Speaker A
Few days ago, I was doing the final check on one of my videos. Then I noticed that my editor kept putting in these kind of disturbing images.
Dan Kieft walks through six methods for using AI in video editing, including trimming dead space, B-roll generation, multi-camera angles, motion graphics, VFX, and sound design with Premiere Pro, DaVi
Key Takeaways
- AI can automate time-consuming tasks like trimming dead space, freeing editors to focus on creative decisions.
- Tools like ChatGPT with MCP connectors (Higgsfield, DaVinci, Premiere Pro, After Effects) let creators run AI-assisted editing workflows directly on their computer.
- AI-generated B-roll and simulated multi-camera angles can be more tailored than generic stock footage, though generation is slow and costs credits.
- Human oversight remains necessary, as AI output must be monitored and reviewed for accuracy and quality.
What the video covers
- The video opens with the creator explaining why he is exploring AI editing after noticing his human editor inserted unflattering images, prompting him to test AI alternatives.
- The creator presents six methods for using AI to edit videos, with the goal of saving editing time so humans can focus more on creativity.
- Basic editing: AI is used to trim dead spaces and silences in raw footage, using a universal prompt that adds editor instructions as adjustment layers and markers.
- The workflow relies on tools such as ChatGPT (Codex desktop app recommended over cloud due to a 512 MB upload limit) and the Higgsfield MCP for AI video generation.
- B-roll generation: AI creates stock-style B-roll clips tailored to the video's content, which is presented as more engaging than generic stock footage.
- Multi-camera simulation: AI generates B-cam and CC-cam angles from a single A-roll, using a reference image of the studio space and the Higgsfield MCP.
- Editing software integration is covered for Premiere Pro, DaVinci Resolve (requires the paid version for the MCP), and After Effects, with the creator noting that any one of these can work.
- Motion graphics and VFX are demonstrated as easier to produce with AI, and the creator notes that AI can also help with sound design.
- The creator notes practical constraints: AI editing is slow, can take many minutes per trim, and consumes credits, so cost-efficient models such as Kling are suggested.
- Results are reviewed critically, with the creator noting that the AI-generated B-cam angles are convincing but that he does not want to use every angle, and that manual monitoring is still needed.
Chapters
- 00:00Why AI Editing: The Problem with the Editor
- 01:14Overview of Six AI Editing Methods
- 02:59Required Tools and Setup
- 06:05Basic Editing: Trimming Dead Space with AI
- 10:03Generating B-Roll with Higgsfield MCP
- 12:37Creating B-Cam and CC-Cam Angles
- 15:25Motion Graphics, VFX, and Sound Design
- 22:01Review, Limitations, and Costs
Full Transcript — Download SRT & Markdown
Speaker A
mogging my appearance, which made me wonder, do I even need this guy now that we got GPT Astra? So I did some research and I found six methods of how you can start using AI to edit your videos. In
Speaker A
So I texted him like, "My hairline isn't that bad."
Speaker A
less time, a human can spend more time on creativity and edit their videos even better. And that's why in this video, I'll be breaking down all of the different techniques that go into AI video editing. I will show you how you
Speaker A
But he just sent me more images mogging my appearance, which made me wonder, do I even need this guy now that we got GPT Astra?
Speaker A
even cover a bit of VFX. Now, last but not least, AI can do a lot when it comes to sound design. So, make sure you watch this entire video to the end and let's get started.
Speaker A
So I did some research and I found six methods of how you can start using AI to edit your videos.
Speaker A
is Hicksfield MCP. This is used for all of our generations. They were also the sponsor of this video, but even if they didn't, this is the best MCP out there and they also have an API now, which we
Speaker A
In fact, everything you've just seen was all made using AI.
Speaker A
Dainci MCP. Don't worry if you're editing through Premiere Pro, then you just need Premiere Pro. Same with After Effects. If you want to do things through After Effects, you just need to have that app on your computer. If
Speaker A
Okay, before we dive into this, I just want to get one thing clear.
