A Midjourney style workflow uses GPT breakdowns to narrow hundreds of image references
beechinour · x · 2026-07-28
- The post says Midjourney’s Style Creator is unusually powerful.
- The workflow described is to gather lots of reference images, ask GPT for a detailed breakdown, then upload both the breakdown and the images into Midjourney.
- Style Creator can surface hundreds of candidate images, and the author recommends choosing the 5–10 closest matches.
- The post also shares a saved style reference ID: --sref 4940438934.
More from Multimodal
- OrcaDub 1.0 launches speech-to-speech video dubbing with 4.83 MOS — qinzytech · 2026-07-28
- Kinetic Abyss shows a 2D animation made with Stable Audio 3 and LTX 2.3 — Tadeo111 · 2026-07-28
- How to turn reference photos into a convincing impasto oil-paint workflow — Suspicious-Koala-570 · 2026-07-28
- Krea2 Detail Enhancer LoRA Removes AI Fog Blur for Crisp Images — linoy_tsaban · 2026-07-28
- Creating a 2000s Pop-Punk Music Video Using Runway and Suno — notiansans · 2026-07-28
- Fooocus Advanced adds SAM3 masking, faster VRAM handling, and SDXL upscaling — EldrichArchive · 2026-07-28