Yep, really impressive and will hopefully get better over time. You could also try breaking your image up into components to get a higher res mesh generation and then spend time joining bits together in Blender... but that was a bit too involved for the tutorial.
Pretty cool tutorial. By the way, CSM can now export in OBJ file format, which can be uploaded directly into Mixamo, so you can skip the file conversion step with Blender.
Awesome! When the software giants bring this all together into one single pipeline instead of jumping between different software apps, I'll be jumping in and making my feature film and immersive game world!
Yeah, like every untalented person in this world with a PC is going to. Like trying to sell books on amazon. Or doing Indie games since everything has become so easy for unskilled normies to do. And then no one is interested in entertainment anymore. Because every average joe is putting his boring crap online and there is so much crap on the internet that you barely find the good stuff :D
3:12 if im not mistaken this isnt actually AI. They say its AI but really its just people quickly approximating a model that looks somewhat similar to the image. At the very least there are websites out there that advertise themselves as AI when its not really AI at all. The biggest tell is usually if it takes hours to generate, if its AI I shouldnt take very long at all. Also if the typology is nearly perfect (not rough looking) it can often mean it was just generic assets meshed together.
looking at the mesh i had internal screaming. I thought this would be of any greater use but i guess when you want cheap, low quality characters and assets it could still be useful. And dude.. just use blender for the animation work rather than after effects. Put ground as shadow catcher and use a HDRI of similar colours and shapes and you're gold. You could even tweak the animation as you go.
awesome video. Amazing, how much time you spend as well creating it. I really like the output, but'd love to see an update with the shadows of the robot falling in front of it, aligning with the other shadows of the jungle scene. I think it would even more increase the realistic feel
I get it, and agree that being able to animate is a key skill, as motion capture limits the style of animation, and can't be applied to all animation styles. i.e. double bounce mickey mouse style, stylistic stunning over the top animation like Ren and Stimpy.
Yeah, dont get me wrong, i think this a cool tool to use, and a great tutorial fyi. It's just not for finished product animation as it is right now. in the future i could see this as maybe early pre-vis workflow.@@AIAnimationStudio
I saw this tutorial 5 months ago. I now know how to use blender pretty well, and use so many other AI apps. My question is after all you did can you download it as an MP4 to upload to Facebook or RUclips? Thanks as I look forward to doing this too!?
This is awesome! Hoping in the future any of these would consider cloth and hair physics as well. I'd presume some people would want long-haired (or long-clothed) characters to be processed this way and it would look weird if the hair and clothes are too stiff while the entire body is animating naturally.
Thanks. Yeah absolutely. Even things like glasses on a character would need to seperately created and added to a model at the moment to give that seperation from the face... but it's useful for lots of other cases. The Character Creator and iClone from RealIllusion, can do some crazily good stuff that would cover alot of this right now though ... but the software cost and learning curve is considerably higher.
Yes this is awesome, but it is more scary than awesome. In this video you could have employed 30 people specialized for separated stuff. Now youre going to need only one.
@@viktortoleskiand it looks like one person cobbled it together. While it's neat it is still SO limited and not worth replacing anyone. That base mesh is garbage, the lights are baked into the textures, the tracking is bad because it isn't a real camera so the points aren't actually accurate. It's very cool that someone can make their own 3d shorts with this, but it's still way far off from replacing most of the artists.
@@viktortoleski It's never as simple as "new tech->less jobs->more poverty", that's just plain naive. I mean, the less work is needed to produce something, the more you can make in the same time window and you can sell it for cheaper too! That is awesome if you ask me :D.
Yes VFX artists, far less of them with far less training. What a horrible argument my Lord I'm so tired of morons using this "it's just another tool in the tool belt" argument.@Thefan
So how much time did this "creation" consumed in real time versus making it from "hand", if typing, pushing mouse and clicking on it, and holding a graphics tablet, whilst already using a computer, software, can be considered hand work or crafting?
Not actually sure, as was testing/learning and then making the tutorial soon after. Still lots of arguments for modelling the character manually depending what you wanted to depict in the scene but there's definitely use cases for these tools. You could model and texture a similar robot using basic modelling techniques comfortably in a day and have a better quality model and rig. But for speed and a simple 1 button press and walking away the CSM version is already impressive. The background scene in runway ML would take ages to create unless you paid for stock footage or flew to a rain forest. Once setup you could expand on the small clip I created using more motion capture, traditional 3d rig animation and various camera cuts.