Speaker A
Okay, let's start with basic editing. We're going to be trimming dead spaces. For this, you want to download the CHP desktop app or the codeex app. The reason why is because the cloud version, if you're using this cloud, you have a
Speaker A
The goal is not to replace my editor.
Speaker A
that and work directly from that. In the cloud, as you can see, you're limited to 512 megabits. And I don't know about you guys, but my camera files are way bigger than that. So, make sure you switch to
Speaker A
This is just a joke intro.
Speaker A
need to start prompting it. And I have a very detailed prompt that anyone can use. It's a universal prompt. I will explain to you right now. So, you upload your video and then you're going to add in this exact prompt. And this is a
Speaker A
The idea is if editing takes less time, a human can spend more time on creativity and edit their videos even better.
Speaker A
that, it will add in editor instructions as adjustment layers. Then it will figure out potential spaces in your video where you can have or add in Bcam or even CC cam. And it uses that with the markers. And lastly, it will give
Speaker A
And that's why in this video, I'll be breaking down all of the different techniques that go into AI video editing.
Speaker A
Da Vinci. I will show you an example later. you might get some things that you need to allow. So, I'm just going to do always allow for now. This might cost you more credits. Keep in mind this process is still quite slow. You can
Speaker A
I will show you how you can easily trim and cut down your video.
Speaker A
while you don't want to do the trimming yourself because you still got to sometimes monitor if it's doing everything correctly. So, it's literally taking over your PC and it's doing everything for you. As you can see, we now have a new version where it's
Speaker A
Then I will show you how you can make multiple different camera angles just from your A-roll.
Speaker A
actually stopped this because I already had this version to begin with, and that's the one I want to show you because here it basically has done the same thing. We're just one step ahead, which I'm going to explain to you in a
Speaker A
We will go over cool looking motion graphics that are now easier than ever to create, and I will even cover a bit of VFX.
Speaker A
It says intro starts here. Then other notes that I have like for example here, I say something about I want to add in some V effects here. And then like it mentions it. Trying to do this. I'm not
Speaker A
Now, last but not least, AI can do a lot when it comes to sound design.
Speaker A
These are just instructions for me and my team to go over later. So we can manually trim these out or you can even ask JPT to do that for you. The other thing that it has done is it has marked
Speaker A
So, make sure you watch this entire video to the end, and let's get started.
Speaker A
Let me explain to you what I mean by Bcam and CC cam. So this what you're watching right now is the A cam. Then this is a B cam. It's a secondary side angle. I don't have a camera there. Like
Speaker A
There are five things that you're going to need if you want to follow along with this AI video editing tutorial.
Speaker A
Storage these days is expensive. But we can use AI. So this clip is entirely generated with AI. And I literally asked Astra to do that for me. Now the other thing that we can do is we can also
Speaker A
The first one is the obvious one, which is ChatGPT.
Speaker A
your surrounding looks like. So, I gave it this image. It's with all of the studio lights turned off. It's a bit of a behind the scenes. It's It's not the most clean looking setup. Like, what the hell's happening here? I'm not going to
Speaker A
We're using Astra as the brain for all of our projects.
Speaker A
segments. So, I'm just going to copy this prompt. We're going to go back to Chachi. And now we're going to enter it in there. And now you can just ask it and it will start up Premiere Pro again
Speaker A
The second one is Higgsfield MCP.
Speaker A
that extra reference of your room of the space of the side angle. And then you're going to say use the Hickfield MCP. Make sure you have the Hickfield MCP connected. Basically, what you can ask Chetchip to do, I will show you right
Speaker A
This is used for all of our generations.
Speaker A
have a subscription, get a subscription first. If you want to support my channel, use my link. Basically, this is the task that you need to do. Okay, once you have done that, you can hit send.
Speaker A
They were also the sponsor of this video, but even if they didn't, this is the best MCP out there, and they also have an API now, which we are using for all of the generations that are about to come that are being done through GPT Astra together with Higgsfield.
