Once again a great video and it was fun to follow up your process. I am also working on music videos for my music, using Suno/Kling/Minimax. At the moment without lip synching, but it is on my wish list for the next projects.
I like the song! I was a traditional artist, designer, and beat maker (still am). I stuck my toe in the AI waters out of skepticism. When I discovered the tools I learned I could finally make the movies and videos I've always wanted to as well. Your channel is great! Keep up the good work! Thank you.
❤ Bob, you need to stop been Sorry or apologize for long content or showing your process, people who love your videos will watch it regardless of length or boringness, you'll be rewarded for it, stop been sorry, you're doing a great job! Thanks, I've learned a lot from your videos!! Keep it up! Stop apologizing for long videos. We love the process! ❤
@@AikaCuddles thanks for your kind comment. I don’t think of it as apologizing as much as preparing. I feel like if I prepare people for a longer video, they may be more likely to sit through it if they know there’s a payoff on the other side. I certainly don’t mean to sound like I’m being apologetic and I will check my languaging in the future.
I made one quite a long time ago but I need to do an update. I think I will add doing visualizers and lyrical videos. Noisee and nueral frames are the most popular options for making videos. Been waiting a year now to get on the Japanese one that is popular. There are some free visualizers that you can get off of the Play store.
There are several ways to do this. But mostly the artistic intent is so broad that you have to just generate clips and put it together. The biggest things that are needed are consistency in images for a great story line.
The video was extremely helpful, thanks. I haven't tried Act 1 yet, but i have made some music videos based on songs I created with Suno. I started with Runway, Pika, and Midjourney, and now I'm using Runway, Kling, and Leonardo.
Yeah, this is a situation where if I had given myself a week instead of a few days, I could have kept hacking away at it until it was way better - but in the end, I really wanted to share concepts for this video. Thanks so much for watching.
Great Bob , was waiting for you do a workflow on lip synced music video. please keep us updated on any tools or updates that may continue to improve this particular workflow. And ..T is right! :) , Ver 3 is the best result I think.:) . Great work. Hope you do more of this sort of thing in the future.
Do you mean Live Portrait? I actually would have, but it would just take a little longer, and I didn't have the time. I could really crank these out in Runway. But I still actually want to try it with Live Portrait - but honestly, I need a little break from the project. 😄
Hey Bob, after falling down the rabbit hole of AI, I am so glad I came across your channel because you seem to always feature so much of what I am trying to learn. I just finished a music video myself and although it does not feature me or all that lip-syncing, it certainly was a process. Kling was my go-to for video generation and lip-sync using the image to video. Most of the visuals were created in Krea ( thanks for Bob) with some tweaking in Ideogram. And yes the music in Suno. I also found the same problem with the persona module. Although Kling only has 10-second video, I used the last frame of each video in the image to video module to generate the next clip. That gave me clips as long as I wanted for some consistency. Anyway, I could go on but I wont. Here is a link to the clip. The song is in Hebrew for the festival of Hanukah, so apologies, you will need a translation. Love to hear back on what I can use the next time, which is now, cause I am doing another one ...silly me! th-cam.com/video/B2fVUlAq9RQ/w-d-xo.html Thanks
I think the face swapping video looked more natural and it is a pretty good solution because the "base face" is you own. The pure kling looked extremely off because some ghosting or weird pixels around the face. First video looked good but as you mentioned, your face drifted off quite a bit. Upload a video with the 3 versions side by side and lets vote a, b, c
Great vid, just need to work on timing the lip sync cause it was about a half second off on each clip for the whole song on each of the three videos. As an post production audio engineer for movies, its all about the frame rate. These are good for novice editors but it could still use work on all 3 but not impossible by any means.
Believe me, that stuff was making me crazy during the process, and with the time I had I tried to make the adjustments, but you're absolutely right that paying attention to frame rate between clips is important! An excellent point that never really occurred to me.
