Invite-only betaLook first · Pay per step

Zero commitment. Explore the tools. Get what you want — for your game, your learning app or your campaign.

Chain the AI tools that make images, 3D models, rigs and voices into one workflow. See what each step costs before it runs, and get the finished files in your repo — or ready to download.

No account to look around. No subscription to make. Credits from $5, and 250 free credits when your invite comes.

Saves to GitHub or GitLabAsk the assistant, or set the steps up yourselfWorks from code too · API · MCP
Steps, as charged
  • Character concept3.25 crFLUX.1 [dev]
  • Pixel sprite1.30 crRetro Diffusion
  • 3D mesh19.50 crTripo
  • Style read from a picture0.12 crClaude
  • Rig16.25 crTripo
  • Isometric sprite3.31 crRetro Diffusion
  • Vehicle mesh10.40 crTrellis
  • Voice line0.29 crElevenLabs
  • Prompt per vehicle0.04 crClaude
  • Walk animation6.50 crTripo
  • Icon cut-out0.65 crBiRefNet
  • Line written and spoken0.17 crClaude, ElevenLabs
  • Vehicle image3.25 crFLUX.1 [dev]
01 · Just ask

Say what you want.
It sets up the steps.

Not sure which model to pick, or how to wire one step into the next? Tell the assistant what you need, in your own words. It works out the steps, picks models we have actually tested, and tells you what a run will cost.

  • Nothing runs until you press Run. It sets things up and offers. You decide.
  • You see the price first. An estimate before the run, the real charge after.
  • It remembers your house style. Only if you ask it to — and you can see and delete what it keeps.
  • You can take over at any point. What it sets up is an ordinary workflow: open it, change it, or run it again.

Working in Claude Code or Cursor? Your agent can use Sushibelt’s tools over MCP — new in October, and no outside agent has connected yet. For developers

Request an invite→
Team assistant

Describe what to make, or attach a picture to match. Each request becomes its own agent; nothing runs until you say so.

Describe the asset you want and I’ll suggest a workflow.

What to make — attach or paste a picture to match…

This assistant is an AI model. Check what it suggests before you run it.

A replay of a real exchange. Someone asked for a low-poly fox knight sprite on a transparent background. The assistant read the brief, set up four steps — the description, making the picture, removing the background and showing the result — saved them, and offered to run them for about 3.3 credits. It ran only when the person pressed Run. The conversation itself cost 9.51 credits.

Replayed from a real exchange on our test build, 5 Oct 2026. Asking cost 9.51 credits; the run it set up cost 3.3. The picture it made isn’t shown — that build didn’t keep it.

02 · The line

Open it up. Change any step.

Whatever the assistant sets up, or you wire yourself, is a workflow you can open. The brief goes through a model that draws, one that turns the drawing into a 3D model, one that rigs it and one that speaks — each one you picked — and comes back as a concept, a mesh, a texture and a line of dialogue that belong to the same character.

Change the model at any step and the rest carries on unchanged. Compare five on the same words before you settle on one.

see a workflow end to end →
A real run · 18 Sep 2026See the whole run →
Your description

“A hooded ranger with a longbow and a wolf-pelt cloak, full body, single character, game asset, neutral background.”

stays the same every time

You write this
Paint a concept

A picture, then a 3D model of it

using FLUX.1 [dev] · Fal

style Adone
about 13.65 credits
The result
Painted concept of a hooded ranger in a grey fur-collared cloak and leather straps, holding a longbow, on a pale background.
Concept painting1024×1024 px
Saved straight into the game project9 saves, made by the run itself — not copied over by handStyles A, B and E were also turned into 3D models, so their cost covers both; C and D are finished as flat pictures.
More of thisa real run · 18 Sep 2026
A die-cast toy dune buggy in silver and bronze with a dark red roof and chunky tyres, on a plain background.

Your picture

A toy buggy. Looked at once — 0.12 credits.

