#also first time making gifs with photoshop!

[mangosaurus]

Jurassic World: Chaos Theory - Cabin Attack Clip ☆

[johnbly]

Too bad the director’s not around, you know? Elena too. Hope they’re alive… They are.

[akirakirxaa]

[ day 26 - ascian ]

This 'Azem' was nothing like the other Ascians.

[ masterpost ]

[cloysterbell]

Pete, I need you to stay here.

[fakewaves]

Until your sin is cleansed... my vengeance will pursue you.

[kiisaes]

tsubomi! 👋

[doctorbrown]

if a whole july writing challenge wasn't enough i decided i was going to undertake a huge gif project for no other reason than to see if i could do it. and you know what, it's sort of looking like it's possible - we've got the ugliest rough draft idea going but once i get all the moving parts and gifs set that i like (that first one especially needs to be changed/fixed hnnnnn don't even talk to me about the rest of it. tbd on if i keep the little selection boxes as they are) we'll be in business

[mystery-star]

Russell Crowe as Ben Wade in 3:10 to Yuma (2007)

[firegiftlouis]

Hey, why not fly south for the winter?

“Hey, little songbird” - Hadestown (1/?)

[sirfrogsworth]

If you have seen Ted Lasso you may have noticed these unusual microphones used by the football commentators.

Despite being a microphone nerd, I had never seen anything like them before. So I decided to go into research mode and discovered these microphones are quite fascinating.

They are called "Lip-Ribbon" or "Commentator's" microphones.

They were specially designed by the BBC in the 1950s for extremely noisy environments. Soccer Football stadiums have peaked at 130 decibels so they needed something that would not get overwhelmed in that circumstance.

They use several very clever techniques to make sure only the voice is picked up and everything else is rejected.

First, they use a bidirectional polar pattern.

That means it will accept sound from two directions, but reject any sound coming in from the sides. And since the diaphragm is only exposed on one side, that helps reject sound coming from the other direction.

Next, the microphone is not very sensitive so you literally have to hold it up to your lips (hence "lip-ribbon") in order for your voice to have enough sound energy to vibrate the diaphragm.

That top part rests directly on your lip and there is a little pop filter to keep your plosives in check.

There is a built-in high pass filter so it rejects any sound below the frequencies typically used by the human voice.

But my favorite trick... a labyrinthian internal baffle system.

(I found a diagram of this when researching but then I lost the tab and I cannot find it again. So you'll just have to accept this crude photoshop I did in 30 seconds to help you understand.)

Sound is energy. And that energy is diminished the farther it travels. The inverse square law for sound states that the intensity of sound decreases by approximately 6 dB for each doubling of distance from the sound source. Sound also diminishes when it reflects off a surface.

That is a very sciency way of saying... make sounds go through a tiny maze and only sounds with the most energy will prevail.

So if you have your lip pressed up against the front of the mic, your voice's energy will make it through the labyrinth of baffles without issue. But every other sound in the stadium will have a much harder time getting through.

These mics may even be vuvuzela-proof.

And even more amazing... this microphone was designed in the 1950s and they have yet to create anything better for incredibly noisy environments.

Isn't that neat?

I think it is neat.

[kinnbig]

✨ Simple Gif Colouring for Beginners ✨

I wrote up my basic gif colouring process for a friend recently, but a couple of people here mentioned they'd also find it helpful! so, as requested, this is a beginner-friendly walkthrough of the way I colour my gifs :) it's aimed at brand new gif makers with no prior experience with photoshop or photo editing.

when I first started gif making I found colouring and photoshop in general suuuper daunting, so I've tried to simplify everything here as much as possible. hopefully this will be relatively easy to follow and not too intimidating!

a couple of things to begin with:

I'm only talking about colouring here - this is not a full gif making tutorial. I've linked to some of my favourites of those here!

I personally like to make bright, 'clean' looking gifs with vibrant but natural colours, so that is the style of colouring this tutorial is geared towards. most of gif colouring is subjective and about personal taste - the only thing that I'd say is possible to get wrong is skin tones, which I talk about a lot in this guide.

as I mostly gif Thai dramas, most of the advice is geared towards colouring for East Asian/South East Asian skin tones - but the techniques should be fairly universally applicable (and here are some tutorials that talk about gif colouring for other skin tones).

I'm not an expert! I'm not claiming this is the best or the only way to colour gifs - it's just how I do it.

this post is very image-heavy. if the images aren't loading (or the gifs are running slowly or cutting/looping weirdly), then try viewing the post in its own tab (rather than on the your dash or someone's blog) and refreshing the page.

okay, full walkthrough beneath the cut!

contents:

1. intro a. natural gif colouring goals b. very very basic colour theory 2. super simple colouring (the essentials) a. curves b. selective colour (and skin tone correction) c. hue/saturation d. saving and reusing colouring e. another simple colouring example 3. other adjustment layers a. brightness/contrast b. levels c. vibrance d. colour balance e. channel mixer 4. troubleshooting a. curves b. saturation 5. fin!

1. intro

the colouring part of gif making can be super overwhelming, especially if (like me when I first started!) you're completely new to photoshop and/or have no experience with colour theory or photo/video editing.

if you're opening photoshop and making gifs for the first time, I highly recommend getting used to making a few basic, uncoloured gifs to begin with. just to practice, rather than post anywhere (though you can always come back and colour them later if you want) - but it'll make the rest of the process much easier if you're already beginning to get used to working in timeline mode of photoshop. give yourself a bit of time to practice and get a feel for things like how many frames you tend to like in a gif, where you like to crop them for the best loop, what kind of aspect ratio you like etc* - so that you're not trying to navigate all of that for the first time on top of everything else!

* frames: for me between 60-90 frames is ideal, but 40-120 frames is the absolute min-max I'd personally use in a normal gifset loops: for the smoothest loops, try to avoid cutting someone off mid-movement or mid-word if possible. aspect ratio: for full-size (540px) gifs, I tend to go for either 8:5 (slightly 'skinnier' gifs), 7:5, or 5:4 (particularly big, thick gifs lmao)

✨ natural gif colouring goals

part of what can be so daunting about starting gif making is not knowing where to start or what you want to achieve. this is definitely something that gets easier with practice - the more gifs you make, the more you'll get a feel for what kind of look you like and the more instinctively you'll know how to get there. it also helps to see if any gif makers you like have made "before and after colouring" posts - these can help with getting a sense of the kinds of changes made through gif colouring. here's one I made!

in general, I like to make my gifs bright and 'clean' looking, with vibrant but natural colours. these are the things I'm usually hoping to achieve with colouring:

brighten dark scenes

remove muddy, yellowish lighting or filters

saturate colours

correct any skin lightening filters or overexposure

make lighting and colours as consistent as possible between gifs within a single gifset, especially gifsets featuring gifs from multiple scenes/episodes/videos

this guide is focusing on natural colouring, but of course there are many cool ways to make stylised/unnaturally coloured gifs. imo you'll need to master these basics first, but if you want to learn how to do things like change the background colour of gifs or use gradients or other cool effects, then @usergif's resource directory has loads of super helpful tutorials!