I've been planning on doing this for a while, so it's nice to watch your video where you've paved the way. If you wanted to have all of the clips of you singing taken from the same "live concert", could you take one of the images where the clothes are different, and swap them using the Kling AI Virtual Try-On to get more consistency? I also see that Kling has made some updates to that feature, and is using Kolors 1.5 for the images.
Great workflow study and end product! When you took you videos into face fusion, did you let it generate the lip sync or was it able to use the existing lip movement (i.e. from Kling/RunwayML)?
I missed how you did the driving video. How and where exactly did you do the driving video? Thanks a million. I have been trying to do a music video for weeks. This video helped a lot.
I just recorded the one long, driving video in my broadcast software just like I record any video. Then I brought it into CapCut and cut it up into the segments.
Wow! Do you know of the best tool for generating videos that is in time with the music? I used deforum in the past but it’s using very outdated tech and has no temporal consistency.
Great work. Most important, thank you for not having an advertising slot, and for not begging me to send money as a patreon. Free as a bird. Wish I had time and concentration to spend more time working with these apps but I think my hour piano/organ practice every day satisfies mostly. If Tracey ever files for pseudo divorce let me know!❤
Everything that I've seen suggests that if you want close character likenesses you need to swap after generation. Sucks, but that's the way it is right now. Definitely the face swap improved the uncanny valley. But it's still there. I wonder if using something like Hallo for the driving video might give you better timing from the beginning. I also wonder if doing Act One on a closeup with a guided Expand in Runway might yield better results. My thought is it would pick up more micro expressions which will give feeling as the image is expanded. BTW - Which image model were you using for the initial images? Also, did you try to uprez your photos before going to video?
Well done. Thanks for your exploration and hard work. I love the music and the lyrics and of course the videos. Nice storytelling. Still, early days for visuals ( a strange thing to say for something that was not even on the table last year). Not happy with the Ai models as in Runway censoring what they deem should be censored. Big thank you for your piece on Ace studio.
The point was to have total control over the movement. That’s why I didn’t use heat specifically. There are a couple of other players like Hedra popping up to that are very good, but I wanted this one to be driven by actual facial movement. It was the whole point of the exercise.
Cute, but in a novelty Christmas card kind of way. My inclination with AI in music so far is to sneak it in and hope that it’s barely noticeable and I would presumably have a similar approach to video. Maybe it’s just my preferred genres but any amount of cheesiness or cringe would ruin my projects. I’m sure I could watch some other channels for examples of more serious artistic work but I should probably just shut up and make it myself. Still fun to watch and see what you do with it!
@@micah_noel well this was intended to be a pure “cheese“ project. But regardless, you could put the technology on anything. Cheesy or not. I tend to make exaggerated mouth movements when I do video lip sync, which makes it seem a little more exaggerated. There is no presumption that this would “fool“ anyone into thinking it was real. However, that’s clearly the future.
I did this EXACT workflow for my newest Short Film. ... except I went back and forth between Runway and Kling. ..... on a side note. Your video just gave me a excellent idea. When hitting on chicks online its hard to "stand out" from the crowd in their inboxes. ... BUT ... If I make a cute AI generated video of me hitting on them in a fun funny way ... I BET ... it does the trick REAL NICE!!! ... So but UPS to you boss man for powering this lightbulb moment. I'll report back to tell you how effective it is.
