When we think of skin retouching we usually imagine digital makeup applied to commercials and music videos, but very rarely consider skin smoothing as a tool to remove distractions and improve image quality in documentary films. Nisma Zaman, winner of a Daytime Emmy and several other awards for television and film producing, decided to try using Digital Anarchy’s Beauty Box presets in Adobe® Premiere® Pro, the industry leading video editor, to assemble a challenging project, where the interviews were filmed outdoors under heavy sunlight, with little time, equipment, and space to get the lighting perfect. Zaman produced and edited a short documentary video featuring seven prominent artists during their creation of murals for ArtBridge’s #7on16th project, an exhibition of 7 female and non-binary NYC street artists. Over the course of 5 days, the filmmaker followed each artist, even riding up 14’ above street level in scissor lifts, as they built the mural to compile a creative overview of the week-long installation. She also worked with her team to create time-lapses and a photo series that digitally recreated each mural for ArtBridge’s project brochures using Adobe Photoshop. To create the digital photo series, Zaman took individual high-resolution frontal photos of the entire mural at even spaces along the block, and then made use of layers, feathering, and the Perspective Warp tool to produce each mural image. The digital murals were then imported into Premiere Pro, along with all other types of documentary footage, where the filmmaker used Digital Anarchy’s Beauty Box to correct distractions on the interviewee’s faces caused by skin shine and uncontrolled light. For the ArtBridge project and all the other artist profile projects that she applied Beauty Box to, Zaman makes sure to reduce the smoothing amount percentages to between 20-30% so she can get the most natural look possible. “I learned that skin smoothing can be an ally to reduce some visual distractions and focus the viewer’s attention on what the interviewees are saying”, explains Zaman. In her opinion, it is also important to always select the dark and light colors for the mask. This allows Beauty Box to identify the range of tones on a subject and adjust the skin smoothing accordingly. The tips come from over 5 years of experience taking advantage of a seamless integration between Premiere Pro and Beauty Box to perfect profile videos on artists, curators, and art professionals. “Just like using Premiere Pro native transitions such as Lumetri Color and Warp Stabilizer, applying Beauty Box to the footage was a quick and easy process in every project I have edited. It is a huge time-saver and a great way to make people look more rested”, Zaman concludes. With extensive background in producing reality-based films for a variety of audiences, Nisma Zaman edits all her films in Premiere Pro, and used the Beauty Box plugin for the first time while working at the Guggenheim Museum, where she produced over 160 videos filmed in NYC, Singapore, Hong Kong, London, and Mexico City. She is known for the high quality and great content of her videos, always leveraging extensions available as part of the Adobe Video ecosystem to deliver creative and compelling storytelling. To learn more about her work, visit https://nismazaman.com/ .
Downloading plugins and demos from our website
One common thing that support gets contacted about is how to download plugins you’ve already purchased. These are available on the Demos page (now called Downloads | Demos). The Demo version is exactly the same as the release version. You enter your serial number or log in and that removes the watermark. So if you see the ‘Demo’ version, that’s exactly what you need. We’ve changed the Main Menu on DigitalAnarchy.com to show ’ Downloads | Demos’ (instead of ‘Demos’) to make this a little more obvious. But the Download page still talks about ‘demos’ a lot, so don’t be put off because of that. These are still the files you want to download. Once you’ve downloaded and installed the plugin, the first time you apply the plugin to a clip in your host app it’ll pop up a dialog asking for your serial number. Enter that and it’ll get rid of the watermark. (FCP sometimes has a problem with this, here’s a tutorial on how to fix it) If you’ve previously registered the plugin and are just re-installing it, your license should be on the machine, so you won’t need to enter in your serial number again. If you get an error message saying ‘Contact Digital Anarchy’, please check your plugin folder to make sure there’s only one copy of the plugin. Sometimes the installer doesn’t uninstall the previous version of the plugin. For example, you might have Beauty Box 4.2.3 and Beauty Box 5.1 installed. If so, manually delete 4.2.3, restart your host app, and the error should disappear. It’s also helpful to know what version you purchased. If it’s not the latest version you’ll need to scroll down a little to find, say, Beauty Box 4.0. The Beauty Box 5.0 installers will be listed at the top of the Beauty Box section, so you need to scroll past those to get to the 4.0 or earlier installers. If you have an older version and want the latest version, you can get a discounted price by going to the Upgrades section of the DA Store. Enter in your older serial number and you’ll get a discount of up to 50% vs. a brand new license. Newer versions have new features, bug fixes and support the latest OS. While your license for an older version is always good for that version, we only update the newest version with bug fixes. So if the OS or Host App breaks an older version, you will have to upgrade. So head over to the Downloads | Demo page and grab the latest version of your plugin!