@@travissmith5994 Thanks. It would be interesting to see if we could get the same images but in rotation by using image weights in order to create a panorama. Might be worth a try.
You can use it via Discord. I've covered it in a few videos. I think one of my older ones still holds true... ruclips.net/video/t5Vq4ahmn74/видео.htmlsi=zILv30Fn3mqJduln&t=117
Thanks for the video. I just want to point out that "FEASIBLE" is very different than "POSSIBLE". This workflow is definitely possible but is it feasible for creating good looking game assets without bugs? A big NO.
You have to pay 60$ for CSM that you own your model which has a bad topology. Every AI wants your money when all you want is earning money.😅 But lets hope SD is great and free mit automatic. Lets hope AI will become free for every use.
Yeah, these A.I. things are just scamming users for their money. It's messed up. I'll just wait for A.I. to be implemented in official software I already use but I am not paying for these tools.
Wow, I just learned how to create and rig a character recently(which takes forever) and just the fact that I can spin up and rig a character with little effort is dope. Definitely can speed up my blender workflow. Probably won’t do the parts from after effects portion and on, but dope nonetheless.
I have a laptop but I have a question to ask Will I need to get a better computer or do I need to get flash drives or anything with downloading so many things could it over power my computer making it to full or do I need a better computer also how much does it cost for all these subscriptions that you're mentioning and if I cannot follow or see the pixels cuz they are kind of small even with my computer on full blow can I get a tutor and get him or her paid by a Pell Grant I'm just asking so that I can know how to do I'm more of a Hands-On person I hear what you're saying but hearing it and doing it it's two different things and I feel that I might need that extra so what would you recommend for a live tutor
it's great vedio but that's ,eans 3d animation will be end Or will demand decrease in the future? becouse that's make me afriad from this position at the future .
The key question is- can I freely use such assets created in CSM in commercial projets, ex. own game made in Unreal or Unity? I assume after some tuning in ex.Blender I can call them my own assets,with full commercial rights?
The workflow is pretty amazing I must admit. The result, not so much unfortunately. I feel like every step could be improved. For example the topology of the mesh is terrible, the texture is very approximated. The animation from the video reference is meaningless and the comp is far from a vfx production quality. That said it's impressive to see the tool evolving and the leap it took since last year. By no mean this comment is to attack the artist or the creative process. It's just an honest reflection on how people are talking about AI like it's the new big thing but as of right now I don't think the quality is there to compete with any artist in terms of quality.
Hey, thanks for commenting. I 100% agree. It's more a showcase of what you can do right now with the different bits of tech to show how far it's come. Much like the text or image to video AI generators like Pika Labs and Runway ML that are booming. The tech is amazing but the use cases for professional work are limited, but for creating content worthy of sharing and entertaining online they're already arguably good enough for lots of use cases. I do find the AI tech fascinating though and it's evolving so quickly and helping (rather than replacing) creative processes. CSM continues to improve with the image to model generation (*plus other upcoming alternatives) but I think there's a long long way to go before it can come close to rivalling manual modelling for professional work. i.e. a proper rig, that works close up. A robot model for example would benefit so much more with rigged articulated pistons in the arms/legs/neck. Differnet textures, semi-transparent piping, LED lights, all sorts of intricacies that you might want to add to a robot require real, skilled time modelling, texturing and rigging. But for a one-click solution it's surprisingly impressive and no doubt has it's place in basic game assets, social media content, early production animatics. I actually used some CSM generated models for client work recently, but only cause I wanted basic 3D models, that were then used as an emitter for particles in a VFX project. Deep motion (whilst oldest) seems to be the best of the bunch at the moment for easy motion capture (at least in terms of feet sliding), but a better filming setup and more takes, would have helped. The tech used in Wonder Dynamics, Wonder Studio is impressive too. There are other apps appearing in this space too that I want to check out when I get time. But real mocap suits or manual animation still wins out but it obviously takes more money / time. The compositing could absolutely do with more time (and skill 🙂) to perfect the lighting/shadows/diffuse/specular. A real HDR image, and higher quality model would go along way too. But these videos are side projects to the day job.