Speaker A
generating these videos using Cense 2.5. And again, like that's a lengthy process regardless. Now, you can see it working here right now. So, you can see it use these Hicksfield MCPS. And if you then go over to Hickfield itself and you go
Speaker A
The third thing that you're going to need, if you're editing through DaVinci Resolve, you're going to need the DaVinci MCP.
Speaker A
here it's for example waiting on the video to confirm. But this is the B-roll that it made for that video. Then I noticed that my editor kept putting in these kind of disturbing images. Keep in mind this is entirely like AI generated.
Speaker A
Don't worry, if you're editing through Premiere Pro, then you just need Premiere Pro.
Speaker A
It's done quite an amazing job. Like we can even see like you don't see it but I see there a shadow on my wall like this shadow. Then if we look at the C cam even this one it's time a human can
Speaker A
Same with After Effects.
Speaker A
have that but overall this quite good the only thing is this is if you want to have CC cam I I don't think this this angle is flattering of me so I just want to use the Bcam and the A cam you can
Speaker A
If you want to do things through After Effects, you just need to have that app on your computer.
Speaker A
Da Vinci editor or if you are trying to get into editing yourself, you might actually want to try out Dainci. Keep in mind, you need to use the paid version for this as the free version doesn't have the MCP to my knowledge. But this
Speaker A
If you're missing one of the three editing softwares, as long as you have one of them, this can still work.
Speaker A
talking on the screen. But the next thing that I'm going to show you is B-rolls. B-rolls are a great way to spice up your videos. The problem, however, is that generic stock footage B-roll looks boring and might not fit
Speaker A
Okay, let's start with basic editing.
Speaker A
minutes. You can save credits by using costefficient models like Cling and they still do the job quite well. Cool. So, how do you generate the B-rolls like I've just shown you? The first thing you're going to need is you need to have
Speaker A
We're going to be trimming dead spaces.
Speaker A
bit more complex, then you might want to use a character sheet like this one or this one. This one is like 100% accurate. Like I literally scan my body and this is actually how muscled I am.
Speaker A
For this, you want to download the ChatGPT desktop app or the Codex app.
Speaker A
on the screen. If you want to see all of the prompts that I'm using in this video, then make sure you're joining the free school community here. For every video that I make, I'm uploading all of the assets, all of the prompts, sharing
Speaker A
The reason why is because the cloud version, if you're using the cloud, you have a limit on the file size that you can attach.
Speaker A
What I did is I uploaded the three images of me. Then I used this skill MD file that explains how to make a character sheet. And then I just gave it a simple prompt like this. Using the skill and my three reference images, can
Speaker A
If you're using this on your PC, you can click to on your computer, and now you can upload really big files that are already on your computer, and it can use them directly from that and work directly from that.
Speaker A
sheet that would look something like this. you now are ready to generate your video. But first, you need to have a video that needs B-roll. So, I recorded this segment for that.
Speaker A
In the cloud, as you can see, you're limited to 512 megabytes.
Speaker A
don't know what to generate next, the best thing that you could do is you can either go for a walk or take a shower because sometimes the best ideas come when you stop trying so hard. Okay. So, at the part of go for a walk, I want to
Speaker A
And I don't know about you guys, but my camera files are way bigger than that.
Speaker A
basically asking it to generate me with this character sheet a CD 2.5 video of me walking in the park. And then I describe what my shot looks like. I do the same for the shower part. Then literally what it does is it uses
Speaker A
So, make sure you switch to on your computer.
Speaker A
could do is you can either go for a walk or take a shower because sometimes the best ideas come when you stop trying so hard. Okay, let's go a little bit more advanced. Let's talk about motion graphics. Here's an example of the
Speaker A
Then you drop in the video that you want to edit.
Speaker A
Effects. All of that on autopilot. If you want to learn how to use GPT as then check out the full tutorial that is in my free school community linked down below. Here's the entire timeline that AI helped me make for all of these. And
Speaker A
And here you can select GPT Astra.
