Midjourney multi-sref weight mixing recipe for cinematic light & motion portraits
michaelrabone · x · 2026-10-16
michaelrabone shares a Midjourney "Style Mix" recipe for cinematic portraits: stack five sref style codes with weights (::4 ::3 ::2 ::2) plus --raw, --stylize 150 and --ar 3:4, producing motion-blurred, warm-lit results that closely resemble real film photography (demos use Leonardo DiCaprio and Robert Downey prompts). The key reproducible trick is weighted multi-sref blending for richer cinematic light than any single style ref.
More from Multimodal
- Snap Spectacles + Gemini 4 Argon demo designs LEGO builds from your brick pile — stspanho · 2026-10-16
- Stanford paper: generative representation learning cuts tokenizer training compute by 7-8x — HirokatuKataoka · 2026-10-16
- AI Image Gen Forces You to Verbalize Visual Intuition: Smoky Velvet Noir Prompt Template — LudovicCreator · 2026-10-16
- UniForge3D open-sourced: joint 3D reconstruction and generation from sparse unposed views — camenduru · 2026-10-16
- Seedance 2.5 Pricing Varies Up to 3-4x Across Providers — videorouter · 2026-10-16
- Seedance 2.5 demo: collapsing-city disaster chase with the prompt shared — umesh_ai · 2026-10-16