✨ very very basic colour theory

[disclaimer! I don't know shit about fuck. I do not study light or art. this is just an explanation that makes sense to me exclusively for the purposes of gif making.]

the primary colours for light/digital screens are red, blue, and green. having all three colours in equal measures neutralises them (represented by the white section in the middle of the diagram).

so to neutralise a colour within a gif, you need to add more of the colour(s) that are lacking.

in practice this usually means: the scene you want to gif is very yellow! yellow is made of red and green light, so to neutralise it you need to add more blue into your gif.

it can also mean the reverse: if you desaturate the yellow tones in a gif, it will look much more blue.

looking at the colour balance sliders on photoshop can make it easier to visualise:

so making a gif more red also means making it less cyan.

removing green from a gif means adding magenta.

taking yellow out of a gif will make it more blue.

tl;dr:

neutralise yellows by adding blue (and vice versa)

neutralise reds by adding cyan (and vice versa)

neutralise green by adding magenta (and vice versa)

2. super simple colouring (the essentials)

starting with a nice sharpened gif in photoshop in timeline mode. (these are the sharpening settings I use!)

some scenes are much harder to colour than others - it helps to start out practising with scenes that are bright/well-lit and that don't have harsh unnaturally coloured lights/filters on. scenes with a lot of brown/orange also tend to be harder.

I usually save a base copy of my gif before I start colouring just in case I end up hating it, or find out later that it doesn't quite fit right into a set and need to redo it etc.

so here is my base gif!

it's an okay gif, but it has a bit of a yellow tint to it that I want to reduce.

colouring is easiest to do in adjustment layers, which can be found under layer -> new adjustment layer - or for me they are here:

there are lots of different types of adjustment layers that do lots of different things - but for me the absolute essentials for colouring are curves, selective colour, and hue/saturation.

I also use brightness/contrast, levels, exposure, vibrance, colour balance, and channel mixer sometimes, depending on the gif - but I use curves, selective colour, and hue/saturation on every single gif.

✨ curves layer

the first thing I always do is a curves layer. when you first open one it will look like this:

first I usually click the ‘auto’ button, just to see what happens. sometimes it makes a big difference (it usually brightens the gif a lot) - but on this gif it didn’t do much.

if it had made the gif look nicer then I would have kept it and added a second curves layer on top to do the rest of these steps.

the next step is selecting the white and black points with the little eyedropper tools.

the bottom eyedropper lets you pick a white point for the gif. click somewhere super light on the gif to see what happens - for this gif, I clicked on the lampshade on the left. if it looks weird, I just undo it and try somewhere else - it usually takes a few goes to find something that looks good.

here's what that did to the gif:

then I pick the top eyedropper and use it to pick a black point by clicking somewhere really dark, again playing around until I find a black point that looks good.

here's what the gif looks like after picking the white and black points:

this can take some experimenting, but you can make super easy drastic changes to your gif just with this. in this case, the curves layer took out a lot of that yellowy tint.

and this is what the curves graph looks like now:

you can click and drag those lines to make further changes if you want - I usually leave them alone though. the colours of the lines indicate which colours have been changed in the gif - for example, you can see from that steep blue line on the graph that blue has been added to neutralise those yellows.

next I usually do another curves layer and just press the ‘auto’ button again to see what happens. usually it brightens the gif a bit more, which I like.

‼️if nothing is working: usually with a bit of fucking about a curves layer works well - but sometimes you can’t find a good white and black point anywhere, and instead your gif turns wacky colours and nothing looks good. this happens more often with very heavily colour tinted scenes :( the troubleshooting section at the end goes over some options, including starting with a levels layer instead.

✨ selective colour (and skin tone correction)

skin tones are made up of a mixture of yellow and red.

removing yellow (or adding blue or red) to a gif will make the skin-tones too red - and removing red (or adding cyan or yellow) to a gif will make the skin-tones too yellow.

adding blue to this gif with the curves layer took out the yellowy tint, which I wanted - but it also took the yellows out of Kim's skin tone, which I don’t want. so I need to put yellow back into the skin tones specifically - without putting it back into the rest of the gif.

selective colour layers let you select an individual colour and adjust the levels of other colours within that colour. you can change how yellow the green shades are, or how much cyan is in the blues, for example.

I need to add yellow back into the red tones to correct the skin tones on this gif. this is the case for most gifs in my experience - the vast majority of the time, unless a scene is very heavily tinted in another colour, a curves layer will add blue/remove yellow.

in the 'colors' dropdown, select the 'reds' section and drag the 'yellow' slider higher - this will add more yellow into just the red shades within the gif.

the amount of yellow you need to add back into the reds depends on how much yellow was taken out of the gif initially - I just play around with the slider until it looks right. if you're not sure, it helps to have some neutrally-coloured (not white-washed!) reference photos of the people in your gif to compare to.

here's the result. Kim's skin is a lot less pink toned and much more natural looking:

✨ hue/saturation

this adjustment layer lets you adjust the hue and saturation of the gif as a whole, and also of each colour individually.

I don't use the hue or lightness sliders unless I'm trying to do something more complicated with the colouring.

clicking the dropdown menu that says 'master' lets you edit the saturation of each colour individually. this is useful if your gif is still super tinted in one colour.

I thought the yellows on this gif were still slightly too bright, so I switched to the yellow channel and desaturated them slightly. (remember if you do this then you need to go back to selective colour and add more yellow into the red skin tones to balance out the desaturation!)

then I increased the 'master' saturation of all the colours to +5:

I usually find the right amount of saturation is somewhere between +5 and +12, but it depends on the gif.

‼️if the gif feels undersaturated, but the saturation slider isn't helping/is making the colours worse, try a vibrance layer instead.

done!

✨ saving and reusing colouring

you can copy and paste adjustment layers between gifs to make your colouring even across each of your gifs for one scene - so if you're making a set of multiple gifs of the same scene, or you think you might want to gif the same scene again in the future, you can save it as a psd so you can reuse the colouring again later.

each gif's colouring will then still need tweaking - different cameras/angles/shots of the same scene can still start out with slightly different colouring.

