Adobe finally has said they are working on their new Export Mode failing to load in Premiere Pro 23.2 and 23.3

Of late when I tried to export from Premiere Pro this is the screen that I got. And this after the them getting rid of the old export window for this new monstrosity (please see this very long thread at Adobe on the monstrosity).

For a little while there I could get it to work if I trashed my preferences and re-synced and the export would work for a few seconds, but this stopped working.

Then thanks to this thread at Adobe, I found that deleting my 23.0 folder from User/Username/Documents/Adobe/Premiere Pro fixed the problem for a single export, then it stoppwed working.

So then I have been using Media Encoder to open the Premiere Pro sequences directly. The Media Encoder version that I had been doing above, reset premiere pro preferences which worked for a while, and 3 the Match Sequence Preview Settings, but I can’t even get to the Export window for that to show up.

Well Finally Adobe has admitted the issue, and posted about it with work arounds.

AppleInsider Reports on Apple acquiring AI-Powered video compression startup WaveOne

Amber Neely has the news that Apple purchased an AI Video Compression company.

This is of course for iPhones, as the technology is made to cut file sizes in half while prioritizing Faces and Text and de-prioritizing backgrounds.

Better video compression is always to be looked for, but I am assuming this won’t be like ProRES HQ or 4444, but more highly compressed, so likely won’t be a great editing compression.

At NAB Adobe Introduced Text-Based Editing in Premiere Pro and a Properties Panel in After Effects

From Eric Philpott’s article at Adobe Blog.

This is huge and I love that it’s awesome transcription feature is being expanded out of for captions into actual editing.

I will have to see automatic tone mapping in action, I always get footage from different cameras, but I don’t think this will be what I need (I tend to throw the clips in DaVinci and make a LUT that will match them perfectly).

Background Auto Save is exciting, and I might turn it up so it saves more often.

Dragging to select track targets should have been there from the start! I will use that literally every day!

And bulk editing titles in the Timeline is huge, and has been needed since you could see all the Text of titles with the text tool.

And After Effects Properties panel could be a huge game changer, as on a daily basis i get frustrated when duplicating sequences how it doesn’t show the same properties that I was manipulating on the copied layer, but with a properties panel this should be faster, and anything faster I will adopt immediately.

And I really need to do a deep dive in to ACES and OpenColorIO workflows so I can try it out in After Effects.

And select able track mattes usable for multiple layers is pretty awesome, though you could do it by doing it on a matte layer and using it as the matte.

And defaulting colorama to the default color picker to save clicks is another time saver, and I always want time savers.

Late last night I got into the Adobe Firefly Generative AI Beta and started playing around

This week Adobe announced their new Firefly Generative AI Beta that you can sign up for. I did on the first day and got in around 8 PM last night. I was playing on my iPad last night (which was fun) though the download buttons seems a little funky on iOS and it didn’t download everything that I asked it to. So I played some more on my Mac today.

There currently 2 active modules, Text to Image and Text Effects.

My name as a text effect with Humpback whales, and the effect set to loose on the characters. You can see the created by Firefly Beta and not for Commercial use bug on the corner.
And my mom’s name done in orchids
And my wife’s name with a tight Steampunk Effect

The type effects are very cool and fast. My biggest complaint was it certainly can’t do one plant or animal per letter, it uses them more as textures than objects, but still I will be using this quite a lot for certain things.

And as for Text to Image, you certainly have to get the prompt right.

For 1960’s psychedelic guitar playing man with beard onstage at woodstock, it went for a modern and disturbing image.

Fairly impressive hands, though those sunglasses, and not sure about the hair in some.

I then tightened it to psychedelic guitar playing man with beard on stage at woodstock in 1968 and things got more interesting.

Love the first and 3rd, then went for graphic instead of photo of the same.

The 2nd one is much more interesting this way, and the 3rd has Floyd from the muppets eyes, or maybe the grateful dead, no idea, but creepy, and the 4th is pretty damn fantastic, though a strangely 7 string guitar with 4 strings.

And then went for an art variation.

These are all pretty damn amazing!

And I do love the controls for image refinement,

And I tried to do some imagery for my short film THE MISADVENTURES OF BEAR, while I do love what it came up with. It certainly isn’t listening to the “dark hallway at night” it is a hallway, But it is certainly lit, and I can’t seem to get it to go dark. The first 4 are art, and then photo afterwards.

And the next are photo.

And then i stayed on photo but tried to go darker, but setting color and tone to cool, and lighting to low lighting.

And then I changed the promp to down a hallway in the dark to see if that would do it, and it didn’t, but I do like the clothing variations it added.

So wow, a really powerful tool I will keep playing with, but it doesn’t seem to know how to do low light or unlit images, or day for night?

Adobe’s AI art generation tool Firefly enters Beta

And you can currently sign up for the beta on the Firefly site right here.

AI has made such an explosion lately, especially Midjourney, which I so want to play with, but don’t really want to pay for just to play. This adobe version seems ideal for me as someone who already subscribed to the creative cloud, and with elements that can be used within Adobe products.

And the Text Effect seems really amazing.

I really want to see one of these that you can put your own images into it and get variations on that coming out (I do believe midjourney does that).