20 shown - 324 total matches
<p>v1.0 Release SGN Niji XL.</p><p>A high-quality semi-realistic anime checkpoint designed for polished character portraits with refined facial aesthetics, expressive eyes, cinematic lighting, and vibrant color rendering.</p><p>Built on an Illustrious XL foundation, SGN Niji XL delivers clean, consistent results with strong composition, detailed rendering, and exceptional performance in close-up and bust-shot illustrations.</p>
<p>This is a cute cartoon/anime mix style which focuses on the cuteness of the characters' faces, and a colorful art style. The art style is based on my game, Pocket RPG. You encounter different players in card game tournament and can recruit players that you defeat. The combat is unique that you select all of your actions before the combat begins, and th...
ComfyUI Workflow for Z Image Any feedback would be appreciated. 📂 Required Models Diffusion Model: z_image_turbo_bf16.safetensors .../ComfyUI/model...
Turn any video into a perfect lip-synced talking masterpiece. Who it's for: creators who want this pipeline in ComfyUI without assembling nodes fro...
This is my daily workflow for Zit. I think everything is pretty well organized with group bypassers so you only need to run what you need. The Lora...
<p><strong>MiaoMiao Harem Anima base 已上传</strong></p><p><strong>这个版本是去风格化的 MiaoMiao Harem Anima 的基础版本</strong></p><p><strong>对lora兼容性优于MiaoMiao Harem Anima 1.0</strong></p><p><strong>出图参数延续MiaoMiao Harem Anima 1.0</strong></p><p><strong>⚠️ IMPORTANT: Usage Guide / 重要食用指南</strong></p><p><strong>Model Output Parameters</strong></p><p><strong>Scheduler Euler Normal Euler a Normal</strong></p><p><strong>Steps 30</strong></p><p><strong>CFG Scale 4.0-6.0 </strong></p><p>Model Recommended Resolution 920x1536</p><p><strong>Positive Prompt （default ）</strong></p><pre><code>masterpiece, best quality, score_7, safe,very aesthetic, masterpiece, best quality, ultra-detailed,pale_skin,fair_skin, high contrast,huge filesize,{此处添加提示词 Add Prompt here}</code></pre><p><strong>Negative Prompt</strong></p><pre><code>worst quality,low quality,score_1,score_2,score_3,artist name, </code></pre><p>⚡ 二次采样优化 / Secondary Sampling Enhancement：</p><p>高清放大不糊不炸，细节质感全面觉醒！</p><p>针对 <strong>Anima 模型</strong> 在高分辨率二次放大过程中容易出现的 <strong>模糊、发花、线条脏乱、细节崩坏</strong> 等问题，我在 <strong>WebUI Forge Neo</strong> 中反复实测，终于调出了一套更加均衡稳定的二次采样参数方案。 这套设置可以在尽量保留原图角色结构、神态、构图与插画气质的同时，显著提升整体清晰度与细节质感——<strong>放大后不容易糊，不容易花，线条更稳，画面更干净，成图完成度更高。</strong>无论是：•角色立绘•半身插画•卡面封面•壁纸级高分辨率输出•细节要求更高的成稿场景都能获得更舒服的放大效果。</p><p><strong>直接按照下面蓝字链接的参数操作即可，基本就是当前 MiaoMiao Anima 版本较为平衡、稳定、实用的二次采样方案。</strong><a target="_blank" rel="ugc" href="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/2f95ba5a-8182-40c3-8148-3a3132996661/original=true/2f95ba5a-8182-40c3-8148-3a3132996661.jpeg">二次采样参数设置图</a></p>
Model repo on Hugging Face Hub.
<p>使用するモデルを減らしました</p><p>We reduced the number of models used.</p>
Model repo on Hugging Face Hub.
<p>I’ve been working on this version for the past three months. While there are still many areas I want to refine without simply blaming "architectural limitations," what I’ve achieved for Version 3 is a massive leap forward.</p><p>As promised, the changes between versions are substantial—you can clearly see the progress in the comparison images. This isn't just another incremental update; it’s a result of deep R&D and surgical weight tuning.</p>
ℹ️ Babes Kissable Lips 5.0 marks a new direction for the model, bringing it closer to its roots. It features an artistic digital style characterized by a unique visage and proportions. This high-gloss digital portrait model delivers luminous, light-reactive skin and exceptional clarity of detail. It renders characters with a polished, almost crystalline quality - smooth surfaces that catch and reflect light beautifully, creating a sense of depth and vibrancy under dramatic lighting.<br /><br />The model excels at expressive facial rendering, particularly in the eyes and lips, which are depicted with refined shapes, subtle textures, and a strong visual presence. Hair is rendered with rich color, volume, and reflective highlights, while the overall aesthetic blends semi-realistic grounding with stylized elegance, resulting in portraits that feel both intimate and cinematic.<br /><br />Its strength lies in vibrant color work, intricate material rendering, and atmospheric lighting. Whether placed against clean gradients, cosmic scenes, or stylized environments, the model consistently produces images with an interesting, cohesive visual language and a strong sense of crafted beauty.<br />
独创的三步生图法，目的是解决lora、画师tag等对模型生图能力固化的现象，通过多步生成赋予最大的生成操作空间。 这个工作流逻辑简单易懂，包含lora、放大、面部修复，一站式生图。 默认模型仅供测试使用。您可以使用任何您喜欢的模型。 面部检测模型下载地址 Anzhc Face seg 640 ...
