How to Use Style References (--sref) in Midjourney V8.1

Add --sref to the end of your prompt, give it a style source, and Midjourney V8.1 renders your subject wearing that aesthetic — its palette, lighting, texture, and finish — while your prompt keeps the subject. The style source can be one or more image URLs, one or more numeric codes, or a blend of both. That is the whole mechanism. The craft is in which source you pick, how many you stack, and how hard you let the style push, and V8.1 changed enough defaults that older habits need a refresh.

V8.1 became Midjourney's default model on June 10, 2026. It renders roughly four to five times faster than earlier versions and can render HD — native 2048×2048 — with --hd or the HD setting, with no separate upscale step. (V8.2 followed as the default on 24 July.) Most relevant here: Midjourney describes srefs and moodboards in V8.1 as exceptionally stable, which is what lets a single style reference carry a whole series instead of quietly drifting subject to subject. This is the hands-on walkthrough; for the conceptual map of what a style code actually is, the complete sref guide is the pillar.

The two ways to pass a style reference

1 · Image reference — the modern default

Paste one or more image URLs straight after --sref. Any direct image link works (a link ending in .png, .jpg, or .webp), but the most common source in practice is a Midjourney-hosted s.mj.run link — the short URL Midjourney mints for an image you generated or uploaded. These are personal and temporary, so they belong in your prompt history, not in a shared swatch book. Midjourney reads the image purely as a style guide: it borrows the look, never the subject.

2 · Numeric style codes

Numeric srefs still work in V8.1. There are 2³² of them — every integer from 0 to 4,294,967,295, about 4.3 billion distinct, repeatable aesthetics; drop one after --sref and you get the same style on any subject. One compatibility rule trips people up: Midjourney's docs say numeric codes and --sref random only work with style versions --sv 4 and --sv 6. So if you feed a number, pin --sv 4 or --sv 6.

That code is from the free set in our sref guide: the woodcut sun of Celestial Decree, made on niji 7.

Image references behave differently from codes in one important way: an image is an interpretation of a specific picture, while a numeric code points at a fixed style vector. Codes are therefore more consistent across runs — which is exactly why people collect them. But image refs let you chase a look you already made and love, with no number to discover. Most real V8.1 work uses image refs.

A real V8.1 prompt, decoded

Here is an actual portrait generated on V8.1 with image references. The prompt below is real; its two style references show as [style reference], because their codes are kept, locked, on the image's decode page. Open the image to read its full decoded style DNA.

Afrofuturist Cybernetic Portrait

Note the caption: this image actually stacked nine references. We're showing two of them — proof that you are not limited to a single style source.

Stacking multiple references

List several sources after one --sref, space-separated, and V8.1 blends them into a composite style. The real images behind this guide go deep on this — one in the set stacked twelve references into a single coherent look. You can mix freely: two image URLs, a URL plus a code, three codes. To bias the blend, append relative weights with the double colon. Midjourney documents these per-reference weights for style references; its docs don't name a version, so test them on V8.1:

Stacking is how you invent a finish no single reference gives you. The discipline: many references pulling in compatible directions compound into richness; references fighting each other average into grey mud. The twelve-ref image works because every source shares a tonal world. Use weights to let one reference lead rather than letting five sources cancel out.

One reference set, a whole family

The real payoff of style references is series consistency. Both portraits below were generated from the same two references on different subjects. The Gongbi linework, mineral pigment palette, gilded filigree, and auratic halo carry across both because the style source stayed fixed while the prompt changed. Stable srefs are what make this repeatable instead of a lucky roll.

Esoteric Buddhist / Gongbi Family

Style weight: --sw

--sref chooses which style to borrow; --sw controls how hard it asserts itself over your prompt. It runs 0–1000 and defaults to 100. For subject-led shots where you want a light flavoring, 50–100 is plenty. For a strong, brand-locked look, 150–300 is the working band — and the real images in this set push further, sitting at --sw 300 for the cyber portraits and --sw 500 for the Buddhist family, where the style is meant to dominate the rendering.

Reach for --sw when a style is "almost right" but too faint or too loud — lower it when the reference eats your composition, raise it when the look won't come through. The full tuning playbook is in the style weight guide.

The V8.1 parameters worth knowing

Style references travel with a handful of other dials. Order among parameters doesn't matter — they just have to come after your subject text, and the version tag goes last by convention.

One Strong Reference Is Often Enough

Three rules that quietly break renders

• Two real hyphens, no space:--sref. Pasting from a doc or chat often converts -- into a "smart" em-dash (—), which Midjourney silently ignores. If a reference seems to do nothing, retype the dashes.
• URLs must point at the image file itself — a direct .png/.jpg/.webp link or an s.mj.run link — not a web page that merely displays the image.
• Numeric codes need a compatible --sv. Codes and --sref random only fire on --sv 4 or --sv 6. If a number gets ignored, your style version is the likely culprit.

The honest part: you can't extract a code from your image

A numeric sref is a coordinate in style space — a random seed that maps one way only: number → style. There is no reverse function. You cannot hand Midjourney an arbitrary image and get back "the sref that made it," and any tool claiming otherwise is bluffing. What's real and useful is the other direction: take an image whose look you want, read its style precisely, then find references that reproduce that feel.

Decode an image →

Google sign-in. 5 credits on sign-up, enough for your first decode.

Keep reading

• Midjourney style codes explained — the complete conceptual sref guide.
• --sref vs --cref vs the omni reference — pick the right reference parameter for the job.
• Best Midjourney sref codes for 2026 — a curated, regularly updated set.
• Midjourney --sw style weight — tune exactly how hard a style hits.
• Browse decoded styles — find a style that matches your reference.