Tag Archives: Photoshop

Photoshop’s Generative Fill Isn’t Great, But It Works Well at Fixing Other GenAI Images

One problem with generative AI is that it’s difficult to get exactly what you want. You can often get something that’s good enough but more often than not, you get 90% of the way to what you want and getting the AI to make the correct changes to get to a 100% is daunting.

(which is why I’m a little skeptical about GenAI for video. For generic B-roll stuff, sure maybe, but wrangling the correct prompts for a 30 second video that needs to be exactly this or that is going to be difficult to say the least. It’s hard enough for a single still image.)

Photoshop’s Generative AI (called Generative Fill) is pretty subpar when compared to some of the more cutting edge ones (DALL-E, Stability AI, etc) for creating images from scratch. However, what it does pretty well is extending images. i.e. If you’ve got an image that you want wider or more head room than it was originally shot with.

OR… if you’ve created something with another AI tool, like DALL-E, as I’ve done here. DALL-E gave me more or less what I wanted but without much of a tail. I spent another 20 minutes or so trying to get DALL-E to give me this fish with a tail before giving up. It really wanted to redo the entire image. So it got frustrating.

This is where Photoshop’s GenAI turned out to be useful. To be fair, they market it as more of a way to extend/improve existing images than creating stuff from scratch. It can create from scratch but the results often aren’t great. But when it comes to extending images, there’s a big advantage to being in Photoshop… selections!

You can make the canvas wider, select the empty area to the side and type in ‘extend image’. Boom.

Now of course it gave me some other variations that didn’t work at all, but doesn’t matter. It gave me a great variation that did work.

Also, prompting something like ‘extend image with skeleton of an angler fish’ didn’t work. It was the simpler prompt ‘extend image’ that did the trick.

(Prompts are weird and a whole art unto themselves. Figuring out what the AI is going to respond to takes a LOT of trial and error. And then you still need to get it to do what you want.)

I then selected the other side and it created that easily.

You can see slight seams where the image was extend. When having Photoshop create the extensions, I tried both selecting the area by itself and selecting a little of the original image (including feathering it). It didn’t really make much difference. You got slightly different imagery but the seams tended to show up no matter what.

The tail was the worst problem however. There was an obvious change in style from the original to the Photoshop extension.

So I selected just that bit and ran Content Aware Fill a few times to cover up the seam. And that worked reasonably well despite CA Fill not being AI. It’s just sampling from other parts of the image.

Selecting the seam and running Generative Fill (prompt: ‘remove seam’) on it created three variations. Two of the three didn’t work but the third one arguably looks better than CA Fill. But they’re both pretty good. So just realize CA Fill can help touch up slight imperfections as well.

Getting DALLE, Midjourney or whatever to give you exactly what you want can be difficult. If you get most of the way there, but are having trouble prompting those tools to fill in the details, Photoshop’s Generative Fill may be able to touch things up or extend the image more easily.

Here’s the final image:

Creating GIFs from Video: The 4K Animated GIF?

Like Us On FacebookLIKE Digital Anarchy!

I was at a user group recently and a video editor from a large ad agency was talking about the work he does.

‘web video’ encompasses many things, especially when it comes to advertising. The editor mentioned that he is constantly being asked to create GIF animations from the video he’s editing. The video may go on one site, but the GIF animation will be used on another one. So while one part of the industry is trying to push 4K and 8K, another part is going backwards to small animated GIFs for Facebook ads and the like.

Online advertising is driving the trend, and it’s probably something many editors deal with daily… creating super high resolution for the broadcast future (which may be over the internet), but creating extremely low res versions for current web based ads.

Users want high resolution when viewing content but ads that aren’t in the video stream (like traditional ads) can slow down a users web browsing experience and cause them to bounce if the file size is too big.

Photoshop for Video?

Photoshop’s timeline is pretty useless for traditional video editing. However, for creating these animated GIFs, it works very well. Save out the frames or short video clip you want to make into a GIF, import them into Photoshop and lay them out on the Timeline, like you would video clips in an editing program. Then select Save For Web… and save it out as a GIF. You can even play back the animation in the Save for Web dialog. It’s a much better workflow for creating GIFs than any of the traditional video editors have.

So, who knew? An actual use for the Photoshop Timeline. You too can create 4K animated GIFs! ;-)

animated GIF

One particularly good example of an animated GIF. Rule #1 for GIFs: every animated GIF needs a flaming guitar.

Creative Cloud from a Software Design Perspective

The Creative Cloud has gotten mixed reviews from users. Many users don’t like the idea of ‘renting’ software and feel Adobe is forcing them to pay more or gouging them. While this may or may not be true, there are other reasons for Adobe wanting to make this switch.

Software is traditionally done in big releases. You work for a year or more and deliver the final product with much fanfare. This is a feast or famine type of thing… users get all or nothing and the company bets the farm that the release is all that and a bag of potato chips. This really isn’t great for either users or the company.

Continue reading Creative Cloud from a Software Design Perspective

What Does the Creative Cloud Mean to You?

Last month we asked folks to do a survey about the Creative Cloud and how they felt about it. I thought I’d share the results as some of you may also be curious what you’re fellow users are thinking about the Creative Cloud.

Creative Cloud

Keep in mind that the survey was done before Adobe announced the price drop on Photoshop & Lightroom to $10/mo. So the data is already somewhat out of date, but maybe sheds some light on why they dropped the price.

Continue reading What Does the Creative Cloud Mean to You?

Photo Manipulation, Contests, and Getting Disqualified

Good article here about how the photo that would have won the National Geographic photo of the year, got disqualified because the photographer used Photoshop to get rid of a trash bag instead of cropping it.

If you’re going to enter contests it’s a good thing to read the rules, but it’s almost a certainty that if you bust out the clone tool or use Content-aware Fill you are going to be disqualified. Obviously if it’s a photo manipulation contest that’s different, but most photography contests want you to do everything in camera, limiting adjustments to minor tweaks like cropping and contrast, things that were relatively easy to do in the darkroom days.

While you might argue what’s the difference between cloning a trash bag out of the photo and cropping it, it’s a very slippery slope. It rapidly becomes more about your Photoshop skills and less about your photography skills. If it’s a photography contest, then it should be about your photography skills.

Here’s the disqualified image, click on it to read the full article and see the original.

disqualifed Photoshopped photo

I hate HDR

Ok, well I only hate one common use of it. That surreal, oversaturated look that seems to be the first thing everyone does when they try the technique. You don’t even need to use HDR, there’s a photoshop plugin for it and you can use Camera Raw to pull it off. Here’s an example of the style:

HDR gone bad

HDR Gone Bad

It’s a novelty look and I’m over it. It was cool for a very short time, then everyone decided they wanted to have surreal images. It’s not that hard of a look to achieve, so it’s not that impressive. Get over it.  :-) I much prefer to use HDR for what it was meant for… which is giving a slightly wider dynamic range to create a shot that has similar contrast and color range to what your eye actually sees. No one has seen colors like the photo above has. Alright, well, yeah I’ve taken mushrooms too, so maybe then… but not normally.

The better use for HDR…

Continue reading I hate HDR