How to use Flicker Free with other effects
Flicker Free is commonly used in conjunction with other effects which can cause errors and slow renders if you do not adjust your settings correctly. If you’re using Warp Stabilizer, Lumetri color, or any color correction effects in addition to Flicker Free in your editing, it’s possible you’ll want to render Flicker Free separately to avoid frame processing errors, host-app crashes and export problems related to your GPU running out of memory. Creating an intermediary render that just has Flicker Free applied, and applying color corrections and effects to the intermediary render can solve a lot of problems. It’s an easy way of solving out of memory errors. These errors happen because Flicker Free works by analyzing a range of frames on the GPU, and can conflict with other effects that are also using GPU processing. They are even more likely to happen if the effects used in conjunction with Flicker Free require heavy GPU processing, like the Warp Stabilizer effect. For example, if Flicker Free is analyzing 15 frames, Warp Stabilizer has to be applied to all 15 of those frames before FF can look at them. This can creates a huge memory bottleneck. Here’s what we recommend as a workflow to combine Flicker Free with other effects without causing any GPU related issues: Always apply other effects after Flicker Free on your clip. (i.e. Warp Stabilizer is applied after FF, so FF just needs to look at the original frames, not the stabilized frames.) This may solve the problems without needing to render another file out. That’s always the first step. However, if you still run into problems, rendering out separate de-flickered clip is the way to go. If exporting/reimporting is not possible, again we recommend at least making sure Flicker Free is applied first – at the beginning of the effects chain (it’ll show up as the first effect in the Effects Control panel) – so it renders using just your clip instead of taking other effects into consideration. It’s also important to check your GPU memory capacity and graphics card specs. If you are still having problems after applying Flicker Free first, you can send your system info plus a screenshot of your timeline and Effect Controls to cs@digitalanarchy.com. Our tech support team will be able to help troubleshoot! Before taking the screenshot please make sure to select the panel with the clip Flicker Free is applied so we can see the Flicker Free settings and any other effects, as well as how the timeline is set up. For a step-by-step guide on how to use Flicker Free with other effects and simple ways to troubleshoot error messages (and visual glitches!) watch this video tutorial: https://www.youtube.com/watch?v=uY2a531qGug&t=12s
Only Beauty Box 5.x Supports Metal GPUs and Apple Silicon
Beauty Box 5.0 and higher supports Metal and Apple Silicon (M1, M2, etc.). This includes the upcoming Beauty Box 6. However, Beauty Box 4.0 does not support Metal GPU rendering on Macintosh. It uses the older OpenCL technology for GPU processing. (on Windows, 4.0 works fine) Premiere Pro/After Effects 2022 and later dropped support for OpenCL rendering, and only supports Metal on the M/Silicon chips and Intel Macs. This means Beauty Box 4.0 does not support GPU rendering in the current Intel builds of After Effects or Premiere. It doesn’t work at all on Silicon Macs. If you’re experiencing slow rendering in Adobe products on a Mac with Beauty Box 4.0 or it’s not showing up at all, that’s probably why. So if you have 4.0 and have an Intel Mac, you’ll probably want to upgrade to 5.0. If you have a M/Silicon Mac you’ll need to upgrade. 5.0 was released before the Silicon chips and that’s the only version of Beauty Box that’s been re-written for those chips. On Windows, Beauty Box 4.0 should still work fine. Both OpenCL and CUDA (for Nvidia) are still supported by Premiere and After Effects. If you’re experiencing slow render times in 5.0 on Intel, double check that Hardware rendering is set to Metal. (on Apple Silicon Macs, it is always set to Metal and you can’t change it) In both Premiere and After Effects go to File>Project Settings>General to change If this is not why you’re having a problem with Beauty Box, try these articles or contact support: Reasons Plugins Might Not Show in the Effects Menu Use GPU can be turned off in the plugin or the Beauty Box ‘About’ dialog.
