Back to Blog

Cinematic Mode Is My Guilty Pleasure, So I Had It Rebuilt

Cinematic Mode is my guilty pleasure. It doesn't plot a route or find you a fight or tell you where the ore is. It turns the map into something you just look at. I think the universe Fenris Creations has built for EVE Frontier is deep and vast, and a universe like that should give you a sense of wonder. Cinematic Mode is how I try to get some of that onto the screen.

It has been in EF-Map almost from the start. The first commit in the repo is 12 August 2025 and Cinematic Mode went in twelve days later. Since then, every time a better model came out, or I just thought of an effect I wanted to see, I'd go back and add to it. Gas between the stars, supernovas, a film look, lens effects. Creator Mode, which I added later for people making videos, was built on top of the same code.

So after about 15 months it was fixes on top of fixes and layers on top of layers. It looked good, I think, but it was heavy and it had got hard to change. This is the story of having it rebuilt from scratch, on EF-Map and on EO-Map, my EVE Online map, with one shared engine under both. From the first prompt to live on both sites took four and a half days.

Cinematic Mode before and after, side by side: the same view of red gas and stars, the old film look on the left and the rebuilt one on the right
Cinematic Mode, old film look on the left and the rebuilt one on the right, from the same camera position on the same data.

I've also put this on the EO-Map blog, because EO-Map got the same rebuild first.

Why now

Two things lined up. Anthropic released Fable 5.2 on 9 November, and I had a couple of usage resets banked on my Claude plan. So on the 12th I asked the agent a fairly open question in the EF-Map repo. Look at how Cinematic Mode is drawn today, and tell me honestly whether a rebuild is worth it or whether I'm just going to burn a week and end up with the same thing.

The answer was more specific than I expected. To draw one frame of the old film look, the map was rendering the whole scene four times and then running about six more full-screen passes over the result. On my machine it cost several times as much graphics card time per frame as the normal map. The old Creator window had 179 controls in it, and a lot of them only existed because some layer underneath needed a knob. I'd written about parts of that stack before, when I refreshed Cinematic Mode in July and when I added the gas between the stars. Each of those was a good step at the time. Stacked up, they were the problem.

A throwaway page first

I'm a vibe coder. I don't read the code and I don't want to. So how this works is that I say what I'm after, the agent comes back with what it found and a suggestion, and there's some back and forth until there's a plan I'm happy with. For something visual, a written plan isn't much use to me though. I need to see it.

So before anything was built, the agent made a throwaway page. Not part of either map, never shipped, just the stars and a new way of drawing gas, with sliders on it. It started with a mood board of real photographs, Hubble's Orion and the Pleiades and the Lagoon nebula, and I said which ones I liked and which I didn't. I didn't like the hard sculpted infrared look at all. Then it was rounds. Eleven of them over two days. The agent would build a version, I'd fly around it and say what was wrong.

The throwaway mock-up page: EF-Map's stars in red gas, with a bar of sliders along the bottom for the gas, bloom and the light echo
The throwaway mock-up page on EF-Map's stars, with the sliders I used along the bottom. It was never part of either map.

Most of what I said was taste, not engineering. The gas shouldn't change colour when you zoom, because a cloud is a thing in a place. It should be neutral dust that picks up its colour from the stars near it and the sky behind it. It should be softer than the first few tries. The supernova took the longest. The first version I couldn't even see, the second looked like a soap bubble. What I wanted was a flash that lights the gas up nearly white, and then a wave moving out through the gas that fades as it goes. The agent calls it a light echo. It took until round eight before I said that's exactly what I wanted, and then another few rounds to get rid of a faint circle I kept spotting when it was moving.

The other thing that came out of those two days was a rule that the two maps keep their own identity. EF-Map is red and EO-Map is blue. The same engine draws both, but they never get the same default sky.

One engine, two maps

EO-Map started as a copy of EF-Map in August this year, and the two have drifted since. I wrote about that in The EVE Online Fork Is Starting to Pay EF-Map Back. The old Cinematic code existed in both, slightly different in each, which is twice the maintenance for one feature.

So the plan was one engine in one folder, and that folder is identical in both repos, byte for byte. It's 53 files, plus a list of what each one should hash to. The tests go red if a file stops matching that list, and a separate check warns if the two repos have drifted apart. The engine itself knows next to nothing about either game. Everything that makes a map itself is handed in from outside by a thin layer on each side. On EO-Map that's all 8,000 or so systems in EVE Online, a 2D layout, real region names and a blue sky. On EF-Map it's only the systems the community has charted, because of Fog of War, under a red sky. The gas only sits round the stars people have actually found. When somebody charts a new system the gas is redone around it and nothing else on the map moves.