I recommend uploading the gifs as a draft post on tumblr so you can see what they all look like next to each other and catch any inconsistencies.

✨ another one! (speedrun!)

HI KEN!

the white point for the curves layer was in the window behind them.

the curves layer removes the muddy yellow tint, but again it makes their skin tones (especially Ken's) very red toned, which is adjusted by the selective colour layer.

3. other adjustment layers

imo many many gifs can be coloured really nicely with just those three adjustment layers, but some need different adjustments.

✨ brightness/contrast

pretty self explanatory!

I personally usually avoid using the 'brightness' slider because I rarely like the effect - I only tend to use the 'contrast' one. 

the 'auto' button is sometimes useful though, especially if you’re struggling with the curves layer.

✨ levels

levels alters the white and black points of the gif, like curves - but unlike curves it doesn't also alter other colours.

use the sliders beneath the graph to alter how dark/light the gif is. you can slide the black slider further to the right to make the blacks darker, and the white slider to the left to make the whites lighter.

levels is a good place to start if your curves layer isn't working.

(I'm going to hit the image limit for this post lol so here are some screenshots of a table I made to demonstrate this rather than actual gifs. sorry!)

on both sides, I dragged the sliders up to where the big jumps are on the graph - this is usually a good place to start!

✨ vibrance

vibrance... makes the colours more vibrant. it's more subtle than saturation.

it's really helpful for gifs that feel grey. sometimes adjusting saturation just makes the greys kind of weirdly tinted, but a vibrance layer can fix that.

vibrance is much more subtle!

✨ colour balance

colour balance affects the overall balance of colours within a gif.

it's good for scenes with heavy tints.

I tend to stick to the 'midtones' dropdown, but you can also alter the colour balance within the shadows and highlights if you want.

✨ channel mixer

I avoided channel mixer for such a long time because it scared me. but it's great for scenes that are very heavily tinted in one colour.

basically, it works with the levels of red, green, and blue within a gif. you select an output colour and then play around with the levels of the colour you selected within each other colour.

kind of the reverse of selective colour?

so in the 'blue' channel, the levels of blue are at 100%, and the levels of red and green are at 0% - but you can impact how much blue is in the reds and greens and blues.

this tutorial explains it well - but imo the best way to get to grips with channel mixer is just to play around with it a bit (sorry)

(when I made this guide for my friend, I also made a slightly more complicated gif colouring walk-through that included using channel mixer. there isn't space to include it within this post, but if anyone is interested I could always upload it as an 'intermediate' gif colouring tutorial - lmk!)

4. troubleshooting

‼️curves

usually with a bit of fucking about a curves layer works well - but sometimes you can’t find a good white and black point anywhere, and instead your gif turns wacky colours and nothing looks good. this happens more often with very heavily colour tinted scenes :(

for example, with this base gif:

using many of the brightest points as a white point turn it wacky colours, like this:

yikes :(

some options for these cases:

try brightening the gif first with the 'auto' button on the curves layer or with a levels layer. having a brighter gif to start with can give you better options for picking a white point.

try finding an alternate, whiter/brighter white point. look for places the light reflects - on this gif, using the light on Porsche's cheekbone works well as the white point. it also helps to find places that would be white if the scene wasn't tinted - the lightest part of a white shirt is often a good place to start, for example.

skip the curves layer, and instead use a levels layer to alter your white/black points, and colour balance or channel mixer to balance the colours.

‼️over/undersaturation

if your gif (especially the skintones) is looking a little washed out or lifeless, it might be undersaturated. boost that saturation - or if that's not working, try a vibrance layer.

oversaturation is often easiest to spot in the mouths and ears of any people in a gif. if the mouths are looking unnaturally, vibrantly red, then you've gone too far with the saturation.

5. fin!

and done! I hope this was coherent helpful to somebody.

if there's anything that I've missed or that doesn't make sense pls feel free to shoot me an ask or a message and I'll do my best to help! I've also collated a bunch of additional reading/resources below.

happy gifmaking 🥰

✨ some links!

photoshop basics by @selenapastel

gifmaking for beginners by @hayaosmiyazaki

gifmaking guide for beginners by @saw-x

dreamy's gif tutorial by @scoupsy-remade (includes instructions on how to blur out burned-on subtitles or annoying video graphics)

beginner's guide to channel mixer by @aubrey-plaza

how to fix orange-washed characters by aubrey-plaza

colour correcting and fixing dark scenes by @kylos

does resampling matter? by usergif

how to put multiple gifs on one canvas by @fictionalheroine

watermarking using actions by @wonwooridul

resource directory by @usergif

[crackers4jenn]

🤝 jared padalecki constantly making cockles jokes

Misha's favorite thing to do in his free time, according to Jared: "photoshop lewd pictures of he and jensen"

Jensen: "(misha) sounds like that in the morning" / Jared: "how do you know??" 🎤

This move:

Misha, to Jensen: "You wanna tell your dream?" / Jared: "WOW. Woah, this just got really romantic."

Jensen: "I also liked the season in which I met Jared's wife." / Jared: "Isn't that the season you met Misha???"

Random fan, as Jensen is dramatically taking off his jacket to an audience of screams: "Happy birthday to me!" / Jared, pretending to look out into the audience: "Misha?!"

This tweet:

🤝 jackles constantly making cockles jokes

Jared, pretending to be Jensen: "Man, Misha's been working out." / Jensen: "He has, though, hasn't he? 😏"

"Misha started the fire? He is pretty hot."

"(Danneel) does refer to (Misha) as her boyfriend, so. Which is funny, 'cause so do I."

The season 5 "blow me" gag reel, obviously:

Fan, to Jensen: "First, I just want to say I think you’re a really talented actor and a lot of people just see you and see how attractive you are and they think you’re just another pretty boy, but you’re a lot more than that and I can’t wait to see what you do in the future because you deserve a lot more recognition." / Jensen, for some reason: "Misha, I appreciate you screening everyone that came through here today."

🤝 misha constantly making cockles jokes

Jensen: "and I was like, 'just swallow it, just swallow it and you can have some water'--" / Misha: "He's always giving that advice."

Jensen: "I actually think you look good, man, I think you look nice and dapper -- and I'm not just saying that in front of (the con crowd), I actually complimented him earlier about it, I said 'I think it looks good, man,'--" / Misha: "It was a little weird" / Jensen: "It was weird" / Misha: "and then he went in for a kiss! and I was like 'whoa whoa whoa!" / Jensen: "I did. Yep. Ey, when in Rome!"

the "I told you" tweet in response to some fan pointing out that Misha was topping Jensen on the trending page.