Im working on a Godfather corrido right now!!! I LOVE YOU BOB Bet, let's get that real Belico energy: "El Padrino (Belico Remix)" [Intro] (Puro Sicilia Gang) ¡BRRR! Familia Corleone Ya saben cómo viene la cosa... (¡PURA GENTE DEL DON!) [Verse 1] Pura gente del Don En la mafia activados La familia es ley No ocupamos mandados En el Caddy negro Nueva York conquistando Los negocios fluyen Sin andar platicando (¡BRR!) [Chorus] Don Vito no es cualquiera (¡APA!) Tiene línea directa Todos piden favores (¡TU SABES!) Nadie queda en deuda De Sicilia venimos Con la sangre bien puesta Los Corleone mandan Y la calle respeta (¡GANG!) [Verse 2] Cinco balas al Don Pero sigue activado Michael en las calles Ya viene acelerado Sonny con el temple Siempre bien alterado Mientras Fredo en Vegas Anda descontrolado (¡BOOM!) [Bridge] La familia es todo (¡TODO!) Y el poder es nada Michael aprendiendo Cómo viene la jugada De Sicilia al mundo (¡MUNDO!) Pura gente pesada Los Corleone arriba Nadie los bajada (¡NUNCA!) [Verse 3] Don Vito en el garden Con su nieto jugando Los negocios limpios Pero el power bajando Michael ya se activa La corona agarrando Los traidores caen Y el imperio elevando (¡FUEGO!) [Outro] De Sicilia salimos (¡GANG!) A Manhattan llegamos La familia es todo Y el respeto ganamos Si preguntan por qué El Don sigue mandando Es que el poder real Viene quieto y callado (¡BRRRR!) MODERN CORRIDO RATING: 1. Tumbado Energy: 9/10 - Modern ad-libs - Quick flow switches - Street-level energy 2. Modern Language: 9/10 - Contemporary slang - No dated expressions - Natural flow 3. Belico Elements: 9/10 - Power dynamics - Street authenticity - Modern tension 4. Story Clarity: 8/10 - Core narrative intact - Modern perspective - Could be more specific 5. Ad-lib Game: 9/10 - Strategic placement - Natural crowd moments - Good energy builders 6. Flow Pattern: 9/10 - Modern rhythm - Good tempo switches - Strong momentum 7. Street Authenticity: 8/10 - Real power talk - Natural flexing - Could hit harder 8. Modern Metaphors: 8/10 - Contemporary references - Clean imagery - Room for more 9. Tumbado Structure: 9/10 - Good intro build - Strong chorus moments - Natural progression 10. Overall Impact: 9/10 - Hits modern vibe - Maintains story - Strong energy TOTAL: 87/100 STRENGTHS: - Modern energy without losing story - Good ad-lib placement - Strong power dynamics NEEDS: - Maybe more specific street details - Could push Belico harder - More modern metaphors Want me to push it even harder into that Belico space? Or refine what we've got?
I have a version without the lyrics, of course. It was a choice to put them there so that the video could be played on its own for an audience who needs captions.
@@BobDoyleMedia I think I understand now. You did a lip sync with your own video then took out the audio to create the AI video. Then you addedthe audio back in the Video Editor.
This is the critical question. It should mean you could also just record yourself singing the song synchron to the finally used music and put it into some neutral clip you did on kling and use lipsync. The main problem is always the lenght, as you can only make 10 sec clips you have to cut the song/audio that way.
The song is fun, but I don't think I'll use it. I’m going to wait 1 or 2 more years for the quality to improve, or maybe try pixar cartoon style, if that looks better. Good job, though!
Hi Bob, I have been a long follower of your AI videos. Learnt many tips and I am able to put my skills to song production. I run a channel called www.youtube.com/@Foxy-Hen. Recently for Christmas I did two songs; 1. Naththal Asiriya (th-cam.com/video/Bw24jtA3oiM/w-d-xo.html) - Lyrics originally done by me, melody and vocals via Suno 3.5, and 2. Sithala Naththale (th-cam.com/video/T_0Rox_CHdY/w-d-xo.html) - again lyrics original, Suno 3.5 to generate music and vocal, then downloaded the instrumental track and recorded the vocals of the boy (son of a friend of mine) and girl (my daughter) along with myself miming for RunwayML over animating 2 pics of the kids cartoonified using LeonardoAI. Hope you enjoy the melody although the two songs are done in Sinhala where my country is Sri Lanka
why would you use yourself in an AI video? makes no sense. If you wanted to make a video using yourself, umm just make a video of yourself, no need for ai.