Here’s why your plugins aren’t showing in the host application
Not seeing your plugins in the host app is likely easier to fix than you think! When the installation process is completed properly, all Digital Anarchy plugins will show inside the Digital Anarchy folder located in your Video Effects folder, ready to be dragged and dropped into your timeline. However, compatibility issues, corrupted installations, and having multiple versions installed could be preventing the plugin from connecting to the host app and appearing as an option in your effects folder. Here are the main reasons your plugin might not be showing in After Effects, Premiere Pro, FCP, Resolve or Avid – and how to quickly fix them. PS: If you are in Premiere and saw the plugin disappear after downloading their latest update or after a crash caused by a Digital Anarchy plugin, scroll down to “4” and check if the plugin is not hidden before trying other things! The option to disable plugins in the Video Effects Manager was always a thing in After Effects, but recently added to Premiere Pro. 1. Installation did not complete properly The most common cause for plugins not showing in the host app is problems in the installation process. For the installation to complete successfully, all host apps must be closed before running the installer. So if the plugin – or the entire Digital Anarchy folder – is not showing up please make sure all apps are closed and re-run the installer. You can also check if the plugins were installed in the correct folder. We recommend not making any changes to the file paths set or used by the installer, but even if no changes are made, files could have been misplaced due to system permissions in both Windows and MAC systems. Windows: For each folder in the path, right-click and select Properties > Security and make sure the designated user doesn’t have any restrictions. Premiere – C:Program FilesAdobeCommonPlug-ins7.0MediaCoreDigital Anarchy AVID – C:Program FilesAvidAVX2_Plug-InsDigital Anarchy Resolve – C:Program FilesCommon FilesOFXPluginsDigital Anarchy MAC – For each folder in the path, right-click and select “Get Info” > Sharing & Permissions and make sure the designated user is set to “Read & Write”. Premiere – Macintosh HD/Library/Application Support/Adobe/Common/Plug-ins/7.0/MediaCore FCP – /Applications/Digital Anarchy AVID – Macintosh HD/Library/Application Support/Avid/AVX2_Plug-ins/Digital Anarchy Resolve – Macintosh HD/Library/OFX/Plugins/Digital Anarchy 2. Incompatible Version Always make sure that you have the latest version installed. All of the latest versions are available under “Demos” at https://digitalanarchy.com. Most of the time you may just have a slightly older version installed and that can be the reason for it not appearing in your host application or for any other issues. Attention Mac users! Older plugin versions like Beauty Box 4.0 and Flicker Free 1.0 are not compatible with the new Apple M-series chip machines. If you have an older version of a plugin that was purchased a while back, buying an upgrade may be required. Check our store for upgrade prices: https://store.digitalanarchy.com/24-upgrades Required paid upgrades are rare, but do happen sometimes since our plugins are license-based and not a subscription. More recent purchases (2019 and later, depending on the plugin upgrade release date) are eligible to receive a free upgrade. If you are not sure your purchase qualifies, please email our sales team at sales@digitalanarchy.com. After upgrading your serial number, make sure all apps are closed, download and run the most recent installer for the plugin. All installers are available under “Demos” at https://digitalanarchy.com Incompatibility issues are also frequent in the latest version of FCP. If that’s what you are using it is likely you will need to run the latest version of our plugins. Check with our sales and tech support teams if you have questions! 3. Update didn’t uninstall the previous version If the plugin does not show after you install an update/upgrade, please make sure that the uninstaller properly removed the previous version from your machine. Some host apps will warn you if there are two versions of the same plugin installed but that is not always the case. The uninstallers are included in all installer downloads available on our website. For Windows, the uninstaller will first run automatically when you run the installer, if it detects that there is already an installed version. For Mac, the uninstaller can be found in the same folder as the installer and can be run manually, apart from the installer, if previous versions are not removed automatically. Make sure to close all apps before running the uninstaller and/or a new installer. 4. Plugin is disabled in Premiere or After Effects If you are using Premiere or After Effects, make sure the plugin is not set to be disabled in the effects preferences. In After Effects: Go to “Effect”. Click on “Manage effect” and make sure the plugin is enabled In Premiere Pro: Click on the “Sandwich” menu close to “Effect Controls”. Click on “Video Effects Menu” and make sure the plugin is enabled. 5. Effect is filtered out in FCP In Final Cut Pro, the Effects Browser has a search field at the bottom with filters for 4k and HDR: If the HDR filter is checked, our effects will be hidden. So if you see the Digital Anarchy section under “VIDEO” in the Effects Browser but don’t see any effects, uncheck the HDR filter to un-hide the effects. If you are still having problems, please send us an email at cs@digitalanarchy.com!