Speaker A
own skill together with AI. And that's why I'm saying like editors are not replaced. Like me and my editor actually collab on this. So we're trying to figure out what can be done and what cannot be done with AI. And we have used
Speaker A
I'm using medium most of the time because it's already expensive enough.
Speaker A
did is I uploaded references of what my community looks like because I would love to have some cool looking motion graphics of that community. Here's the banner of that community. Still need to update this. Then I also added in some
Speaker A
You could go high, but only if you're rich.
Speaker A
graphics and it just went to work. Like it just used After Effects and it made all of these things for me and after going a bit of back and forth, it finished the After Effects motion graphic for me. It even gave me the
Speaker A
Then we need to start prompting it.
Speaker A
editor to tweak little things. The next one is more of an advanced workflow, and this is quite hard to explain because there were so many different prompts that went into this. But I'll try my best to give you a summary. First, we're
Speaker A
And I have a very detailed prompt that anyone can use.
Speaker A
this is I added in a bunch of different references of styles that I liked and then again I just started talking using Whisper Flow about the kind of animations and things that I want to see. So then it started to create these
Speaker A
It's a universal prompt.
Speaker A
of what it wanted to use. And then I manually used these prompts inside of Hicksfield because I didn't trust Astra there and didn't want to waste too many credits. Keep in mind if you're doing this and you have the approve for me or
Speaker A
I will explain it to you right now.
Speaker A
I always want to approve because you will burn through tokens. so quickly using this method. So then I got like all of these different prompts. I manually created them inside of Hicksfield and then I tweaked like all of the different settings. So this is me
Speaker A
So, you upload your video, and then you're going to add in this exact prompt.
Speaker A
into my timeline and I added like a small little things like this white transition right here. But all of this is done handinhand with Astra. Okay, so there's one motion graphic which is this pixel version of me and I'm going to
Speaker A
And this is a super long prompt.
Speaker A
it to create a pixel version of me. So it made like these three different versions using the hixel MCP. Then I basically asked it if it can now give me a cedance 2.5 prompt and I wanted to do
Speaker A
So, I'm going to break it down for you.
Speaker A
now if you upload the part where you want to have that in your video together with your asset and then you ask it to replace it and we get this cool looking result where I walk into the frame and
Speaker A
Basically, what this prompt does is it first instructs ChatGPT to trim the raw footage.
Speaker A
of my favorite things to do with AI is making VFX. So I'm now going to show you how you can do an effect like this. So you want to learn how to do VFX? Well, let me actually let me show you. Wait, what the hell is
Speaker A
Then, it will ask it to transcribe that footage and trim out the dead spaces.
Speaker A
Oopsie. So there are a couple steps that go into making a video like that. First of all, it starts with your recording. Now this was my raw recording and I already envisioned what I wanted to do. So I
Speaker A
After that, it will add in editor instructions as adjustment layers.
Speaker A
Let me actually move back a little bit. So now we're going to do this.
Speaker A
Then it will figure out potential spaces in your video where you can have or add in B-cam or even CC cam.
Speaker A
you're using Premiere or if you're using Da Vinci and your timeline looks like this where you can just see like normal time of how many seconds it's into the video, change this to the view. I do that with command and then clicking on
Speaker A
And it uses that with the markers.
Speaker A
arrives in my hand. So, I'm just going to leave a mark right here at 279. So, I'm just going to add in a mark. And then I'm going to do the same when I'm clapping into my hands. So, right here,
Speaker A
And lastly, it will give you the finished version in Premiere Pro or DaVinci Resolve.
Speaker A
through them step by step. So, the first thing we need is a creature. My first version of the creature was this. I made the mistake here where this didn't really look photorealistic until after a few generations, I finally landed on
Speaker A
I'm using Premiere Pro right here because we are using that for most of the editing that we do on this channel.
Speaker A
this. Again, the prompt is simple. I'm just describing like what I want to make, what the background looks like, the lighting, the style, and I'm using Cream 5.0 Pro for this. So now we already have two of our things. Then the
Speaker A
And this is what my team is also using.