  • A full-size rally hatchback in bronze and dark grey, photographed on a pale floor.
    Rally hatchback13.69 cr
  • A full-size panel van in bronze and grey with a roof rack.
    Panel van13.69 cr
  • A monster truck in bronze with huge black tyres, seen from the front.
    Monster truck13.69 cr
  • A copper-coloured 1930s hot rod with an exposed engine.
    1930s hot rod13.69 cr
Each one is a picture and a 3D model, saved into the game project.54.88 credits, all four

Where it fell short: it copies what the picture is described as, not the picture itself. The buggy was a toy, the description never said so, and the four came back full-size. The whole run →

03 · More of this

Upload one thing you like. Get the rest of the set.

Drop in a picture of something you like and the line makes more things in the same look. One toy buggy in; a rally car, a van, a monster truck and a hot rod out — each as a picture and a 3D model.

Built for prototypes and games where everything looking like it belongs together matters more than any one piece being perfect.

see a real Style Match run, and where it fell short →
04 · Where it lands

The files land in your repo.

The run’s own delivery step commits each finished file to the GitHub or GitLab branch you name — next to the rest of your game, with its history. Nobody downloads anything or copies it over.

Style Finder and Style Match made seventeen commits into a Unity project that way — pictures, 3D models and a spoken line, nothing placed by hand.

Plugins that bring runs straight into Unity, Godot, Blender and Unreal are being tested, and not yet published. What exists

see both runs, and where they fell short →
A 1930s hot rod in polished copper with an exposed chrome engine and flame decals, three-quarter front view on a white ground.
The picture
A render of the hot rod's 3D mesh as the run delivered it — red and copper, chrome engine, flame decals — with a stray sliver of geometry by the front wheel.
Its 3D model
One vehicle as Style Match committed it: the picture, and its 3D model rendered as delivered — one mesh, 18,294 triangles, with a stray sliver by the front wheel.
Every step on the bill

See what every step cost.

Here is one real run, line by line: what each step made, which model made it and what it charged. Before you run anything you see an estimate; after, the real charge — and where a run fell short, we say so.

The bill for one runa real run · 21 Sep 2026

What went in

“Aelin, a half-elf ranger in weathered brown leather with a green hooded cloak, dark hair with one white streak, a scar through the left eyebrow, sharp green eyes, a longbow on her back.”

Some of what came out

  • Aelin, a half-elf ranger in brown leather and a green hooded cloak, full body, facing forward.
    The look
  • Aelin from behind, showing the cloak and the quiver.
    Back
  • A flatter, cel-style icon of Aelin on a clear background.
    Icon

Thirteen assets in all — every one on Discover with the step that made it.

What each step charged

  • Nine images, 3.25 eachFLUX.1 [dev] on Fal29.25
  • Icon cutoutBiRefNet on Fal0.65
  • 3D meshTripo19.50
  • RigTripo16.25
  • Walk animationTripo6.50
  • Voice lineElevenLabs0.29
Total, one run72.44 credits

A credit is a cent — about $0.72.

Where it fell short: the 3D model is heavy — 101,050 triangles, far over a mobile budget — and nobody checked the rig or the walk beyond the steps finishing. Everything that fell short →

From code

Works without the UI

Any HTTP client — a CI job, a Unity editor script, an agent like Claude Code — starts a run with a team API key via POST /api/v1/workflows/:id/runs. Same audit trail, no browser — though from code, image steps run on your own Fal or Replicate key for now. AI agents that speak MCP can connect too — that server is new as of October.

for developers →
What it costs

No subscription required

Credits from $5, spent step by step. Each run shows what every step cost — estimated before, charged after. No seat fee. A monthly plan is optional: it adds bonus credits and more storage.

browse real outputs on app.sushibelt.ai →

Want in?

The beta is invite-only, and we let teams in a few at a time. Leave your email and we’ll send an invite when one is free.

We only use it for the invite. Privacy