This nonsensery, which inspired this post:

🤝 and, finally, spn making a joke about cockles

[tickfleato]

how to make cool blobby turing patterns in photoshop

i'll preface with i learned the basic loop from skimming a tutorial on youtube, but as someone who prefers written tutorials i'm sure many would appreciate one! also, the second part of this is some of the visual effects i figured out on my own using blending modes and stuff.

i'm using photoshop CS4 on a mac so some buttons and stuff might be in different places on windows and newer photoshop versions but all the actions are the same. my canvas is 1000x1000 pixels.

UPDATES (i'm hoping these'll show up whenever you open the readmore?)

it's possible to do something similar in krita using this plugin, made by the love @arcaedex

it's also possible to do this in photopea, a free browser alternative to photoshop! the results are pretty much identical.

FIRST off you wanna get or make a black and white image of some kind. it has to be one layer. can be noise, a photo, a bunch of lines, whatever. here's mine, just some quick airbrush lines:

now find the actions tab. idk what it looks like in newer versions of photoshop but you probably won't need to dig!

hit the little page thingy to make a new pattern. once you hit 'record', it'll record everything you do. the little square 'stop' icon will end it.

now you want to do a high pass filter. you can mess around with the radius to change the size of your squiggles, but the tutorial had it set to 6. experiment!

now add the 'threshold' adjustment layer. i use the adjustments tab but i think there's also a dropdown menu somewhere. keep it at the default, 128. merge it down. (control or command + E or you can right click it like some kind of weirdo)

and finally, the gaussian blur! the radius of this affects the shape and size of your squiggles as well. i like to keep it around 4.5 but you can mess around with that too.

after that, hit 'stop' on the action you're recording, and then repeat it a bunch of times using the 'play' button, until you have something you like, like this:

WOW!! that was fun!! and only a little tedious thanks to the power of macros. anyway, here's some fun layer blending stuff i like to do. it's with a different pattern cause i made this bit first.

anyway, using a black and white gradient (or a grey base that you do black and white airbrush on), make a layer with the vivid light. this will make the blobs look thicker or thinner.

then, for cool colors, do a gradient map adjustment layer over that:

and finally, my best friend, the overlay layer. just using a gradient here bc i'm lazy, but feel free to experiment with brushes, colors, and blending modes!

NOW GO. MAKE COOL SHIT WITH THE POWER OF MATH. AND SEND IT TO ME

also these are not hard and fast rules PLEASE mess around with them to see what kind of weird shit you can make. here's a gif. as you can see i added some random airblush blobs in the middle of it, for fun.

[mithrandirl]

i always get questions when i do a split gifset, and it's a deceptively simple process so i thought i'd try to show how i do it! i don't know if these types of gifsets have a more universally recognized name, but that's what i call them so that's what i'm going with.

i'm going to write this assuming you have a solid familiarity with photoshop and making gifs, but please feel free to send me an ask if anything is unclear. i use video timeline/smart objects so will be showing that (here's a great general tutorial on giffing with timeline). i will also be talking A LOT about gif dimensions, so first let's briefly go over the limits and theory a little bit.

a 1 column gifset can accommodate gifs 540 pixels wide

2 columns = 268 pixels each with a 4 pixel gutter between

3 columns = 177, 178, 177 pixels with 4 pixel gutters

i'm mostly going to talk about 2 column split gifs here (what i will refer to as 2x1 from now on - 2 across and 1 high), but the process is the same for 3 column (3x1) and so on (1x2, 2x2, etc).

so, why would you even want to make a gifset like this? i mean, let’s face it, generally, bigger is better for gifs on tumblr, and there are obvious incentives to 540 width gifs over 268 or 177/8 width, especially since the upload limit went to 10MB. but even 10MB isn’t much when you’re talking about high quality footage. gif making is a constant balance between quality (whatever that means to you: frame dimensions, sharpening, coloring, etc) and file size. split gifs are a cheat to that limitation >:)

i personally believe an untapped frontier of tumblr gifmaking is playing with dimensions and time. that sentence makes me sound like an old-timey sci-fi villain, but you get the idea: gifmaking is an art and there are many fun and interesting ways of exploring the medium. you can do a lot with 268 pixels! longer frame loops to gif longer scenes unbroken, bolder coloring on a wide shot you don’t want to pare down. and, a shorter x axis means the y axis’s bang goes a lot further on a buck. also just if you have a 2 column set but only 5 gifs so you need to make one take up 2 slots. there's a lot of reasons but the most important one is it's fun :) here are some examples of other split gifs i've made: x, x, x

this isn't so much a limitation, more of a shift in how you think about gifs, but it's important to remember that each gif should ideally be doing something still. when making split gifs, it’s easy to pick a wide scene without thinking about how it’ll be split down the middle, and then you’re left with a lot of something on one side and a lot of incongruous nothing on the other - or you're left with a person cut in half awkwardly in the middle. so while a split gif can still be a whole scene, you shouldn’t ignore the break and what it means to the bigger picture. now this is personal preference, but i like to play with the break and make it a part of the gifset. mirrored movement, subjects trapped on either side but still talking to each other, a bird flying from one side to the other. fun with frames! it can be another way of drawing attention to specific images/moments/feelings happening within the same shot.

SIMPLE SPLIT GIFS

to more narrowly define what i’m calling “simple split gifs,” it’s one set of frames split down the middle into two separate gifs that are meant to play concurrently, side by side.

first thing's first, crop your gif and uncheck delete cropped pixels if it is not already (very important). i'm cropping it to the 1x1 size, in this case 268x350. if you need to see how the full size will look, you can try it out with 536 first. but this one is pretty easy, this is the exact center of the frame (the left boundary of this crop is the center line) and both their heads fit within their respective 1x1 crop.

then color as you normally would. if your scene is very different one side to the other, it might be easier for you to color on a wider crop and then either crop again or copy paste your coloring to the smaller crop version. i do that with the 2x6s, but it's usually not that big a deal to color the 2x1s with just the small crop on your canvas at the time. this scene is very symmetrical, both in movement and colors, so i'm good.

now the fun part! once you've got one side how you want it, save/export as you normally would. at this point i also like to make a mental note of how many frames there are.

so i have 49 frames and it's still only ~3MB! this is just an example that i picked from my rotk fancy set, otherwise i probably would have made this gif longer.

then onto the other side, so i ctrl + z my way back to my smart object video timeline. to get to theoden i just drag and drop the smart object 268 pixels over. since this one is in the exact center of the image, it even helpfully guides me (this can get annoying if you are NOT giffing the center of the image fyi, but you can always manually go pixel by pixel too if you need to with your <- -> keyboard buttons. just always remember where you started and count accurately). i can never move around my smart object without hiding the adjustment layers on top of it, so you'll see me do that in this screen recording.

see how it corrected me when i dragged it a few pixels down by accident, and with all those pink guidelines? sometimes photoshop is good 😌

then make sure you still like the coloring, adjust whatever needs to be adjusted, but watch out! don't make any major changes because it still has to match the other side. and export again.

what we perceive as 1 series of frames chopped down the middle is just 2 separate gifs with the same frame rate. when tumblr loads the images, it will run concurrently in the post (even though it never does in the draft post 🙄). and that's it!