@@Gamesso1slOo0l because I don’t have cowboy hats, I don’t have a location that is willing to set up lights and cameras to do my silly video for a Christmas card, I don’t have a band ready to stand behind me and play…
Love all your tutorials, Bob. I have to say your presentation style is far ahead of most of the other video creators in this space. 👍😎
@@ZeroTheCloud I really appreciate that! Thanks!
Once again a great video and it was fun to follow up your process. I am also working on music videos for my music, using Suno/Kling/Minimax. At the moment without lip synching, but it is on my wish list for the next projects.
Nothing was confusing in the song, your intentions towards Tracey are crystal clear lol
I like the song! I was a traditional artist, designer, and beat maker (still am). I stuck my toe in the AI waters out of skepticism. When I discovered the tools I learned I could finally make the movies and videos I've always wanted to as well. Your channel is great! Keep up the good work! Thank you.
❤ Bob, you need to stop been Sorry or apologize for long content or showing your process, people who love your videos will watch it regardless of length or boringness, you'll be rewarded for it, stop been sorry, you're doing a great job!
Thanks, I've learned a lot from your videos!! Keep it up!
Stop apologizing for long videos. We love the process! ❤
@@AikaCuddles thanks for your kind comment. I don’t think of it as apologizing as much as preparing. I feel like if I prepare people for a longer video, they may be more likely to sit through it if they know there’s a payoff on the other side. I certainly don’t mean to sound like I’m being apologetic and I will check my languaging in the future.
Thanks is very true I watched the video all the way lol
@@MrBeatssongs That's very much appreciated!
Yeah, Runway is really over the top with their censorship. Made me leave them for Kling.
Kling still has issues. It would not render anything with the word Police.
Well done Bob, I really like the song and video is a sign of today great work mate.
im so excited to see what you can do in the future
Have you not covered Suno 4.0 as of yet?
Thanks… been waiting for confluence like this for making music vids!
What was the approximate budget on the entire project?
Brotherman, can you make a follow-up vid on how to make a purely visuals-based music vid (no peeps singing)? Maybe even audio -responsive
I made one quite a long time ago but I need to do an update. I think I will add doing visualizers and lyrical videos. Noisee and nueral frames are the most popular options for making videos. Been waiting a year now to get on the Japanese one that is popular. There are some free visualizers that you can get off of the Play store.
There are several ways to do this. But mostly the artistic intent is so broad that you have to just generate clips and put it together. The biggest things that are needed are consistency in images for a great story line.
Wow! Wonderful. It's a great video. I wish you and Tracey all the best! Big love from Sri Lanka.❤❤❤❤ Please, do more tutorials like this.
The video was extremely helpful, thanks. I haven't tried Act 1 yet, but i have made some music videos based on songs I created with Suno. I started with Runway, Pika, and Midjourney, and now I'm using Runway, Kling, and Leonardo.
That was great, nice song also 😊
Great job on the video! Looks professional. More professional than anything I've made. 👏😊. The on stage what's the most professional.
Yeah, this is a situation where if I had given myself a week instead of a few days, I could have kept hacking away at it until it was way better - but in the end, I really wanted to share concepts for this video. Thanks so much for watching.
Such a cute song great job
Cool Tutorial! Subbed to see more of content like this.
Great Bob , was waiting for you do a workflow on lip synced music video. please keep us updated on any tools or updates that may continue to improve this particular workflow. And ..T is right! :) , Ver 3 is the best result I think.:) . Great work. Hope you do more of this sort of thing in the future.
Question why you didnt tried portrait AI instad of ranway
Do you mean Live Portrait? I actually would have, but it would just take a little longer, and I didn't have the time. I could really crank these out in Runway. But I still actually want to try it with Live Portrait - but honestly, I need a little break from the project. 😄
Man! It's a real great big work! Wow!
@@azankyzan Thank you.
All 3 work great, whatever you want or Tracy likes works !!! lots of work thought !