Free NAB 2024 Exhibits Pass, Come See Beauty Box 6.0
NAB is three months away! We have a booth right next to Adobe in South Hall Lower, SL7043, so we’ll be easy to find. If you haven’t registered yet, you can use this code for a free exhibits pass: NS9892 Go here to register for NAB: https://registration.experientevent.com/ShowNAB241/ We’ve got a new version of Beauty Box, our AI based digital makeup and retouching plugin, coming soon! It’ll be released before NAB, but we’ll definitely be showing that off. The big new feature uses AI to whiten teeth. We’ve always used AI in other ways in Beauty Box, but this is a much more sophisticated version. We’ve put a lot of work into it and we’re pretty excited about it. There will also be a couple other announcements/release around April, so stayed tune for that. If you haven’t chatted with us lately, come by the booth and say hello. You can learn about all the new stuff. Including Data Storyteller which we released a few months ago and won a Best of NAB 2023 from Videomaker!
Data Storyteller: chart and map visualizations for Premiere Pro, After Effects and FCP
NAB Update: Data Storyteller wins Videomaker’s Best of NAB 2023 award! It was great going to NAB and getting validation from Videomaker and many of the folks that came by the booth that there is definitely a need for better data visualization tools for video production. Please sign up for the beta and let us know what you think! I’ve had a fascination with data visualizations for a while. When done right they can get be both beautiful and incredibly informative. And with the world awash in data, big and small, there’s a lot of stories that can be told by looking at data. Data Storyteller is a plugin for Adobe After Effects, Premiere Pro and Apple Final Cut (Resolve is coming!) that hopes to make this easier for video production. We’re about to go into beta with it, so if you’re interested in joining the beta, reach out to:beta@digitalanarchy.com We realize that individual video editors don’t need to do this kind of work all the time, but it does come up. And for some of you it comes up a lot! So there needs to be a better way of creating visualization, be it a simple bar chart or a Bubble chart showing years of data, than trying to shoehorn Excel charts into video. The focus will be to try to make it as easy as possible to create cool visualizations. There will be various templates to start with as well as a Wizard to guide the initial creation. Of course, often the hard part with data viz is selecting the data to visualize. So that part you’ll have to figure out. 🙂 But once you do, hopefully we can make the animation part relatively easy. 1.0 will support Bar, Line, Scatter/Bubble charts as well as maps for US and the world. All of these can be linked to simple CSV or Excel files for basic animations or you can create more complex animations using larger data sets or even multiple data sets (e.g. 25 files with 25 years of the same data). We have plans for more chart types but those are the initial charts. The backend for Data Storyteller is D3.js so there are many chart types we could do in the future. We’re still a month or two away from release, but we want to get it into the hands of those interested in doing this type of work. So if you want to get the beta when it’s available, please reach out to beta@digitalanarchy.com Our team of anarchists will be at NAB 2023, booth #N1316 (North Hall) demoing the beta of DataStoryteller – So you can check out the two new plugins and the types of animated charts and map visualizations that can be created. Best,Jim TierneyChief Executive Anarchist Here are the Key features DataStoryteller offers: Support for Simple or Complex Data: Imported CSV or Excel files can be simple spreadsheets or more complex, with multiple sheets or large data sets. Built-in Spreadsheet: A built-in spreadsheet allows users to see and select all of the data or select specific cells, rows, and columns that they wish to visualize. Multi-file Animation: One of the strengths of Data Storyteller is the ability to upload multiple data sets. For example, multiple years of census data can be uploaded and then animated year by year, creating complex visualizations that tell a story with much more depth than a simple bar chart. Range/Filter Animation: Editors can choose to slowly reveal or hide data by animating the spreadsheet selection or filtering values that are higher or lower than a user defined threshold. By using keyframes that determine when and where each new data point appears, it is possible to create animations that animate specific data for more impact. Multiple Dimensions: Another strength is support for data with many attributes. For example, in our Census data, for different cities you might want to show Age, Income, Crime level, and Cost of Housing. Any of these can be used to control X position, Y position and Size and Color of the resulting data point. All of which can be animated over time. Preset Templates: A wide variety of templates help users get started on creating beautiful data visualizations. Vector Charts: The charts are all vector based graphics, so can be rendered at any size, including HD, 4K, 8K, 12K or higher. DataStoryteller charts and maps can be setup from scratch or by using a template. Setting up a basic chart works much like creating graphics in Excel or Apple Numbers, with the advantage of all features being tightly integrated with the video editing platform. The integration with After Effects, Final Cut and Premiere Pro makes it easy to apply changes and show the animations in the video editing application, without the need to export/import files back and forth.
