<h1 id="a-realistic-model-built-for-quality-and-creative-range.-jn862oe3i">A realistic model, built for quality and creative range.</h1><h3 id="zenith-9oqt108ut">ze·nith</h3>noun. the time at which something is most powerful or successful.RobMix Zenith is the next iteration on my series of artisan photorealistic model merges with unnecessarily superlative version names.This merge is like a classic martini—simple, with just a couple of ingredients, but mixed with precision and handled with care. It blends RobMix Evolution with Corcel's fantastic <a target="_blank" rel="ugc" href="https://huggingface.co/Corcelio/mobius">Mobius</a> base model, with block-by-block tuning to draw out the best of the RobMix style with the best of Mobius' quality and creativity.Note: Mobius requires a clip skip of -3. This merge doesn't, but you can get some interesting results by experimenting with clip skip values between -1 and -3.Like my other merges, it's geared toward a photographic style with an emphasis on balancing realism with creativity, but also has some gems with illustrated or artistic styles if you prompt for them.This model works great as a plug-and-play model out of the box, but it shines with some workflow optimizations. I've made some suggestions at the end of this post, and you can try them out with my workflows <a target="_blank" rel="ugc" href="https://github.com/roblaughter/comfyui-workflows">here</a>.<h3 id="recommended-settings-hsd2kpn1d">Recommended Settings</h3>In the sample images, second pass is a 1.5x latent upscale, 0.3 to 0.4 denoise, 40 steps. Everything was generated in Comfy.<ul><li>Sampler: DPM++ 3M SDE</li><li>Scheduler: AlignYourSteps</li><li>CFG: 3-4 (or use <a target="_blank" rel="ugc" href="https://github.com/Extraltodeus/ComfyUI-AutomaticCFG">Automatic CFG</a>)</li><li>Steps: 30-40</li><li>Clip Skip: -2 or -3</li><li>Aspect Ratio: 1:1, 2:3, 3:4, 16:9, 21:9, vertical or horizontal</li></ul>Advanced Settings<ul><li>FreeU v2<ul><li>b1: 1.05</li><li>b2: 1.08</li><li>s1: 0.95</li><li>s2: 0.8</li></ul></li><li>Perturbed Attention Guidance<ul><li>Scale: 0.5-1</li><li>Adaptive Scale: 0.1</li></ul></li><li><a target="_blank" rel="ugc" href="https://github.com/Extraltodeus/ComfyUI-AutomaticCFG">Automatic CFG</a></li></ul><h3 id="how-to-prompt-this-model-rr7c5x365">How to prompt this model</h3>This model works best with natural language style prompting. I've gotten the very best results by separating CLIP-G and CLIP-L, using natural language in CLIP-G and SD 1.5-style keyword based prompting in CLIP-L.I've created a <a target="_blank" rel="ugc" href="https://chatgpt.com/g/g-OndbVJ3Et-image-prompt-generator">custom GPT</a> to help with this. By default, it will generate CLIP-G style prompts, but you can optionally ask it for CLIP-L and/or T5 style prompts. The GPT follows my <a target="_blank" rel="ugc" href="https://www.youtube.com/watch?v=fqjW-ZGG-gQ">Prompt Pyramid</a> style of prompting, which may not be the best, but it's how I do things.Example CLIP-G*<pre><code>A high-resolution, atmospheric photograph capturing a serene sunset over a mountainous landscape. The composition features a lone tree standing on a hillside, silhouetted against the warm, golden light of the setting sun. The sky is a gradient of soft oranges and yellows, blending into the horizon. Rays of sunlight stretch across the scene, creating long shadows and adding depth to the rolling hills. The overall mood is peaceful and contemplative, with a harmonious balance between light and shadow. The exposure is perfectly balanced, emphasizing the natural beauty and tranquility of the landscape.</code></pre>* If your prompt exceeds 75 tokens, be sure to properly handle concatenation.Example CLIP-L<pre><code>High-resolution photograph, young woman, leaning out of vintage red car window, arms crossed on door, head tilted, calm contemplative expression, curious gaze, engaging connection, framed upper body, smooth vintage vehicle lines, nostalgic feel, softly blurred background, serene reflective mood, muted warm tones, timeless quality.</code></pre>

RobMix

Recommended SettingsI generally use:<ul><li>DPM++ SDE 3M Karras</li><li>40 steps</li><li>CFG 7-10</li></ul>Second pass is a 1.5x latent upscale, 0.3 denoise, 40 steps. Everything was generated in Comfy or StableSwarmUI.Recommended PromptsThis model works great with short prompts, and tends to follow longer prompts fairly well. I haven't really tried word salad SD 1.5 style prompts with it, so your mileage may vary.I like to use phrases like dark, contrasty, and underexposed because I think they look particularly crispy.No negative prompts are required. The only thing I occasionally use are painting, illustration if I want to push it a bit further toward photorealism.All of the sample images are unedited, fresh out of the oven.About This ModelThis is my first — and maybe my only — model merge.I spent the last few weeks mashing up some of my favorite photorealistic models and LoRAs into a big messy ball, and after six iterations or so, something cool popped out. So I wanted to share.I wish I could remember what all went into it, but I wasn't keeping track because I didn't plan to make something I'd unleash on the world.I was initially training it as a photorealistic model for human portraits, but it's proven to be insanely good across a wide range of styles and mediums, including abstract ideas.Subject matter range is excellent. It has a diverse range of photographic styles — nature, portrait, candid, astro — and camera angles/focal lengths — telephoto, ultrawide, close, wide, macro, etc. I'm a photographer, so that makes me happy.Because it's intended to produce images with a photographic style, prompts for things that are typically 2D (such as drawings, anime, etc.) tend to get a bit of "pop." If you don't want that, you may be better off with a model that's better aligned with that style. It's kind of cool, IMO.For aspect ratios, it works great up to 21:9, both horizontally and vertically, without many of the typical issues of doubling subjects, horror show anatomy, etc. Obviously, if you cram a portrait into a 9:21 vertical pano, you might get some weird results.It's capable of making less than perfect looking people. Hands are pretty good. And it can actually crank out some usable text, which was a fun bonus.

Files with SHA256: 9ebd01f6c27b59fe3d4d4d8298106dfbca133bdc7cd711bf04cee3cbfa03c58e