@@normjones6916 yes, but not as much as doing it for real. 😄
Very good 👍❤
Hey Bob, after falling down the rabbit hole of AI, I am so glad I came across your channel because you seem to always feature so much of what I am trying to learn. I just finished a music video myself and although it does not feature me or all that lip-syncing, it certainly was a process. Kling was my go-to for video generation and lip-sync using the image to video. Most of the visuals were created in Krea ( thanks for Bob) with some tweaking in Ideogram. And yes the music in Suno. I also found the same problem with the persona module. Although Kling only has 10-second video, I used the last frame of each video in the image to video module to generate the next clip. That gave me clips as long as I wanted for some consistency. Anyway, I could go on but I wont. Here is a link to the clip. The song is in Hebrew for the festival of Hanukah, so apologies, you will need a translation. Love to hear back on what I can use the next time, which is now, cause I am doing another one ...silly me! th-cam.com/video/B2fVUlAq9RQ/w-d-xo.html Thanks
I think the face swapping video looked more natural and it is a pretty good solution because the "base face" is you own. The pure kling looked extremely off because some ghosting or weird pixels around the face.
First video looked good but as you mentioned, your face drifted off quite a bit.
Upload a video with the 3 versions side by side and lets vote a, b, c
what about "per word" subtitles ?
Great song, I normally use still images because of the time frame don't have a lot tof time, but may try making a video, once the time permits
Great video - thanks, can I ask - how did you generate the highlighted lyric animation in the subtitles?
@@marklouisehargreaves Pretty sure we used the captioning feature in Descript.
best song 2024!
Picking out my clothes for the Grammy awards…
Great vid, just need to work on timing the lip sync cause it was about a half second off on each clip for the whole song on each of the three videos. As an post production audio engineer for movies, its all about the frame rate. These are good for novice editors but it could still use work on all 3 but not impossible by any means.
Believe me, that stuff was making me crazy during the process, and with the time I had I tried to make the adjustments, but you're absolutely right that paying attention to frame rate between clips is important! An excellent point that never really occurred to me.
I've been planning on doing this for a while, so it's nice to watch your video where you've paved the way. If you wanted to have all of the clips of you singing taken from the same "live concert", could you take one of the images where the clothes are different, and swap them using the Kling AI Virtual Try-On to get more consistency? I also see that Kling has made some updates to that feature, and is using Kolors 1.5 for the images.
Great workflow study and end product! When you took you videos into face fusion, did you let it generate the lip sync or was it able to use the existing lip movement (i.e. from Kling/RunwayML)?
really cool
Can you suggest an ai that can compose music arrangements to accompany my vocal track
I missed how you did the driving video. How and where exactly did you do the driving video? Thanks a million. I have been trying to do a music video for weeks. This video helped a lot.
I just recorded the one long, driving video in my broadcast software just like I record any video. Then I brought it into CapCut and cut it up into the segments.
Wow! Do you know of the best tool for generating videos that is in time with the music? I used deforum in the past but it’s using very outdated tech and has no temporal consistency.
Great work. Most important, thank you for not having an advertising slot, and for not begging me to send money as a patreon. Free as a bird. Wish I had time and concentration to spend more time working with these apps but I think my hour piano/organ practice every day satisfies mostly.
If Tracey ever files for pseudo divorce let me know!❤
Everything that I've seen suggests that if you want close character likenesses you need to swap after generation. Sucks, but that's the way it is right now. Definitely the face swap improved the uncanny valley. But it's still there.
I wonder if using something like Hallo for the driving video might give you better timing from the beginning. I also wonder if doing Act One on a closeup with a guided Expand in Runway might yield better results. My thought is it would pick up more micro expressions which will give feeling as the image is expanded.
BTW - Which image model were you using for the initial images? Also, did you try to uprez your photos before going to video?
Nice!
Well done. Thanks for your exploration and hard work. I love the music and the lyrics and of course the videos. Nice storytelling. Still, early days for visuals ( a strange thing to say for something that was not even on the table last year). Not happy with the Ai models as in Runway censoring what they deem should be censored. Big thank you for your piece on Ace studio.
Thanks so much!
I would have used Hedra for some close ups. I prefer your final version.