The Different Ways Customers Use Beauty Box
I was interviewed for an article in the Telegraph about retouching in film/TV. The final article sort of missed the point, as non-industry publications often do, that it’s hard to make humans look good with bright video lights, cameras, and all the things that production involves. (they spun it as an ‘A-list vanity’ thing) But it did get me thinking about how different users deal with that production problem when using Beauty Box. (Link to the article is at the bottom of the post) I do find it interesting talking to different customers who are using Beauty Box for different purposes. It’s used on an extremely wide range of productions from low budget wedding videos to feature films. And, of course, how it’s used on those productions varies widely as well. On the lower budget end, the editor generally applies it to the entire clip, hits Analyze Frame, dials in some settings to make the subjects look a bit better and then calls it a day. The budget isn’t there for a lot of fine beauty work (just like there wasn’t a budget for a makeup artist). The above may be the case if the editor is pressed for time… turning around video shot earlier in the day at an event or for news, where it needs to go live the same day. The basic settings work very well for applying a layer of digital makeup that offsets the lack of makeup, bright video lights or any of the other factors that make a subject’s skin look bad in a video. We’ve worked hard to maintain the texture of the skin so that you have a very realistic application of the smoothing algorithms. When Beauty Box users have a bit more time/budget the workflow changes a bit. They can set up tracking masks and just retouch, say, the forehead or the cheeks. This is much more detailed beauty work and you can see some tutorials on using tracking masks here. Generally this is how Beauty Box is used for commercials, TV, etc. As you get up into feature films, where there are definitely budgets for makeup artists, we see Beauty Box being used for makeup heavy applications. For example, in LBJ, Woody Harrelson needed to prosthetics to make him look older. As such, digital retouching was used to make those more seamless and realistic. Same goes for films in the fantasy genre, if you’ve got a bunch of elves, orcs and whatnot running about, you may have some makeup problems that need fixing. That’s generally where Beauty Box is a critical tool. It’s cool to hear about the wide range of productions it’s used on. The idea for Beauty Box came from watching a talk given by a music video vfx artist at Motion Graphics LA in the mid-2000s. He discussed his process of going frame by frame, duplicating skin layers, etc. I figured there had to be a better way of doing that and a few years later Beauty Box was born as the first beauty plugin to take the problem seriously. (There were a couple other plugins out there that purported to do it, but they were just applying a blur to a masked area and it didn’t look realistic. Beauty Box not only smooths the skin but tries to keep the original skin texture giving a much more realistic look) So to see it used on feature films, episodics, reality and so much more is one of the amazing things about making these tools. lol… of course, customers will tell us about this stuff privately, but getting folks to give us permission to talk publicly about specific shows/films is tough. If you’re doing something cool with Beauty Box and are willing to let us talk it up, please shoot me an email! (jim@digitalanarchy.com) And P.S…. We’re hard at work on Beauty Box 6.0, using A.I. and some other advanced tech, so look for that coming shortly. (And we give free upgrades to folks that let us say nice things about their Beauty Box work, so…. 🙂 Here’s a link to the Telegraph article. fyi… it’s behind a paywall and if you sign up for the free trial, you’ll need to CALL them in the UK to cancel. You’ve been warned. 🙂 The article is not as skewed as the headline suggests, but it does largely miss the point that this is a video production problem as much as (or more so) a vanity thing. https://www.telegraph.co.uk/films/0/digital-de-ageing-hollywood-lying-us-secret-side-special-effects/
Transcriptive tools for Documentary Filmmaking
Interview-based productions were already one of the main use cases for AI transcriptions when we first released Transcriptive. Having all content converted into text meant the footage was searchable, and the ability to create captions allowed video editors to comply with accessibility and broadcasting requirements. What we didn’t know was how much documentary production workflows would play a role in the plugin development: we added the ability to transcribe not only sequences, but also entire clips, comments and strikethrough can now be added to transcripts, Transcriptive.com lets production teams collaborate outside of Premiere if need be. PowerSearch became such an essential tool to find content in a project that we included it with Transcriptive Rough Cutter, and the ability to use transcript text to cut video made a product that started as an AI transcription tool become a pretty complete suite of products with different workflow options – very different from everything we had done so far. This week we received an email from a client who has been using Transcriptive since the beginning. He was asking if we could save him some time from learning all the new additions to the plugin – there are many indeed! – and highlight a few essential “new features” that focus on interview-based productions. So here we are, sharing our favorite new features with you all. Read on and learn