COMPLEX SPLIT GIFS

again i'm making up terms, but i call anything with more than 2 components a complex split gifset. i've tweaked some things in the process as i went along, but this is generally how i did the lotr series. these sets are basically just many split gifs with transitions. and here's where endurance becomes a factor :) there's a lot of prep done blind. but if set up well, it will be fairly easy to pull together by the end.

first i decide on my dimensions, using my upper bounds to determine how big i'm going to go. since lotr has very nice large file sizes, i can go pretty big without sacrificing much in quality. i decided on 3 rows of 350 pixel height gifs and it's worked well for me. that means my biggest gif will have a total height of 1050 pixels - fun! you could also do 8 rows, with two 2x2s or just a series of 2x1s that transition to 1x1s. there really is no limit to this except your imagination and source material.

i cap everything i'm going to use before i even open photoshop, then do all of them at once. uncheck delete cropped pixels, then i make my gifs! this is where i spend 90% of the time on this set. every gif should be the size of the smallest 1x1 gif (268x350 for me). i make all 10 into a fully colored, separate psd. (and then i usually go back through all of them a few times to get the colors to match better 😅) for the bigger ones (2x1: 536x350 and 2x6: 536x1050), i just crop them as if they were 1x1 but always thinking about how they will look when big. this gets tricky when i do the big one :) my lazy workaround for that is to basically make it twice: one cropped as it will be and one full size for me to color. then i copy and paste all the coloring layers onto the small one and voila, i know that the coloring in the upper right slice will also look good on the bottom left slice 1050 pixels away because i saw it on the full size version.

coloring is probably the biggest thing i'm thinking about with this kind of set. the whole idea is that these gifs are using the same colors, more or less, throughout each phase. even with the 1x1s, they're still part of a larger color concept, and they should (🤞) work with each other.

in a pinch, i like to eyedrop a color from one gif and add it as an accent to another. one of my 1x1s had a much more muted color palette originally, but i wanted it to have deeper blues and yellows to complement the 1x1 that would go next to it, so i added some gradients on lower opacity over it, color picked from other gifs i already colored.

i keep my coloring and the smart object in separate folders to help me in the final step of combining everything, and then i trim everything down to my lowest common denominator of frames. you might think you need to keep frames pretty minimal if you're doing 3 phases with transitions like this, but there's more room to work with on a small gif, in terms of file size. i usually do 30-50 frames for each phase, with the assumption that i'll be adding a transition on each side of each gif that will eat up some frames (i usually do 4-6 frame fade transitions). for the rotk set my final frame count was 129 and i never went over 8MB on a gif, so there's plenty of space play around with things :)

and then, combine! whatever order you start with, you are stuck with (unless you're getting even more complicated, but we won't go into that lol). for these sets i go small 1x1 -> medium 2x1 -> big 2x6. i like to think of it in phases from this point on. small is the first phase, then medium, then big. then i put in the fade transitions, chopping up the first phase gif so the last one will fade into it, restarting the whole cycle seamlessly. i'm just doing a quick and dirty fade here, but here's a tutorial if you want more explanation on transitions.

at this point i save this psd as its position, "top left" or whatever (usually it's a psb by this point too 🥲), just in case i need to go back to it. then i export this first gif and move on to the rest.

it's the same concept as a simple split gif: drag and drop the smart object to the new position, but now there are multiple phases to keep track of. folder organization has been key for me to keep everything straight. i move through the gifs in a backwards S, starting with the top left. but you could go any direction, just gotta stick with it and remember your counts. in my case, i'm always thinking of 268 pixels over and, for the 2x6, 350 up/down. it's a tedious process, but it goes quick (apart from waiting for photoshop to load each time you export).

i did this series as a color concept aesthetic kind of thing, so my theory was by using the same-ish colors throughout, that would save me in the end when it came time to export. there's only 256 colors max to work with on a gif, and that's usually what gets me over the 10MB limit. but as i said, i have never even gotten close to the size limit on this series. it's pretty hard to reach the limit on 268 pixels, but not impossible. (i did run into that on the emma set i did, and that was hell. but also not an impossible fix in the end.)

and that's it! if you try any of this and have trouble, i'm happy to help if i can but mostly this is a "click around and see what works for you" kind of process. and feel free to tag me on your split gifsets :) i love seeing them <3

[dianagj-art]

No. It has to be me. Anyone else would probably do it wrong

Congratulations to @mutantninjamidlifecrisis for not only being the first fic to make cry in quite a while, but also being the first fic ever to get such a reaction out of me that I had to laid down my phone and just breathe for a few minutes until I calmed myself enough for my hands to stop shaking, this happened multiple times while I read chapter 8, I even had to stand up and walk around my room once to calm down.

anyways if you havent read this fic yet go read it

Bonus lil gif under the cut bc photoshop screwed up the colors when I tried to export the whole page as a gif

[antoniosvivaldi]

Neural Filters Tutorial for Gifmakers by @antoniosvivaldi

Hi everyone! In light of my blog’s 10th birthday, I’m delighted to reveal my highly anticipated gifmaking tutorial using Neural Filters - a very powerful collection of filters that really broadened my scope in gifmaking over the past 12 months.

Before I get into this tutorial, I want to thank @laurabenanti, @maines , @cobbbvanth, and @cal-kestis for their unconditional support over the course of my journey of investigating the Neural Filters & their valuable inputs on the rendering performance!

In this tutorial, I will outline what the Photoshop Neural Filters do and how I use them in my workflow - multiple examples will be provided for better clarity. Finally, I will talk about some known performance issues with the filters & some feasible workarounds.

