FUBUWA MIX 3D REAL

*Showcase images include embedded workflow and are post-processed with sharpening and noise grain.In other words, your results may vary depending on your workflow.Recommended settings are below.Version featuresRather than improvements, each version has their own strengths.v1.1 - Most realisticv1.2 - Semi realistic - sometimes include outlinev1.33 - Slightly less realistic than 1.1 in exchange for better lighting/composition/prompt adherence. Version notesv1.33Focus on keeping realism while improving composition, background and lighting compared to v1.1.Less creative/aesthetic than 1.2 in terms of background.v1.2More focus towards semi realism *includes outline at certain timesBetter lighting, composition, background, aestheticStructure feels more stable compared to v1.1Model focus3DCG features with more detailed skin texture. (Heavily dependent on heun sampler, not recommended if using web generator or if you don't know what you're doing)Face proportions closer to real life. Less anime like.Strength/QuirksFacial features can respond to promptsWeaknessWill do beauty mark/mole under eyeSkin pores can look too smooth/uniform/unnatural texture depending on sampler/scheduler.Backgrounds (res_multistep + normal with high steps 50-100 - has chance to resolve scale issues but might introduce artifacts) (better in version 1.2 and above)Recommended settings(can see workflow via uploaded images)initial samplerres_multistep + normal/simple steps 30-100, cfg 3.5fast, reliable but slightly boring/simplistic resultsdpm_adaptive + exponential steps doesn't matter since adaptive, cfg 4.5slower but very reliable without much errorsupscale/hiresfixrealesrgan_x2 (only because it's fast - don't think it makes a big difference which ever used)heun + normal/ddim_uniform(second choice)steps 15-20, cfg 3, denoise 0.35-0.55using heun+normal as the upscale/hiresfix is what brings out the noise/texturefacedetailerheun + normalsteps 10, cfg 2.5, denoise 0.25-0.4Remarksres_multistep is fast and converges at high steps, fixes the structural problems 90% of the time.usual euler/2m/3m + sgm uniform/normal/karass should work thoughi prefer heun as it produces natural noise/texture at lower step values and loses it at higher (recommended schedulers: normal/ddim_uniform/ays+)for prompt adherence: higher resolution can have lower cfg, lower resolution need higher cfgpersonal frequently used resolution before upscale: 896x1120 or 1152×1440 (more pixels = more space for details like hands)post-processing nodes with sharpening, bloom, grain, tone curves for more texture in final image. (see workflow in images)