name : LUMIERE</li><li>Model Architecture : <a target="_blank" rel="ugc" href="https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0">Stable Diffusion XL 1.0</a></li><li>Marged Model : <a target="_blank" rel="ugc" href="https://civarchive.com/models/1188071/animagine-xl-40">Animagine XL 4</a> <a target="_blank" rel="ugc" href="https://civarchive.com/models/376130/nova-anime-xl">Nova Anime XL</a></li><li>License : <a target="_blank" rel="ugc" href="https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENSE.md">CreativeML Open RAIL++-M</a></li></ul><hr /><h2 id="prompt-guide">✨ Prompt Guide</h2>LUMIERE uses prompting techniques and methods commonly employed with the most widely used SDXL models. Please refer to the prompting techniques below.<ul><li>Prompt Structure<pre><code>(GENDER), CHARACTER NAME, SERIES, STYLE, SITUATION OR OTHER TAGS, QUALITY TAGS</code></pre></li><li>Quality Enhancement Prompt<pre><code>masterpiece, high score, great score, absurdres</code></pre></li><li>Negative Prompt<pre><code>lowres, bad anatomy, bad hands, text, error, missing finger, extra digits, fewer digits, cropped, worst quality, low quality, low score, bad score, average score, signature, watermark, username, blurry</code></pre></li></ul><hr /><h2 id="recommended-setting">⚙️ Recommended Setting</h2><pre><code>Sampling method : Euler a, DPM++ 3M SDE
Sampling steps : 20 - 40
CFG : 5 - 6</code></pre><hr /><h2 id="model-structure">🔧 Model Structure</h2>LUMIERE was merged and trained using the following structure.<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/1e8765cd-978d-441f-82a5-9618337a168a/width=525/1e8765cd-978d-441f-82a5-9618337a168a.jpeg" /><hr /><h2 id="sponsor">💞 Sponsor</h2>I’d appreciate your support and interest!<a rel="ugc" href="https://coff.ee/backgwa">coff.ee/backgwa</a>

LUMIERE

LUMIERE-Q is built upon LUMIERE, a sophisticated hybrid model combining fine-tuning on SDXL 1.0 with various merged models. This advanced model integrates extensive custom LoRA datasets, enabling the generation of high-quality, bias-free images with remarkable consistency and detail.

Files with SHA256: 2344e234aa1afac04cdc93cdc59590d8049f566f1340c2af0f8eadca1f3aa98b