← all video builds ~/builds $ ./mirage-blend-build.py --render

Spinning coins. Blend modes. Subject on top.

A spinning-mirage × blend-overlay loop. The underlay stays static while a halftone mesh of spinning coins — sized inversely to the light volume — blends over it with soft-light, multiply, or overlay, and the background-removed subject + drop shadow sit on top. 1080×1080, 30fps, seamless 3s loop.

soft-lightmultiplyoverlay3s loop

mirage-blend-build — sample output · 3s

● autoplay · muted · seamless loop — the exact file you receive the recipe for 1080×1080 · 30fps

Unlock free — 22s sponsor view → See the GIF

examples

The loop, as a GIF.

A share-ready GIF of the mirage blend build — rounded corners, seamless 3-second loop. Perfect for a feed, a pin, or a message.

Mirage Blend build — animated GIF example — mirage-blend-build.gif · rounded · loops forever · 1080×1080 · 30fps

what this build is

The cleanest look in the set.

One still, three blend modes, a cut-out subject and a drop shadow — the purest expression of the halftone-mirage style, built for seamless 3-second looping.

Light-volume halftones

Coins are sized inversely to the image's light volume, so the lattice follows the highlights and shadows.

Three blend overlays

soft-light, multiply, and overlay — each changes the whole mood of the same source image.

Subject cutout + drop shadow

Background-removed subject composited on top with a drop shadow (no outer glow) for depth.

Seamless 3s loop

Designed to loop cleanly — perfect for Reels, Stories, and profile-grid posts.

how it works

From still to spinner.

A deterministic four-step pipeline. Build the lattice, spin it, blend it, and composite the subject on top.

01 lattice

Build the halftone lattice from the source image's light volume.

02 spin

Per frame: spin the coins in a staggered wave, flip at the edge.

03 blend

Blend the halftone layer over the underlay with soft-light / multiply / overlay.

04 composite

Subject cutout + drop shadow on top → ffmpeg muxes → mirage_ex1_soft_light.mp4.

what's inside

The .md build guide.

You're getting a downloadable .md build file written for AI agents (and humans). It contains the full recipe, the exact dependencies, the run command, and every knob to tune — plus the finished sample video is embedded above so you can see exactly what it produces.

mirage-blend-build.md

the downloadable guide — full recipe, dependencies, run command, every knob (this is the file you buy)

animate_blend_mirage.py

the build script (the recipe, in code)

mirage_ex1_soft_light.mp4

finished sample output — 3s seamless loop (shown above)

source_female_2.jpg · subject_female_2.png

example input image + background-removed subject cutout (replace with your own)

neon_arrangements.py · neon_halftone.py · pfp_halftone_subject.py

shared halftone glyph / icon / intensity-map helpers

output

1080×1080 · 30fps · 3s seamless loop · H.264

halftone

mesh lattice of spinning coins sized inversely to light volume

blends

soft-light / multiply / overlay

composite

background-removed subject + drop shadow (no outer glow)

dependencies

Python 3.10+, numpy, Pillow, ffmpeg on PATH

compare & contrast

Chinchilla build vs. Higgsfield AI models.

Our builds are deterministic code — the same recipe renders the same frame every time. Higgsfield's lineup (Seedance 2.0, Kling 3.0, Veo 3.1, Soul, Marketing Studio) is generative AI — diffusion and transformer models that sample new pixels each run. Different tools, different jobs.

dimension

this build

higgsfield ai

How it renders

Code-authored. numpy + Pillow + ffmpeg draw every frame. Same input → same output, version-controllable.

Diffusion / transformer models sample new pixels each run — no two renders are identical.

Control

Per-pixel. Edit a constant (wave speed, grain, blend mode) and re-render the exact change.

Prompt + seed steering. Interpretive; you guide the model rather than specify frames.

Identity & subject

Your actual asset. The real photo / subject cutout stays pixel-faithful; zero identity drift.

Soul Characters and reference images keep identity, but generative output can drift; or it invents people who don't exist.

Brand lock

Baked in. Fonts, palette, layout and motion are exact brand tokens in code.

Brand look is approximated via prompt; Marketing Studio adds product/avatar retrieval for ads.

Cost model

Free to unlock — a short sponsor view sized to the render workload releases the recipe, then free local renders forever.

Per-generation credits / API cost on every video you produce.

Speed

Seconds to minutes locally, batchable, no queue.

API job queue — minutes per render, rate-limited by account.

Output style

Graphic motion. Halftone, typographic and blend-mode loops tuned to music.

Photoreal, cinematic, or stylized AI footage — scenes, actors, b-roll.

Best for

Portrait and persona content — artist/creator promo loops, profile-picture animation, and on-photo overlays that keep the real subject front and center.

Footage that doesn't exist, actors & avatars, ads with people, net-new b-roll.

They're complementary. Generate the hero asset with Higgsfield, then feed it into a Chinchilla build to make it an on-brand, loopable, music-synced social video you can re-run every day.

Get the Mirage Blend build.

Free download. Unlock the mirage-blend-build.md guide with a short sponsor view — the same recipe that renders the video above. Paste it into any AI agent and it can rebuild, remix, and re-skin the effect for your own content.

downloadable .md for AI agents instant delivery

free no account · unlocked by a sponsor view

Unlock the .md →

22s watch time — scaled to this build's render workload (181 units), capped at 60s