more about them! Clip Mode: we added the ability to transcribe clips a while back, but some people have been so used to transcribing sequences that they do not realize turning “Clip Mode” on can be a game changer when there’s a high volume of interview footage to sort through. By transcribing the whole clip you can have all content – not only the cuts on your timeline – searchable, and use the clip to enter soundbites into the timeline straight from the transcript. Clip mode also lets you create or import transcripts for individual media files (as well as multicam clips). These transcripts are attached to the files and will load whenever you open that clip in the Source Monitor, which makes it easy to search for specific quotes and add them to a sequence. Offline Alignment: some productions still prefer to use human transcripts, especially if their interviews have very specific jargon or scientific terms. Using transcripts generated outside of Transcriptive also becomes a necessity if the interviews hold private information and privacy is a concern. Transcriptive does require internet connection to create new transcripts, but offline alignment makes it possible to import existing transcripts to either a clip or sequence. It is only available for English, but the alignment is free of cost, analyzes the text and audio, and syncs them up word for word. If you have a lot of transcripts to align you can use Batch Alignment to submit them all at once. Import all of the transcripts, select those clips and sequences in the Project panel, and select Batch Project to queue up all the alignments at once. An important note: when aligning transcripts offline you’re free to use Premiere for other things while these process. Just make sure to do not close Premier until the offline alignments are finished. PowerSearch: our “Google like” plugin is still the best way out there to find content in your Premiere project, and Transcriptive Rough Cutter users no longer need to pay extra to use it. Your Transcriptive serial number now also activates PowerSearch. The panel is more efficient than using the search box in Transcriptive because it searches the transcripts in your entire project all at once, displaying a list of results for each clip and sequence where your search term appears. Clicking on one of these results opens that clip or sequence in the Program Monitor or Source Monitor and jumps to the location of that line. This makes it easy to find specific dialogue anywhere in the project. If you’re using markers to label your clips/sequences, PowerSarch can search marker text as well. Rough Cut: the option to use shortcuts to enter soundbites into a sequence, straight from the transcript text, is one of our newest – and most powerful – additions to Transcriptive. Set an in (Ctrl+i) and an out point (Ctrl+o) in the transcript, select the sequence and press Ctrl+Comma (Windows) or Ctrl+8 (Mac) to insert the select. That’s it! Keep adding selections from different clips to to quickly assemble a rough cut. Also, if you strikethrough (using the Strikethrough button next to a paragraph in the transcript) or delete text, you can click the Create Rough Cut button to generate a new sequence with all of the deleted areas removed. This is an easy way to cut down, for example, an hour long interview into a shorter sequence using just the transcript text. This new sequence will have a transcript synced with those edits that you can export, search, or index with PowerSearch. Transcriptive.com is also an amazing addition to Transcriptive although not specially important to documentary productions. Learn more about our web app here: https://digitalanarchy.com/transcribe-video/app/features.html Have a favorite feature you love, but was not mentioned here? Let us know which one! We would love to hear from you: cs@digitalanarchy.com.
Beauty Box 5.0 Tips to Speed Up Video Skin Retouching
Beauty Box 5.0 can retouch skin while maintaining real-time playback on 1080p footage on most machines, and real-time playback or close to it on 4k footage on faster machines. Render speed does depend on a lot of factors, like the GPU speed of your computer, the resolution of the footage, having other effects applied, and the host application you’re using. Here are some things you can check to make sure you’re getting the best performance out of Beauty Box. Make sure the plugin is using the GPU to render The most important factor for better speed is to have Beauty Box use your machine’s GPU to render. In the plugin effect controls, there will be a “Use GPU” checkbox at the bottom – make sure this is checked, and that it isn’t grayed out. If “Use GPU” is grayed out, here’s how to re-enable it: Go to this location: Windows: Documents\Digital Anarchy Mac: Users\Shared\Digital Anarchy And find one of these files: DA_OpenCL_Devices.txt DA_CUDA_Devices.txt DA_Metal_Devices.txt Open the file. You should see something like the screenshot below. If Enabled = Off, change the text to say Enabled = On, then save the file. Restart your editing application and now the checkbox should be active. Open the file. You should see something like the screenshot below. If Enabled = Off, change the text to say Enabled = On, then save the file. Restart your editing application and now the checkbox should be active. Having “Use GPU” disabled by default is most common when installing Beauty Box for the first time, but also may happen after updating your computer or host application. If Beauty Box seems to be causing slow playback in your projects, check that file to make sure Beauty Box is actually using the GPU. Apply Beauty Box before other effects If you