Tutorial Structure:

Meet the Neural Filters: What they are and what they do

Why I use Neural Filters? How I use Neural Filters in my giffing workflow

Getting started: The giffing workflow in a nutshell and installing the Neural Filters

Applying Neural Filters onto your gif: Making use of the Neural Filters settings; with multiple examples

Testing your system: recommended if you’re using Neural Filters for the first time

Rendering performance: Common Neural Filters performance issues & workarounds

For quick reference, here are the examples that I will show in this tutorial:

Example 1: Image Enhancement | improving the image quality of gifs prepared from highly compressed video files

Example 2: Facial Enhancement | enhancing an individual's facial features

Example 3: Colour Manipulation | colourising B&W gifs for a colourful gifset

Example 4: Artistic effects | transforming landscapes & adding artistic effects onto your gifs

Example 5: Putting it all together | my usual giffing workflow using Neural Filters

What you need & need to know:

Software: Photoshop 2021 or later (recommended: 2023 or later)*

Hardware: 8GB of RAM; having a supported GPU is highly recommended*

Difficulty: Advanced (requires a lot of patience); knowledge in gifmaking and using video timeline assumed

Key concepts: Smart Layer / Smart Filters

Benchmarking your system: Neural Filters test files**

Supplementary materials: Tutorial Resources / Detailed findings on rendering gifs with Neural Filters + known issues***

*I primarily gif on an M2 Max MacBook Pro that's running Photoshop 2024, but I also have experiences gifmaking on few other Mac models from 2012 ~ 2023.

**Using Neural Filters can be resource intensive, so it’s helpful to run the test files yourself. I’ll outline some known performance issues with Neural Filters and workarounds later in the tutorial.

***This supplementary page contains additional Neural Filters benchmark tests and instructions, as well as more information on the rendering performance (for Apple Silicon-based devices) when subject to heavy Neural Filters gifmaking workflows

Tutorial under the cut. Like / Reblog this post if you find this tutorial helpful. Linking this post as an inspo link will also be greatly appreciated!

1. Meet the Neural Filters!

Neural Filters are powered by Adobe's machine learning engine known as Adobe Sensei. It is a non-destructive method to help streamline workflows that would've been difficult and/or tedious to do manually.

Here are the Neural Filters available in Photoshop 2024:

Skin Smoothing: Removes blemishes on the skin

Smart Portrait: This a cloud-based filter that allows you to change the mood, facial age, hair, etc using the sliders+

Makeup Transfer: Applies the makeup (from a reference image) to the eyes & mouth area of your image

Landscape Mixer: Transforms the landscape of your image (e.g. seasons & time of the day, etc), based on the landscape features of a reference image

Style Transfer: Applies artistic styles e.g. texturings (from a reference image) onto your image

Harmonisation: Applies the colour balance of your image based on the lighting of the background image+

Colour Transfer: Applies the colour scheme (of a reference image) onto your image

Colourise: Adds colours onto a B&W image

Super Zoom: Zoom / crop an image without losing resolution+

Depth Blur: Blurs the background of the image

JPEG Artefacts Removal: Removes artefacts caused by JPEG compression

Photo Restoration: Enhances image quality & facial details

+These three filters aren't used in my giffing workflow. The cloud-based nature of Smart Portrait leads to disjointed looking frames. For Harmonisation, applying this on a gif causes Neural Filter timeout error. Finally, Super Zoom does not currently support output as a Smart Filter

If you're running Photoshop 2021 or earlier version of Photoshop 2022, you will see a smaller selection of Neural Filters:

Things to be aware of:

You can apply up to six Neural Filters at the same time

Filters where you can use your own reference images: Makeup Transfer (portraits only), Landscape Mixer, Style Transfer (not available in Photoshop 2021), and Colour Transfer

Later iterations of Photoshop 2023 & newer: The first three default presets for Landscape Mixer and Colour Transfer are currently broken.

2. Why I use Neural Filters?

Here are my four main Neural Filters use cases in my gifmaking process. In each use case I'll list out the filters that I use:

Enhancing Image Quality:

Common wisdom is to find the highest quality video to gif from for a media release & avoid YouTube whenever possible. However for smaller / niche media (e.g. new & upcoming musical artists), prepping gifs from highly compressed YouTube videos is inevitable.

So how do I get around with this? I have found Neural Filters pretty handy when it comes to both correcting issues from video compression & enhancing details in gifs prepared from these highly compressed video files.

Filters used: JPEG Artefacts Removal / Photo Restoration

Facial Enhancement:

When I prepare gifs from highly compressed videos, something I like to do is to enhance the facial features. This is again useful when I make gifsets from compressed videos & want to fill up my final panel with a close-up shot.

Filters used: Skin Smoothing / Makeup Transfer / Photo Restoration (Facial Enhancement slider)

Colour Manipulation:

Neural Filters is a powerful way to do advanced colour manipulation - whether I want to quickly transform the colour scheme of a gif or transform a B&W clip into something colourful.

Filters used: Colourise / Colour Transfer

Artistic Effects:

This is one of my favourite things to do with Neural Filters! I enjoy using the filters to create artistic effects by feeding textures that I've downloaded as reference images. I also enjoy using these filters to transform the overall the atmosphere of my composite gifs. The gifsets where I've leveraged Neural Filters for artistic effects could be found under this tag on usergif.

Filters used: Landscape Mixer / Style Transfer / Depth Blur

How I use Neural Filters over different stages of my gifmaking workflow:

I want to outline how I use different Neural Filters throughout my gifmaking process. This can be roughly divided into two stages:

Stage I: Enhancement and/or Colourising | Takes place early in my gifmaking process. I process a large amount of component gifs by applying Neural Filters for enhancement purposes and adding some base colourings.++

Stage II: Artistic Effects & more Colour Manipulation | Takes place when I'm assembling my component gifs in the big PSD / PSB composition file that will be my final gif panel.

I will walk through this in more detail later in the tutorial.

++I personally like to keep the size of the component gifs in their original resolution (a mixture of 1080p & 4K), to get best possible results from the Neural Filters and have more flexibility later on in my workflow. I resize & sharpen these gifs after they're placed into my final PSD composition files in Tumblr dimensions.

3. Getting started

The essence is to output Neural Filters as a Smart Filter on the smart object when working with the Video Timeline interface. Your workflow will contain the following steps:

Prepare your gif

In the frame animation interface, set the frame delay to 0.03s and convert your gif to the Video Timeline

In the Video Timeline interface, go to Filter > Neural Filters and output to a Smart Filter

Flatten or render your gif (either approach is fine). To flatten your gif, play the "flatten" action from the gif prep action pack. To render your gif as a .mov file, go to File > Export > Render Video & use the following settings.