The point was to have total control over the movement. That’s why I didn’t use heat specifically. There are a couple of other players like Hedra popping up to that are very good, but I wanted this one to be driven by actual facial movement. It was the whole point of the exercise.
Cute, but in a novelty Christmas card kind of way. My inclination with AI in music so far is to sneak it in and hope that it’s barely noticeable and I would presumably have a similar approach to video. Maybe it’s just my preferred genres but any amount of cheesiness or cringe would ruin my projects. I’m sure I could watch some other channels for examples of more serious artistic work but I should probably just shut up and make it myself. Still fun to watch and see what you do with it!
@@micah_noel well this was intended to be a pure “cheese“ project. But regardless, you could put the technology on anything. Cheesy or not. I tend to make exaggerated mouth movements when I do video lip sync, which makes it seem a little more exaggerated. There is no presumption that this would “fool“ anyone into thinking it was real. However, that’s clearly the future.
I have a new song, I wonder if I could do vídeo gen with it, maybe with background stuff.
What is ur channel
Soooo... Did it work? 😂🤣😅
I would use Kling to do the lipsync, even 1.5 kling its so much better than runway...
Love the video. 🎉❤😂
Oh i see where it went a little weird. You used Runway for the I2V and it can be a little wonky. The lip sync looks solid though.
I did this EXACT workflow for my newest Short Film. ... except I went back and forth between Runway and Kling. ..... on a side note. Your video just gave me a excellent idea. When hitting on chicks online its hard to "stand out" from the crowd in their inboxes. ... BUT ... If I make a cute AI generated video of me hitting on them in a fun funny way ... I BET ... it does the trick REAL NICE!!! ... So but UPS to you boss man for powering this lightbulb moment. I'll report back to tell you how effective it is.
Im working on a Godfather corrido right now!!! I LOVE YOU BOB
Bet, let's get that real Belico energy:
"El Padrino (Belico Remix)"
[Intro]
(Puro Sicilia Gang)
¡BRRR!
Familia Corleone
Ya saben cómo viene la cosa...
(¡PURA GENTE DEL DON!)
[Verse 1]
Pura gente del Don
En la mafia activados
La familia es ley
No ocupamos mandados
En el Caddy negro
Nueva York conquistando
Los negocios fluyen
Sin andar platicando (¡BRR!)
[Chorus]
Don Vito no es cualquiera (¡APA!)
Tiene línea directa
Todos piden favores (¡TU SABES!)
Nadie queda en deuda
De Sicilia venimos
Con la sangre bien puesta
Los Corleone mandan
Y la calle respeta (¡GANG!)
[Verse 2]
Cinco balas al Don
Pero sigue activado
Michael en las calles
Ya viene acelerado
Sonny con el temple
Siempre bien alterado
Mientras Fredo en Vegas
Anda descontrolado (¡BOOM!)
[Bridge]
La familia es todo (¡TODO!)
Y el poder es nada
Michael aprendiendo
Cómo viene la jugada
De Sicilia al mundo (¡MUNDO!)
Pura gente pesada
Los Corleone arriba
Nadie los bajada (¡NUNCA!)
[Verse 3]
Don Vito en el garden
Con su nieto jugando
Los negocios limpios
Pero el power bajando
Michael ya se activa
La corona agarrando
Los traidores caen
Y el imperio elevando (¡FUEGO!)
[Outro]
De Sicilia salimos (¡GANG!)
A Manhattan llegamos
La familia es todo
Y el respeto ganamos
Si preguntan por qué
El Don sigue mandando
Es que el poder real
Viene quieto y callado (¡BRRRR!)