The new Cinematic Mode on both maps side by side: EF-Map's stars in red gas on the left, EO-Map's stars in blue gas on the right
The same engine on both maps: EF-Map under its red sky on the left, EO-Map under its blue one on the right.

EO-Map went first, in five stages, each one built behind a hidden switch so the live site never saw a half-finished picture. Then EF-Map was a port of something already proven. That order was the agent's suggestion and I think it was the right one. By the time it got to EF-Map most of the hard questions had already been answered.

Creator Mode

Creator Mode is for people who want a scene to record. The old window had every slider I'd ever asked for, which is fine for me and hopeless for anyone else. What I asked for this time was easy mode. Pick a look, pick a finish, press record.

Creator Mode before and after with the window open on the Ember look: the old window with tabs and sliders on the left, the new gallery of looks, finishes and switches on the right
Creator Mode on the Ember look with the window open: the old window on the left, the new gallery of looks, finishes and switches on the right.
The new Creator Mode on the Ember look with Clean plate on: amber stars and stargate lines in glowing orange gas, no interface
The same Ember scene with Clean plate on, which is the picture you record.

So it opens on a gallery. On EF-Map that's your own map as it is, plus nine looks, and four finishes on top of any of them. There are four switches for stargate lines, labels, effects and a spotlight on one cluster. The controls that survived are under Fine tune for the people who want them. Of the 179 old controls on EF-Map, 64 were retired and 27 were merged into something else. On EO-Map the window went from 201 controls to 137. I went through that list with the agent, I didn't want a blind cut.

The one thing I chose not to carry over was old saved scenes. Scenes saved in the previous Creator can't be opened in the new one. Nothing in anyone's browser was deleted, and it tells you once, but they don't load.

Display Settings

This one was me. Every change over the last year had added a tick box somewhere in Display Settings. Performance Mode on one card, Cinematic Effects on another, Universe Effects inside the Cinematic window. It had got unwieldy and a bit stupid, and it was different on each map.

The General tab of Display Settings before and after: on the left Performance Mode, an accent colour card and a Cinematic Effects tick box; on the right one Map look row with five steps at the top
The General tab of Display Settings. The old Performance Mode and Cinematic Effects tick boxes are gone, and Map look sits at the top.

Now there's one row at the top called Map look, with five steps from lightest to richest. Performance, Performance with bloom, Standard, Atmosphere, and Atmosphere with universe effects. Atmosphere is the film look on the map you actually work in. It's the same row in the same place on both maps. Two of the old sky styles went as well, so the Backdrop tab is down to the Frontier sky and a minimal glow.

Was it faster

Here are the numbers. Graphics card time per frame, old against new, measured in the same run on the same build with the camera turning the whole time. This is my RTX 4070 SUPER, so treat it as one machine, not a benchmark.

GPU milliseconds per frame, camera moving, middle camera position, game closed

Surface and sizeOld, msNew, msNew as a share of old
Cinematic Mode1920x10801.800.890.50
Cinematic Mode2560x14403.401.470.43
Cinematic Mode3840x21606.541.730.26
Film look on the working map1920x10801.790.920.52
Film look on the working map2560x14403.371.590.47
Film look on the working map3840x21606.551.870.29
Creator Mode1920x10801.810.920.51
Creator Mode2560x14403.371.580.47
Creator Mode3840x21606.501.870.29

Across all three camera positions, with the camera moving, the new picture cost between 0.14 and 0.52 of the old one.

So roughly half the cost at 1080p and under a third at 4K. Across every camera position on EF-Map the new picture came in at between 0.14 and 0.52 of the old one. The bigger change is what happens when you stop moving. The old film look redrew everything, every frame, even when nothing on screen had changed. The new one draws nothing at all when the map is still. Measured over ten seconds with the working map still, the new one drew nothing and changed no pixels, against about 1.7 million changed pixels on the old build.

Those headline runs were with the game closed, because that's the only way to get a clean before and after. But these maps are second-monitor tools. Most people have them open while they're playing, so I care more about what happens with the game running. I'm playing EVE Frontier, which I'd guess is at least as heavy on a graphics card as EVE Online, though that is only a guess. So while this article was being written I had the whole test run again with the Frontier client open. The card was already 40 to 55% busy with the game before the test started.

Cinematic Mode, GPU milliseconds per frame, camera moving, middle camera position

SizeGame closed, oldGame closed, newGame running, oldGame running, new
1920x10801.800.891.800.90
2560x14403.401.473.391.48
3840x21606.541.736.671.73

Game running means the EVE Frontier client was open at the start and at the end of the run, on 16 November from 14:22 to 14:50 UTC.