Setting up:

o.) To get started, prepare your gifs the usual way - whether you screencap or clip videos. You should see your prepared gif in the frame animation interface as follows:

Note: As mentioned earlier, I keep the gifs in their original resolution right now because working with a larger dimension document allows more flexibility later on in my workflow. I have also found that I get higher quality results working with more pixels. I eventually do my final sharpening & resizing when I fit all of my component gifs to a main PSD composition file (that's of Tumblr dimension).

i.) To use Smart Filters, convert your gif to a Smart Video Layer.

As an aside, I like to work with everything in 0.03s until I finish everything (then correct the frame delay to 0.05s when I upload my panels onto Tumblr).

For convenience, I use my own action pack to first set the frame delay to 0.03s (highlighted in yellow) and then convert to timeline (highlighted in red) to access the Video Timeline interface. To play an action, press the play button highlighted in green.

Once you've converted this gif to a Smart Video Layer, you'll see the Video Timeline interface as follows:

ii.) Select your gif (now as a Smart Layer) and go to Filter > Neural Filters

Installing Neural Filters:

Install the individual Neural Filters that you want to use. If the filter isn't installed, it will show a cloud symbol (highlighted in yellow). If the filter is already installed, it will show a toggle button (highlighted in green)

When you toggle this button, the Neural Filters preview window will look like this (where the toggle button next to the filter that you use turns blue)

4. Using Neural Filters

Once you have installed the Neural Filters that you want to use in your gif, you can toggle on a filter and play around with the sliders until you're satisfied. Here I'll walkthrough multiple concrete examples of how I use Neural Filters in my giffing process.

Example 1: Image enhancement | sample gifset

This is my typical Stage I Neural Filters gifmaking workflow. When giffing older or more niche media releases, my main concern is the video compression that leads to a lot of artefacts in the screencapped / video clipped gifs.

To fix the artefacts from compression, I go to Filter > Neural Filters, and toggle JPEG Artefacts Removal filter. Then I choose the strength of the filter (boxed in green), output this as a Smart Filter (boxed in yellow), and press OK (boxed in red).

Note: The filter has to be fully processed before you could press the OK button!

After applying the Neural Filters, you'll see "Neural Filters" under the Smart Filters property of the smart layer

Flatten / render your gif

Example 2: Facial enhancement | sample gifset

This is my routine use case during my Stage I Neural Filters gifmaking workflow. For musical artists (e.g. Maisie Peters), YouTube is often the only place where I'm able to find some videos to prepare gifs from. However even the highest resolution video available on YouTube is highly compressed.

Go to Filter > Neural Filters and toggle on Photo Restoration. If Photoshop recognises faces in the image, there will be a "Facial Enhancement" slider under the filter settings.

Play around with the Photo Enhancement & Facial Enhancement sliders. You can also expand the "Adjustment" menu make additional adjustments e.g. remove noises and reducing different types of artefacts.

Once you're happy with the results, press OK and then flatten / render your gif.

Example 3: Colour Manipulation | sample gifset

Want to make a colourful gifset but the source video is in B&W? This is where Colourise from Neural Filters comes in handy! This same colourising approach is also very helpful for colouring poor-lit scenes as detailed in this tutorial.

Here's a B&W gif that we want to colourise:

Highly recommended: add some adjustment layers onto the B&W gif to improve the contrast & depth. This will give you higher quality results when you colourise your gif.

Go to Filter > Neural Filters and toggle on Colourise.

Make sure "Auto colour image" is enabled.

Play around with further adjustments e.g. colour balance, until you're satisfied then press OK.

Important: When you colourise a gif, you need to double check that the resulting skin tone is accurate to real life. I personally go to Google Images and search up photoshoots of the individual / character that I'm giffing for quick reference.

Add additional adjustment layers until you're happy with the colouring of the skin tone.

Once you're happy with the additional adjustments, flatten / render your gif. And voila!

Note: For Colour Manipulation, I use Colourise in my Stage I workflow and Colour Transfer in my Stage II workflow to do other types of colour manipulations (e.g. transforming the colour scheme of the component gifs)

Example 4: Artistic Effects | sample gifset

This is where I use Neural Filters for the bulk of my Stage II workflow: the most enjoyable stage in my editing process!

Normally I would be working with my big composition files with multiple component gifs inside it. To begin the fun, drag a component gif (in PSD file) to the main PSD composition file.

Resize this gif in the composition file until you're happy with the placement

Duplicate this gif. Sharpen the bottom layer (highlighted in yellow), and then select the top layer (highlighted in green) & go to Filter > Neural Filters

I like to use Style Transfer and Landscape Mixer to create artistic effects from Neural Filters. In this particular example, I've chosen Landscape Mixer

Select a preset or feed a custom image to the filter (here I chose a texture that I've on my computer)

Play around with the different sliders e.g. time of the day / seasons

Important: uncheck "Harmonise Subject" & "Preserve Subject" - these two settings are known to cause performance issues when you render a multiframe smart object (e.g. for a gif)

Once you're happy with the artistic effect, press OK

To ensure you preserve the actual subject you want to gif (bc Preserve Subject is unchecked), add a layer mask onto the top layer (with Neural Filters) and mask out the facial region. You might need to play around with the Layer Mask Position keyframes or Rotoscope your subject in the process.

After you're happy with the masking, flatten / render this composition file and voila!

Example 5: Putting it all together | sample gifset

Let's recap on the Neural Filters gifmaking workflow and where Stage I and Stage II fit in my gifmaking process:

i. Preparing & enhancing the component gifs

Prepare all component gifs and convert them to smart layers

Stage I: Add base colourings & apply Photo Restoration / JPEG Artefacts Removal to enhance the gif's image quality

Flatten all of these component gifs and convert them back to Smart Video Layers (this process can take a lot of time)

Some of these enhanced gifs will be Rotoscoped so this is done before adding the gifs to the big PSD composition file

ii. Setting up the big PSD composition file

Make a separate PSD composition file (Ctrl / Cmmd + N) that's of Tumblr dimension (e.g. 540px in width)

Drag all of the component gifs used into this PSD composition file

Enable Video Timeline and trim the work area

In the composition file, resize / move the component gifs until you're happy with the placement & sharpen these gifs if you haven't already done so

Duplicate the layers that you want to use Neural Filters on

iii. Working with Neural Filters in the PSD composition file

Stage II: Neural Filters to create artistic effects / more colour manipulations!

Mask the smart layers with Neural Filters to both preserve the subject and avoid colouring issues from the filters

Flatten / render the PSD composition file: the more component gifs in your composition file, the longer the exporting will take. (I prefer to render the composition file into a .mov clip to prevent overriding a file that I've spent effort putting together.)