Speaker A
that. So we now have created the three of our references. Then what you can do is you can take all three of these references, put them inside of Chet or CL. Then you add in your video. And then
Speaker A
But this also works with DaVinci.
Speaker A
then it will give you a very detailed prompt of everything that's happening precisely on the time stamp. like it would come up with that timestamp and it will tell you exactly where that thing needs to go and it will reference these
Speaker A
I will show you an example later.
Speaker A
After doing that, you can look at a side by side and then you have results like this. So, you want to learn how to do VFX? Well, let me actually let me show you. Wait, what the hell is
Speaker A
You might get some things that you need to allow.
Speaker A
Oopsie. So that is exactly how you can generate these V effects. If I went too fast, please let me know. I can make a separate video about this if you want to.
Speaker A
So, I'm just going to do always allow for now.
Speaker A
You can do this both through Chip itself and also through Dainci. Let's first start by doing this in Astra 6.
Speaker A
This might cost you more credits.
Speaker A
prompt where I'm saying that the uploaded MP4 file is my SLOG 3 footage. And the other file is the official Sony recording 709 conversion L. I want to use this to color grade my MP4 by using the conversion L. And please for the
Speaker A
Keep in mind this process is still quite slow.
Speaker A
given me this folder and if we look at these side by side then you can see that we now have a color graded video. This is the super simple way. Again, sometimes this might take a while. In this case, you don't want it. I
Speaker A
You can literally see it take over your PC and clicking on things for you.
Speaker A
mind like it can still be quite slow. The other thing you can do is you can use the Dainci MCP. If you have the premium version of Dainci, then you can ask it to color grade directly in Dainci. It is much quicker and it will
Speaker A
Still, some of these things annoyed me, as it took like 14 minutes to do some of these trims.
Speaker A
design. Sound design is what sells your videos. If you're doing sound design manually, you can now use AI to do sound design for you. There are various different ways. And again, this also might deserve a video on its own because
Speaker A
So, I would only do this while you're working on something else and while you don't want to do the trimming yourself, because you still got to sometimes monitor if it's doing everything correctly.
Speaker A
I personally don't really like the sound that Cens made for this one. So what we can do is we can upload this into Astra and then we can just give it a super simple prompt. I want you to craft a CDE
Speaker A
So, it's literally taking over your PC and doing everything for you.
Speaker A
for any type of video. In this case I used this animation but you can also literally do this for a intro video.
Speaker A
As you can see, we now have a new version where it's marking potential B-roll.
Speaker A
not happy with because I always want to check the prompts that it's going to use. So, as you can see, it wrote a super detailed prompt of the audio. And now you want to go through this and see
Speaker A
It is adding some adjustment layers.
Speaker A
trust me, I've been there. If you have any changes, change them. Otherwise, copy this. Go into Hickfield. Upload your original track in CNS 2.5. Then paste in the prompt right here. Make sure you add in video one to refer to
Speaker A
It is doing everything for me.
Speaker A
like it sounds a bit better, but the video quality has noticeably gotten worse. So, you just want to download that video. Then, you want to separate those audio tracks and then you want to replace that with the original video.
Speaker A
Like, it's now even rendering.
Speaker A
gave you and make it match." Then Astra will do the work for you and you will have your original highquality clip with the new audio that you just generated.
Speaker A
Now, as you can see, ChatGPT has ran all of these commands using my Premiere Pro, and it made this version.
Speaker A
In particularly, we're using Astra 6 as the brains of this. If you want to try this out yourself, I would recommend using Hixoot for that. I will leave the link in the description down below. And if you have any questions on this video,
Speaker A
I actually stopped this because I already had this version to begin with, and that's the one I want to show you, because here it has basically done the same thing.
Topics:AI video editingChatGPTHiggsfield MCPPremiere ProDaVinci ResolveAfter EffectsB-roll generationAI trimmingmulti-camera editingVFX
![[YBA] frosti — Transcript](https://i.ytimg.com/vi/KAH0o3xSL3w/maxresdefault.jpg)