Almost identical, and the spread across every camera position was 0.14 to 0.51 against 0.14 to 0.52 with the game closed. Part of that is how it's measured. The test takes the fastest frame it sees, which is the cost of the drawing itself, and a game running alongside can only add waiting on top of that. So the saving is the same size either way. What changes with the game running is that there's less of the card left over to share, and that's when halving your own cost is worth having. If it runs fine next to the game on my machine, I think it's going to be fine for most people.

What it took

Claude Code keeps a transcript of every session, so I had the agent count this one up the same way it did for my month on Claude Ultra.

4 days 12 hoursFrom my first prompt to live on both maps
9Sessions
191Helper agents those sessions started
21,957Requests to the models
6.38 billionTokens
98.2%Of those tokens were cache reads
$2,269At Anthropic's API list prices
About 112Agent-hours, every agent counted separately
6Agents working at once at the peak
77Prompts from me
Counted from the Claude Code transcripts, from my first prompt at 01:25 UTC on 12 November to EF-Map going live at 13:50 UTC on 16 November. The cost is what the tokens would cost at Anthropic's published API prices, not what I paid.

The first prompt went in at 01:25 UTC on 12 November and EF-Map went live at 13:50 on the 16th, so 108 hours start to finish. EO-Map had gone live the day before. In that time there were nine sessions, and between them they started 191 helper agents. That's 21,957 requests to the models and 6.38 billion tokens, and 98.2% of those tokens were the models re-reading the conversation so far from a cache, which is how these long sessions always look.

At Anthropic's published API prices that lot comes to $2,269. It isn't what I paid. I pay $200 a month for the plan. It isn't what it cost Anthropic to serve either. I think it's a fair yardstick for how much work got done though. Opus 5.5 did $1,842 of it, which is the helpers that did the building and the reviewing. Fable 5.2 did $397, running eight of the nine sessions and doing the planning. The very first assessment was actually Opus 5.5. Sonnet 5.5 did $30, mostly sitting through long test runs so the expensive models didn't have to.

The same count, split into the three phases

PhaseSessionsHelper agentsMy promptsAgent-hoursTokensList-price cost
Assessment, mock-up and plan2284416780 million$281
EO-Map, five stages and follow-ups69831643.38 billion$1,256
EF-Map port and release1652322.22 billion$731
All three9191771126.38 billion$2,269

There was at least one agent working for 71 of the 108 hours. Add each agent up separately and it's about 112 hours of agent time, with up to six going at once. My side was 77 prompts. About 12,500 words of that was me talking into a microphone. The rest was stage prompts the agent had drafted for me to paste into a fresh session, which is how I keep each stage's conversation small. The EF-Map port is the bit I still find a bit daft. It ran off one prompt, overnight and into the next day, and my second prompt was yes, ship it.

I had a theory that the token figure would be inflated. The orchestrating agent often sat waiting more than an hour for a helper to finish, and the cache it reads from only lasts an hour. So when it woke up it would have to take in the whole conversation again at double the normal price. I had that counted as well. It happened 16 times, 11 of them while it waited on a helper and five while I was away from the keyboard. It doesn't change the token count, because the same tokens get read either way, they just cost more when the cache has gone cold. Those 16 came to $57, about 2.5% of the total. The helpers have a shorter cache, five minutes, and theirs going cold cost more, $121, most of it while helpers sat waiting on their own long test runs. So I was right that it happens. It just doesn't matter much.

The agents weren't left to mark their own homework. Every stage ended with a separate review agent whose only job was to attack the work, and they earned their keep. On EF-Map the first review found two blockers and nine things that should be fixed, and the second found nine more. Near the end the orchestrating agent made a one-line change of its own, which broke a unit test, and that went red on the final run and was fixed before anything shipped. The release check also caught that the first preview build was missing a folder of game assets. None of that reached the live site.

What's left

It's live on both maps now. There are a few small things on the list. Supernovas and novas don't draw in a Creator scene with the gas off, which is how Creator opens unless your map is on Atmosphere, so that needs fixing in the shared engine on both sides. Clean plate should also hide the marker and name of a system you've selected. A handful of newly charted systems on EF-Map now sit past the edge of the fixed box the gas is laid out in. They still get gas, but the box will need widening as the map grows. And I've only tested this in Chrome on one graphics card, so if it looks wrong in Safari or Firefox I'd like to know.

Open Cinematic Mode and have a look, or set the map to Atmosphere in Display Settings. If something looks off, let me know and I'll get it sorted.

Related Posts

ef-map cinematic mode eve frontier map creator mode three.js volumetric gas claude code agents fable 5.2 map look atmosphere