Note: In some of my layout gifsets (where I've heavily used Neural Filters in Stage II), the rendering time for the panel took more than 20 minutes. This is one of the rare instances where I was maxing out my computer's memory.

Useful things to take note of:

Important: If you're using Neural Filters for Colour Manipulation or Artistic Effects, you need to take a lot of care ensuring that the skin tone of nonwhite characters / individuals is accurately coloured

Use the Facial Enhancement slider from Photo Restoration in moderation, if you max out the slider value you risk oversharpening your gif later on in your gifmaking workflow

You will get higher quality results from Neural Filters by working with larger image dimensions: This gives Neural Filters more pixels to work with. You also get better quality results by feeding higher resolution reference images to the Neural Filters.

Makeup Transfer is more stable when the person / character has minimal motion in your gif

You might get unexpected results from Landscape Mixer if you feed a reference image that don't feature a distinctive landscape. This is not always a bad thing: for instance, I have used this texture as a reference image for Landscape Mixer, to create the shimmery effects as seen in this gifset

5. Testing your system

If this is the first time you're applying Neural Filters directly onto a gif, it will be helpful to test out your system yourself. This will help:

Gauge the expected rendering time that you'll need to wait for your gif to export, given specific Neural Filters that you've used

Identify potential performance issues when you render the gif: this is important and will determine whether you will need to fully playback your gif before flattening / rendering the file.

Understand how your system's resources are being utilised: Inputs from Windows PC users & Mac users alike are welcome!

About the Neural Filters test files:

Contains six distinct files, each using different Neural Filters

Two sizes of test files: one copy in full HD (1080p) and another copy downsized to 540px

One folder containing the flattened / rendered test files

How to use the Neural Filters test files:

What you need:

Photoshop 2022 or newer (recommended: 2023 or later)

Install the following Neural Filters: Landscape Mixer / Style Transfer / Colour Transfer / Colourise / Photo Restoration / Depth Blur

Recommended for some Apple Silicon-based MacBook Pro models: Enable High Power Mode

How to use the test files:

For optimal performance, close all background apps

Open a test file

Flatten the test file into frames (load this action pack & play the “flatten” action)

Take note of the time it takes until you’re directed to the frame animation interface 

Compare the rendered frames to the expected results in this folder: check that all of the frames look the same. If they don't, you will need to fully playback the test file in full before flattening the file.†

Re-run the test file without the Neural Filters and take note of how long it takes before you're directed to the frame animation interface

Recommended: Take note of how your system is utilised during the rendering process (more info here for MacOS users)

†This is a performance issue known as flickering that I will discuss in the next section. If you come across this, you'll have to playback a gif where you've used Neural Filters (on the video timeline) in full, prior to flattening / rendering it.

Factors that could affect the rendering performance / time (more info):

The number of frames, dimension, and colour bit depth of your gif

If you use Neural Filters with facial recognition features, the rendering time will be affected by the number of characters / individuals in your gif

Most resource intensive filters (powered by largest machine learning models): Landscape Mixer / Photo Restoration (with Facial Enhancement) / and JPEG Artefacts Removal

Least resource intensive filters (smallest machine learning models): Colour Transfer / Colourise

The number of Neural Filters that you apply at once / The number of component gifs with Neural Filters in your PSD file

Your system: system memory, the GPU, and the architecture of the system's CPU+++

+++ Rendering a gif with Neural Filters demands a lot of system memory & GPU horsepower. Rendering will be faster & more reliable on newer computers, as these systems have CPU & GPU with more modern instruction sets that are geared towards machine learning-based tasks.

Additionally, the unified memory architecture of Apple Silicon M-series chips are found to be quite efficient at processing Neural Filters.

6. Performance issues & workarounds

Common Performance issues:

I will discuss several common issues related to rendering or exporting a multi-frame smart object (e.g. your composite gif) that uses Neural Filters below. This is commonly caused by insufficient system memory and/or the GPU.

Flickering frames: in the flattened / rendered file, Neural Filters aren't applied to some of the frames+-+

Scrambled frames: the frames in the flattened / rendered file isn't in order

Neural Filters exceeded the timeout limit error: this is normally a software related issue

Long export / rendering time: long rendering time is expected in heavy workflows

Laggy Photoshop / system interface: having to wait quite a long time to preview the next frame on the timeline

Issues with Landscape Mixer: Using the filter gives ill-defined defined results (Common in older systems)--

Workarounds:

Workarounds that could reduce unreliable rendering performance & long rendering time:

Close other apps running in the background

Work with smaller colour bit depth (i.e. 8-bit rather than 16-bit)

Downsize your gif before converting to the video timeline-+-

Try to keep the number of frames as low as possible

Avoid stacking multiple Neural Filters at once. Try applying & rendering the filters that you want one by one

Specific workarounds for specific issues:

How to resolve flickering frames: If you come across flickering, you will need to playback your gif on the video timeline in full to find the frames where the filter isn't applied. You will need to select all of the frames to allow Photoshop to reprocess these, before you render your gif.+-+

What to do if you come across Neural Filters timeout error? This is caused by several incompatible Neural Filters e.g. Harmonisation (both the filter itself and as a setting in Landscape Mixer), Scratch Reduction in Photo Restoration, and trying to stack multiple Neural Filters with facial recognition features.

If the timeout error is caused by stacking multiple filters, a feasible workaround is to apply the Neural Filters that you want to use one by one over multiple rendering sessions, rather all of them in one go.

+-+This is a very common issue for Apple Silicon-based Macs. Flickering happens when a gif with Neural Filters is rendered without being previously played back in the timeline.

This issue is likely related to the memory bandwidth & the GPU cores of the chips, because not all Apple Silicon-based Macs exhibit this behaviour (i.e. devices equipped with Max / Ultra M-series chips are mostly unaffected).

-- As mentioned in the supplementary page, Landscape Mixer requires a lot of GPU horsepower to be fully rendered. For older systems (pre-2017 builds), there are no workarounds other than to avoid using this filter.

-+- For smaller dimensions, the size of the machine learning models powering the filters play an outsized role in the rendering time (i.e. marginal reduction in rendering time when downsizing 1080p file to Tumblr dimensions). If you use filters powered by larger models e.g. Landscape Mixer and Photo Restoration, you will need to be very patient when exporting your gif.

7. More useful resources on using Neural Filters

Creating animations with Neural Filters effects | Max Novak

Using Neural Filters to colour correct by @edteachs

I hope this is helpful! If you have any questions or need any help related to the tutorial, feel free to send me an ask 💖