<p><strong>Chaotique is a creative-first Duchesse merge focused on versatility, expressive prompting, and stylistic freedom.</strong><br />It handles both simple and complex prompts with ease, excels at artist and style tag blending, and offers exceptional lighting control. More anime-leaning than previous Duchesse models, its core style is intentionally restrained to adapt to a wide range of aesthetics and LoRAs. Built for experimentation, not rigidity.</p>
<p>About this version</p><p><strong>MiaoMiao RealSkin Anima 必看参数</strong></p><p><strong>⚠️ IMPORTANT: Usage Guide / 重要食用指南</strong></p><p><strong>Model Output Parameters</strong></p><p><strong>Scheduler Euler Normal Euler a Normal</strong></p><p><strong>Steps 30</strong></p><p><strong>CFG Scale 4.0-6.0</strong></p><p>Model Recommended Resolution 920x1536</p><p><strong>Positive Prompt （default ）</strong></p><pre><code>masterpiece, best quality, score_7, safe,very aesthetic, ultra-detailed,pale_skin,fair_skin, high contrast,huge filesize,{此处添加提示词 Add Prompt here}</code></pre><p><strong>Negative Prompt</strong></p><pre><code>worst quality,low quality,score_1,score_2,score_3,artist name,simple background,, extra toes,lowres, (bad), text, error, fewer, extra, missing, worst quality, jpeg artifacts, low quality, watermark, unfinished, displeasing, oldest, early, signature, artistic error, username, bad feet,scan, [abstract], english text, shiny hair </code></pre><p>⚡ 二次采样优化 / Secondary Sampling Enhancement：</p><p>高清放大不糊不炸，细节质感全面觉醒！</p><p>针对 <strong>Anima 模型</strong> 在高分辨率二次放大过程中容易出现的 <strong>模糊、发花、线条脏乱、细节崩坏</strong> 等问题，我在 <strong>WebUI Forge Neo</strong> 中反复实测，终于调出了一套更加均衡稳定的二次采样参数方案。 这套设置可以在尽量保留原图角色结构、神态、构图与插画气质的同时，显著提升整体清晰度与细节质感——<strong>放大后不容易糊，不容易花，线条更稳，画面更干净，成图完成度更高。</strong>无论是：•角色立绘•半身插画•卡面封面•壁纸级高分辨率输出•细节要求更高的成稿场景都能获得更舒服的放大效果。</p><p><strong>直接按照下面蓝字链接的参数操作即可，基本就是当前 MiaoMiao Anima 模型 系列较为平衡、稳定、实用的二次采样方案。</strong><a target="_blank" rel="ugc" href="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/2f95ba5a-8182-40c3-8148-3a3132996661/original=true/2f95ba5a-8182-40c3-8148-3a...
<p><span style="color:rgb(130, 201, 30)">Starting with v0.25, this model has completed the alpha testing phase. </span>Settings and features will be stable, it will be a 12-step dmd2 model. Therefore, this page has been completely rewritten. If you are looking for information about older versions, refer to this <a target="_blank" rel="ugc" href="https://c...
Model repo on Hugging Face Hub.
Model repo on Hugging Face Hub.
ℹ️ <strong><u>Babes 1.2i13 Illustrious</u></strong> marks a refined evolution in the series, now grounded in the Illustrious architecture. This version enhances fidelity, subject framing, and compositional clarity while expanding the range of colors and refining body proportions and facial harmony. The signature Babes aesthetic remains beautifully intact - luminous, polished, and artistically expressive - but now feels even more precise, balanced, and visually cohesive.<br /><br /> Visually, the model creates radiant, high-fidelity portraits with softly sculpted features, luminous skin tones, and gracefully expressive faces. Colors bloom with rich yet harmonious saturation, from jewel-like accents in hair and attire to natural, flattering lighting that adds depth and dimension. Linework stays crisp and elegant, backgrounds gain subtle storytelling detail, and overall compositions feel cinematic and thoughtfully framed, inviting the viewer into each scene with warmth and quiet sophistication.<br /><br /> Babes 1.2i13 Illustrious captures the essence of modern digital artistry at its most refined: elegant, vibrant, and full of life. It excels at fashion-forward concepts, fantasy-inspired narratives, and serene character studies alike, delivering a premium aesthetic that feels both timeless and alive. Whether you seek graceful elegance or creative storytelling, this version offers a versatile and captivating visual language.
Transforms visuals and audio into intelligent, coherent text outputs fast. Who it's for: creators who want this pipeline in ComfyUI without assembl...
Creates portraits with real human skin texture and natural lighting. Who it's for: creators who want this pipeline in ComfyUI without assembling no...