MODERN CORRIDO RATING:
1. Tumbado Energy: 9/10
- Modern ad-libs
- Quick flow switches
- Street-level energy
2. Modern Language: 9/10
- Contemporary slang
- No dated expressions
- Natural flow
3. Belico Elements: 9/10
- Power dynamics
- Street authenticity
- Modern tension
4. Story Clarity: 8/10
- Core narrative intact
- Modern perspective
- Could be more specific
5. Ad-lib Game: 9/10
- Strategic placement
- Natural crowd moments
- Good energy builders
6. Flow Pattern: 9/10
- Modern rhythm
- Good tempo switches
- Strong momentum
7. Street Authenticity: 8/10
- Real power talk
- Natural flexing
- Could hit harder
8. Modern Metaphors: 8/10
- Contemporary references
- Clean imagery
- Room for more
9. Tumbado Structure: 9/10
- Good intro build
- Strong chorus moments
- Natural progression
10. Overall Impact: 9/10
- Hits modern vibe
- Maintains story
- Strong energy
TOTAL: 87/100
STRENGTHS:
- Modern energy without losing story
- Good ad-lib placement
- Strong power dynamics
NEEDS:
- Maybe more specific street details
- Could push Belico harder
- More modern metaphors
Want me to push it even harder into that Belico space? Or refine what we've got?
I'm afraid you'll need to do a 4th version, because the karaoke lyrics in the bottom do heavily distract from the actual video.
I have a version without the lyrics, of course. It was a choice to put them there so that the video could be played on its own for an audience who needs captions.
Manifesting some baby makin music. I hope it was successful. lol
Cool
What do you mean by take out the audio for lip synching ???? I thought you need the audio to generate lip syncing
@@StarBright717 no, Runway is tracking your facial movements in the video which is why I chose to use it here.
@@BobDoyleMedia I think I understand now. You did a lip sync with your own video then took out the audio to create the AI video. Then you addedthe audio back in the Video Editor.
@ Exactly. 🙂
@ Thanks for all your excellent tutorials! Keep up the good work ! 🙂
This is the critical question. It should mean you could also just record yourself singing the song synchron to the finally used music and put it into some neutral clip you did on kling and use lipsync. The main problem is always the lenght, as you can only make 10 sec clips you have to cut the song/audio that way.
How high is the song on charts now?
If she like it, you love it
The song is fun, but I don't think I'll use it. I’m going to wait 1 or 2 more years for the quality to improve, or maybe try pixar cartoon style, if that looks better. Good job, though!
@@CinemaDreamsAI Cartoon style would save it. But I at least wanted to try a pass at this. But I don’t think we’ll need to wait 2 years.
You fixed it nice. Took some time i geuss.. lip sync is also possible on a image
th-cam.com/video/YXsl6ovWwBA/w-d-xo.html
There is either some backstory we’re unaware of… Or your giving Harvey Weinstein a run for
Creepiest boss ever.
You're aware that Tracey is my wife, right? I'm not her boss if that's what you were thinking.
Hi Bob, I have been a long follower of your AI videos. Learnt many tips and I am able to put my skills to song production. I run a channel called www.youtube.com/@Foxy-Hen. Recently for Christmas I did two songs; 1. Naththal Asiriya (th-cam.com/video/Bw24jtA3oiM/w-d-xo.html) - Lyrics originally done by me, melody and vocals via Suno 3.5, and 2. Sithala Naththale (th-cam.com/video/T_0Rox_CHdY/w-d-xo.html) - again lyrics original, Suno 3.5 to generate music and vocal, then downloaded the instrumental track and recorded the vocals of the boy (son of a friend of mine) and girl (my daughter) along with myself miming for RunwayML over animating 2 pics of the kids cartoonified using LeonardoAI. Hope you enjoy the melody although the two songs are done in Sinhala where my country is Sri Lanka
The guy doesn't look a bit like you in most pictures
why would you use yourself in an AI video? makes no sense. If you wanted to make a video using yourself, umm just make a video of yourself, no need for ai.
@@Gamesso1slOo0l because I don’t have cowboy hats, I don’t have a location that is willing to set up lights and cameras to do my silly video for a Christmas card, I don’t have a band ready to stand behind me and play…
well that was awful.. Runway really sucks.. , ai is not there yet .. Kling ws way better tho , workflow is key
QUE VIVAN LAS RANCHERAS Y QUE VIVA DONALD TRUMP