A realistic model, built for quality and creative range.
ze·nith
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 Mobius 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 here.
Recommended Settings
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.
• Sampler: DPM++ 3M SDE
• Scheduler: AlignYourSteps
• CFG: 3-4 (or use Automatic CFG)
• Steps: 30-40
• Clip Skip: -2 or -3
• Aspect Ratio: 1:1, 2:3, 3:4, 16:9, 21:9, vertical or horizontal
Advanced Settings
• FreeU v2
• b1: 1.05
• b2: 1.08
• s1: 0.95
• s2: 0.8
• Perturbed Attention Guidance
• Scale: 0.5-1
• Adaptive Scale: 0.1
• Automatic CFG
How to prompt this model
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 custom GPT to help with this. By default, it will generate CLIP-G style prompts, but