Real output
Measured, not claimed.
Where these clips came from, what they scored, and a
second example that flatters us, labelled as such.
The hard case. Source: A Trip Down Market Street
(Miles Brothers, San Francisco, 1906), the Prelinger Archives copy at the Internet Archive, public
domain. This is a real archival transfer at 640×480, not a clean file we degraded on purpose:
it is soft because a 1906 print, copied and digitised a century later, is soft. The clip above is
that film run through Max, the generative restore in Crisp Pro, on a Mac. Both sides
are shown at the same size: on the left the transfer enlarged with a plain resize, on the right
Max’s 1280×960 output, both cropped the same way to fit this frame.
One thing had to happen first, and it is worth knowing if you have old film of your own: the
transfer repeats each film frame two or three times to fill 30 frames a second. Max restores every
frame it is given, so the copies come back slightly different and flicker. Crisp gave it one copy of
each film frame instead, 58 of them for these 4.8 seconds.
Why old film carries repeated frames →
Max is slow on purpose: those 58 frames took 30 minutes 22 seconds on an M1 Ultra Mac Studio,
31.4 seconds a frame.
Look at the Ferry Building at the end of the street: in the transfer the clock tower is a grey shape,
and Max gives it its clock face, its windows and the line of its roof. The building fronts and the
overhead wires come out the same way.
And the part that flatters us, said plainly: Max smooths the film grain away
completely, and fine texture such as the cobbles and the horses’ coats may be the model
filling in rather than detail recovered from the film. Believe the tower and the window frames; be
wary of the cobbles. Both clips play the same two and a half seconds unedited, compressed for the
web with identical settings.
The easy case, and we will say why. A city at night from the International Space Station, NASA, public domain. Unlike the clip above, this one was degraded on purpose: a sharp original reduced to 426×224 to stand in for low-resolution footage, then upscaled 16× to 6816×3584 and shown here at 1704×896. That is a much kinder test than real archival film, because the detail was there to begin with. Against a plain resize to the same delivered size it scores 3.42× the fine detail, where the archival clip above manages 1.50×. Both are shown because one without the other tells you half the truth: this is what Crisp does when the source cooperates, and the clip above is what it does when the source does not.
The case most people actually have, and we made this one on
purpose. Everything above is real footage. This is not: a sharp CC0 clip
(Die Ewige Welle und Surfers in Augsburg, Wikimedia Commons, public-domain
dedication) was deliberately reduced to what a mid-2000s camera phone recorded
(cropped to 4:3, 176×144, 15fps, H.263 at 64 kbps) and then restored, all 38 frames of it. We say
so because the number is the best on this page and you should know why: against a plain
upscale to the same size it holds 1.93× the fine detail, where the
1936 archival clip manages 1.50× and the 1950s one 1.23×. A badly compressed
source has more to give back than a decent scan does. If your old phone videos and photos
look like the left half, that is the gap Max is closing. But the honest version of
this claim is that we chose the damage, and real damage is rarely so tidy.
Past 4×, and who it is for. The upscaling networks are
trained at 2×, 3× and 4×, so anything larger has to be a chain of real
passes rather than one bigger number: 8× is a 4× pass followed by a 2×
pass, and 16× is 4× twice. Each pass gets the network built for it, which is why
8× is not simply 16× stopped early. On the same 160×120 crop, 4× takes
0.6 seconds, 8× takes 1.0, and 16× takes 1.5.
Side by side, 4×, 8× and 16× of the same crop look nearly
identical, so there is no panel of them here. The extra passes buy pixel dimensions, not
visibly more detail. 16× is for when you need the size, and past 8× the
picture stops changing much.
These are for small sources, and Crisp will tell you so.
The big multipliers exist for the footage that needs them: tape captures, old camcorder
files, 480p archive scans. A 640×480 clip at 16× is a 10240×7680 file and
encodes fine. A 1080p clip at 8× would be 15360×8640, which is past what the Mac
video encoder will write at all, so Crisp greys those out against the clip you
actually loaded and shows the finished size next to the picker, rather than letting you find
out after the render.
