20 shown - 209 total matches
I just made a new Telegram Group and Discord group drop in for chats, questions, feedbacks or just to share your work. 欢迎加入 纸飞机 和 Discord 群组。 喜欢我的作...
Optimized Low-VRAM Workflow for Z-Image-Base (GGUF) Refined version of my ZIT workflow, modified to work with ZIB This workflow delivers the full p...
<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>
Very simple, but it works quite well. I don't like the original workflow form by comfyui_stereoscopic's authors, so I built my own. Be aware that t...
<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...
GOONERS REJOICE LTX-2.3 Sulphur (NSFW MODEL) Distil Workflow — Installation Guide This workflow runs on smthemex's ComfyUI_LTX2_SM custom node pack...
You can get this model, along with many others, by joining The Tinkerer on Whop. It’s one monthly membership, and you’ll also get early releases, p...
<p>ℹ️ Five Stars Illustrious 11 represents a graceful new milestone in the Five Stars lineage, centered on enhanced stability, refined framing, and superior overall quality. This iteration delivers greater compositional harmony and visual consistency, allowing every creation to emerge with natural balance, intentional structure, and a quietly confident presence that feels both polished and effortless.</p><p>The model's signature luminous aesthetic shines through in radiant, light-kissed skin, expressive and delicately sculpted facial features with captivating eyes, and voluminous, intricately detailed hair that flows with graceful movement. Vibrant yet sophisticated color palettes blend seamlessly with cinematic lighting and richly atmospheric backgrounds, crafting immersive scenes filled with depth, elegance, and quiet wonder.</p><p>Above all, Five Stars Illustrious 11 offers creators a high-fidelity digital canvas where beauty, technical refinement, and artistic intention unite in harmonious, captivating imagery - an evolution that feels both familiar and freshly elevated.</p>
<p>2026.5.20</p><p>Updated V3 with: </p><ul><li><p>Softer and rounder face shapes</p></li><li><p>Improved lighting and glossy shading</p></li><li><p>Better overall consistency and cuteness</p></li><li><p>Cleaner fur details and smoother rendering</p></li></ul><p>Hope you enjoy 🐾</p>
<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>
flux-1-dev-non-commercial-license
Model repo on Hugging Face Hub.
Hello Community, Several users asked for my workflow, so I decided to share it with everyone. Maybe it will be useful for some of you as well. Firs...
<p>Features</p><ul><li><p>RE looks with EX posing</p></li><li><p>High expression / lighting capability</p></li></ul><p>NoobAI EPS v1.1 + Illustrious v2.0-stable + ChenkinNoob v0.5 DARE applied</p>
flux-1-dev-non-commercial-license
I just made a new Telegram Group and Discord group drop in for chats, questions, feedbacks or just to share your work. 欢迎加入 纸飞机 和 Discord 群组。 RH 体验...
Model repo on Hugging Face Hub.
Model repo on Hugging Face Hub.
flux-1-dev-non-commercial-license
flux-dev-non-commercial-license