are color correcting your video or using other effects on the same footage Beauty Box will be applied, remember that the order that effects are applied can have an impact on render speed. We generally recommend applying Beauty Box first, before other effects and color correction. In some rare cases, Beauty Box will perform better as the last effect applied – if it’s working slower than usual at the top, drag it to the bottom of the effects list, below your other effects. But usually having it applied first will make rendering faster. Know what works best for the host app you are editing on: Premiere and FCP are faster than After Effects at this point in most of our tests (as of AE and Premiere 2022, and FCP 10.6.3), although this can change over time as different applications add new features and optimizations. Here are a few applications-specific tips: Premiere Pro: Make sure the renderer is set to Use the GPU. Go to File > Project Settings > General. In the General tab, under Video Rendering and Playback, set the Renderer dropdown to Mercury Playback Engine GPU Acceleration (CUDA/OpenCL/Metal). (CUDA) is for Nvidia GPUs, (OpenCL) is for AMD GPUs, and (Metal) is for Apple GPUs. IF this is set to Mercury Playback Engine Software Only, your project won’t use the GPU to render, and Beauty Box will render more slowly – you generally will only want to use Software Only with Beauty Box if you’re running into an error with one of the GPU Acceleration options. After Effects: The same Premiere information above applies here as well. After Effects also has an option called “Enable Multi-Frame Rendering” in Edit > Preferences > Memory & Performance. You can use Beauty Box with this setting on, but it will be slightly slower in the current version of AE (2022). We do expect Multi-Frame Rendering to improve in future versions of AE, so it’s worth testing the speed of it on vs off in your projects, especially in future versions of AE. Final Cut Pro: If FCP is performing slowly while using Beauty Box, turn off Background Rendering in the Preferences > Playback menu, and turn off Skimming either by clicking the Skimming button below the Viewer, clicking it in View > Skimming, or pressing S. Resolve: We recommend applying Beauty Box in either Edit or Color modes. It works in Fusion, but will render more slowly. In combination with the automated masking and skin tone analysis capabilities, the tips we listed above can help video editors speed up the post-production skin retouching process considerably! But if you’re looking for advanced tutorials, you can learn how to create manual masks to retouch specific skin areas, isolate and track moving subjects, and more at https://digitalanarchy.com/beautyVID/tutes.html .
Testing A.I. Transcript Accuracy (most recent test)
Periodically we do tests of various AI services to see if we should be using something on the backend of Transcriptive-A.I. We’re more interested in having the most accurate A.I. than we are with sticking with a particular service (or trying to develop our own). The different services have different costs, which is why Transcriptive Premium costs a bit more. Gives us more flexibility in deciding which service to use. This latest test will give you a good sense of how the different services compare, particularly in relation to Adobe’s transcription AI that’s built into Premiere. The Tests Short Analysis (i.e. TL;DR): For well recorded audio, all the A.I. services are excellent. There isn’t a lot of difference between the best and worst A.I… maybe one or two words per hundred words. There is a BIG drop off as audio quality gets worse and you can really see this with Adobe’s service and the regular Transcriptive-A.I. service. A 2% difference in accuracy is not a big deal. As you start getting up around 6-7% and higher, the additional time it takes to fix errors in the transcript starts to become really significant. Every additonal 1% in accuracy means 3.5 minutes less of clean up time (for a 30 minute clip). So small improvements in accuracy can make a big difference if you (or your Assistant Editor) needs to clean up a long transcript. So when you see an 8% difference between Adobe and Transcriptive Premium, realize it’s going to take you about 25-30 minutes longer to clean up a 30 minute Adobe transcript. Takeaway: For high quality audio, you can use any of the services… Adobe’s free service or the .04/min TS-AI service. For audio of medium to poor quality, you’ll save yourself a lot of time by using Transcriptive-Premium. (Getting Adobe transcripts into Transcriptive requires a couple hoops to jump through, Adobe didn’t make it as easy as they could’ve, but it’s not hard. Here’s how to import Adobe transcripts into Transcriptive) (For more info on how we test, see this blog post on testing AI accuracy) Long Analysis When we do these tests, we look at two graphs: How each A.I. performed for specific clips The accuracy curve for each A.I. which shows how it did from its Best result to Worst result. The important thing to realize when looking at the Accuracy Curves (#2 above) is that the corresponding points on each curve are usually different clips. The best clip for one A.I. may not have been the best clip for a different A.I. I find this Overall Accuracy Curve (OAC) to be more informative than the ‘clip-by-clip’ graph. A given A.I. may do particularly well or poorly on a single clip, but the OAC smooths the variation out and you get a better representation of overall performance. Take a look at the charts for this test (the audio files used are available at the bottom of this post): All of the A.I. services will fall off a