Never pay twice for the same AI render.
Atlas is a free tool for people who generate AI images and video. It remembers every render you make — so when you tweak one shot, only that shot rebuilds and the rest is instant and free. If a GPU dies mid-run, it resumes where it stopped. And it tells you the cost before you spend a cent.
$ atl render main t2i@1 2df0… running done t2i@1 2df0… → 81a4… 1.2s $0.03 i2v@1 9fef… running done i2v@1 9fef… → 1b47… 38s $0.36 2 tasks executed, 0 cached, $0.39 spent $ atl render main # run it again — nothing changed 0 tasks executed (all cached) · $0.00 spent
Rendered once for $0.39. Run it again with nothing changed and Atlas serves every frame from cache — $0.00. That gap, across every tweak and retry, is the whole point.
AI generation quietly bleeds
money and hours.
If you make images or video with AI, you've lived at least one of these.
“I fixed one shot in a 60-shot batch — and paid to regenerate all sixty.”
Wasted spend“The rented GPU crashed at 90%. Three hours of renders, gone with it.”
Lost work“The bill came back triple my guess — and I had no way to see it coming.”
Surprise invoicesAtlas is built so you never feel any of them again.
Three problems, gone for good.
Not settings you configure or remember to switch on — this is simply how Atlas works, every time.
You never render the same thing twice
Atlas fingerprints every render. Change one input and only that piece rebuilds — everything identical is served from cache, instantly, for $0. Paying twice for the same frame simply can't happen.
A dead GPU never costs you progress
Every run is saved as it happens. When a machine crashes or you stop it, one command picks up exactly where it left off. Hours of finished renders stay finished — no starting over.
You see the price before you pay it
Set a budget. Atlas shows the full cost up front and refuses to spend past your limit. The bill is never a surprise, because you approve it first.
Same renders. Half the pain.
✕ Without Atlas
Every workflow you use today
- Re-run the whole batch to fix one shot — and pay for all of it again
- A crash wipes hours of finished renders
- Guess the cost, then flinch at the invoice
- No record of which settings produced which result
✓ With Atlas
The same work, made accountable
- Only the shot you changed rebuilds — the rest is instant and free
- Resume from the exact moment a run stopped
- See the full price up front; never spend past your budget
- Every result traced to its exact recipe, seed, model and cost
Describe what you want.
Atlas handles the rest.
Describe the work as recipes
Text-to-image, image-to-video, compositing — a graph of content-addressed recipes, by hand or from the Python Director's DSL.
Set a budget, see the plan
Open an envelope, run atl plan. You get the exact task list and a P90 cost estimate before anything spends.
Render — cached, resumable, accountable
Atlas runs only what's missing and records every artifact's model, seed, cost and license in a provenance ledger.
Change one thing, re-render only what's dirty
Bump a character design; atl dirty lists exactly which shots fell behind — and what fixing them costs. The rest stay cached.
$ atl canon bump mara.visual --ref v2.png mara.visual: v1 → v2 $ atl dirty 2 shots reference an outdated design: shot/01/01 mara closeup ~$0.39 shot/02/02 mara on train ~$0.39 4 other shots unaffected — still cached. estimated to fix: $0.78
Use your GPU—or Atlas Cloud.
The core engine stays free and open source. Capable desktops render locally; Atlas Cloud provides budget-gated GPU production when you need more power.
- Full render engine & cache
- Resumable, budget-gated runs
- Replicate API bridge
- Python Director's DSL
- Community support
- Everything in Core
- Pro plugin pack & premium bridges
- Priority support
- Early access to new capabilities
- Commercial use
- Everything in Pro
- Self-host commercial license
- Up to 10 seats
- Private plugin registry
- SLA support
- Hosted, resumable renders
- Usage-based billing
- Team dashboards
- Closed beta
Questions, answered.
Is Atlas really free?
Yes. The Core CLI is Apache-2.0 licensed and free forever. You only pay for Pro features, a commercial self-host license, or (later) managed Cloud rendering. You always pay your model provider — e.g. Replicate — directly for generation.
Does my API token or artwork ever touch your servers?
No. Atlas runs entirely on your machine. Your provider tokens are read from environment variables and never written to disk, logs, or any server, and never transmitted to us. Plugins run as sandboxed subprocesses with a filtered environment.
Which models and providers are supported?
The first release ships a Replicate bridge for text-to-image and image-to-video. The plugin protocol is open and versioned, so any provider can be added — the Pro plan bundles additional premium bridges.
When can I use it?
We're in early access now. Grab a spot above and we'll email you the moment your invite is ready — and nothing else.
Can I use Atlas commercially?
Yes. Core is Apache-2.0 (commercial use permitted). Pro and Team add commercial support and a self-host license for organizations that need one.
Stop paying twice for the same frame.
Join early access and be first to render with Atlas.