cliff, accuracy-wise, as the audio quality degrades. Any result lower than about 90% accuracy is probably going to be better done by a human. Certainly anything below 80%. At 80% it will very likely take more time to clean up the transcript than to just do it manually from scratch. The two things I look for in the curve is where does it break below 95% and where does it break below 90%. And, of course, how that compares to the other curves. The longer the curve stays above those percentages, the more audio degradation a given A.I. can deal with. You’re probably thinking, well, that’s just six clips! True, but if you choose six clips with a good range of quality, from great to poor, then the curve will be roughly the same even if you had more clips. Here’s the full test with about 30 clips: While the curves look a little different (the regular TS A.I. looks better in this graph), mostly it follows the pattern of the six clip OAC. And the ‘cliffs’ become more apparent… Where a given level of audio causes AI performance to drop to a lower tier. Most of the AIs will stay at a certain accuracy for a while, then drop down, hold there for a bit, drop down again, etc. until the audio degrades so much that the AI basically fails. Here are the actual test results: TS A.I. Adobe Speechmatics TS Premium Interview 97.2% 97.2% 97.8% 100.0% Art 97.6% 97.2% 99.5% 97.6% NYU 91.1% 88.6% 95.1% 97.6% LSD 92.3% 96.9% 98.0% 97.4% Jung 89.1% 93.9% 96.1% 96.1% Zoom 85.5% 80.7% 89.8% 92.8% Remember: Every additonal 1% in accuracy means 3.5 minutes less of clean up time (for a 30 minute clip). So that’s the basics of testing different A.I.s! Here are the clips we used for the smaller test to give you an idea of what’s meant by ‘High Quality’ or ‘Poor Quality’. The more jargon, background noise, accents, soft speaking, etc there is in a clip, the harder it’ll be for the A.I. to produce good results. And you can hear that below. You’ll notice that all the clips are 1 to 1.5 minutes long. We’ve found that as long as the clip is representative of the whole clip it’s taken from, you don’t get any additional info from the whole clip. An hour long clip will product similar results to one minute, as long as that one minute has the same speakers, jargon, background noise, etc. Any questions or feedback, please leave a note in the Comments section! (or email us at cs@digitalanarchy.com)
Transcribing Multiple Audio Channels with Transcriptive for Premiere Pro
Setting Transcriptive to “Clip Mode” to transcribe your video and audio files in Premiere Pro is the best option when the goal is to use transcripts to find sound bites and assemble rough cuts throughout the editing process. Transcribing in “Clip Mode” means everything in your clip is converted into searchable text, the transcribed text is attached to the original clip instead of the sequence, and you can pull sound bites from the text anytime – for any sequence – without having to transcribe bits and pieces for each sequence. However, using “Clip Mode” has some limitations when your video or audio clips have multiple audio channels. When you transcribe a clip, Transcriptive exports that clip’s audio through Media Encoder. For clips with stereo or a single mono audio channel, this is no problem. But if you have multiple audio channels, Premiere only allows Transcriptive to export the top channel (channel 1), and, unfortunately, right-clicking a clip and opening the “Modify > Audio Channels” to re-assign the channels doesn’t help. If some of your recorded audio is on a different channel, it won’t be transcribed. And if channel 1 is empty, Transcriptive will return a blank transcript. Fortunately, there is a pretty easy workaround. Transcribing a sequence gives us a lot more control over what audio we’re exporting. When you submit a sequence to be transcribed, Transcriptive mixes down all of the unmuted audio channels. This means you can mute unwanted audio and transcribe everything else. If your sequence has channels you don’t want to be transcribed – scratch audio, music, etc – you can mute them before submitting the sequence to Transcriptive. You can also set in and out points in the sequence to control what area you’re transcribing (in and out points are another thing we aren’t able to read in Clip Mode, so only use them when transcribing a sequence). To transcribe a clip with multiple audio channels: Create a new sequence with that clip Mute any unwanted audio channels in the sequence, and set your in and out point Turn off Clip Mode and transcribe the sequence. Once transcribing is done, switch “Clip Mode” back on and select your clip in the project panel. The transcript will load attached to the original clip, and now you can delete the sequence. This is what your transcript will look like with “Clip Mode” on: In Transcriptive 3.0, you can Batch Transcribe sequences as well as clips. So while creating a sequence for each clip with multiple audio channels is an extra step, you can still transcribe those sequences all at once – select them in your Project panel in Premiere, click the top left menu in Transcriptive, and select Batch Project. Once transcribing is done, repeat step 4 above to attach each transcript to the clip. Here’s a Batch Transcription tutorial to watch for more info. We’re hoping future versions of Premiere will give us more control over what we can do in Clip Mode, and allow us to handle in/out points and multiple audio channels better. For now, the sequence workaround is the best way to get around these limitations. If you have any questions about Transcriptive Rough Cutter or want a two-week trial license, send us an email at cs@digitalanarchy.com