You can generate some great AI voices using something like ElevenLabs. It's really very good, and you can optionally record you're own voice for improved control over emphasis, then swap in one of the AI voices. As for animating lip syncing, there's a few options (I need to explore these more soon). Things like DiD, Hey Gen are one approach. Lalamu Studio has a free lipync demo, which is low res b ut can work well. Plus there's sync labs new platform.
So how much did this all cost in the end? seems like an expensive set of toys where you need to pay for every step, is getting a 3d model with a rig free at least?
To be honest, there is so much jumping into different software, and, as you mentioned, they can be quite expensive. It is simply much faster to do it all by hand. Additionally, I love to know what will happen if the person who makes the request asks for changes :)
Simply cause my Deepmotion output was a bit poor. Largely due to my poor input video, messy scene and poor lighting, which didn't give Deepmotion the best input to work with. So, I'd simply cherry-picked that part of the motion for the purposes of the tutorial. In hindsight, had I known the video was going to get more than a few thousand views I would have spent a bit more time filming. 😆. Plus more time polishing the finished composition/shadow direction. etc etc... and maybe done a few different shots to tell a short narrative story. (Which was the goal at the time, before I get distracted by the next shiny AI process.)
Thank you, great job! subscribe and like! PS: Sorry, but the light source is behind the figure, as can be seen from the leaves, and for some reason the shadow falls back, although nothing in the environment has highlights or shadows from there. If the figure casts a shadow forward, the picture will be more perfect.
Thanks so much. Glad you liked it. Deffo would benefit from a good bit more time improving where the shadow is cast and tweaking the levels/curves a bit so it sits within the environment a lot better. I mention something like that toward the end of the video but as it was already over 30 mins long I decided that'll do. 😆.
Yeah this process could have been more refined, but admittedly was just working on ways to use the existing tools then. But with the same process (and time spent refining) you could use it to make a much longer piece of content relatively quickly. I should revisit this one soon.
I think in this instance I think it was pure luck. I did'nt actually use the rear view for the CSM process. But if you want it, you can try including the prompt 'character sheet' in Midjourney to encourage it to produce multiple views of the same character in its generations.
This is really wonderfrul for people without any talent or imagination. It's great that talentless people can pretend this way, WHILE destroying their own futures. Thank you ! :)
Hmm, sad that it creates so much polys, not very useful for (mobile) game devs, only maybe useful for movie creators, where poly numbers don't counts. Would like to find an AI that can construct with less chaotic vertices/polys. Seems I still need to create such by hand, but thank you for info.
Thanks for asking, I've added it to the video description, it's also available on the channels 'about' page. Here's the link... cheers. discord.gg/r77JDPEMs5
Hey.. yep you 100% could. 👍 Plus the quick rendering would be there and definitely comparable (better) than via Element 3D and After Effects and you wouldn't need OBJ sequences and could use an FBX or the newer USD format. The main benefit of using AE is that it does open up other visual approaches, plus the real main benefit is that I know After Effects a lot better than I know my way around Unreal. 😅
Working on a cheaper (kinda different) approach. But yeah Adobe Creative Suite (and in particualr After Effects) is really useful for compositing the scene, motion graphics etc etc.. but there are less developed alternatives.
Bro your literal name is aianimation. Just make it AnImation :P Make the A the way you have it and the i slightly larger than the rest of the lower case letters and you’ve got gold. You literally already have AI in the name Animation. Just pop it out 😂
Promising technology but it won’t replace professional modelers and animators in the next 10+ years. At best it’s a toy to spice up social media content.
@@AgispsiThe 80/20 rule will likely kick in with AI too, where 80% of the results are available in 20% of the time, but fine tuning the last 20% takes 80% of the time. 2 years time it'll be great for hobby/casual use, but it's not going to create Transformers level meshes and rigs in that time.
Mark my words if they aren't nerfed due to govt and people freaking out ... in one years they'll be able to produce disney level movies... Ai is growing exponentially not linearly!
I think (hope) it will also create lots of jobs as well. Plus open up ways for creatives to tell untold stories in new ways. Having been an animator and now studio owner for 20+ years ... The genie is definitely out the bottle and I think the best approach is to embrace the new tools, learn and create.
The 3D model looks really bad for any extensive use, what's the point spending a hour to have something kept away from being too close from the camera ? how can a viewer connect on a cinematographic level with something kept far away ? It would indicate distance which is a message to the viewer, it looks like something way too situational to make anything developped around it
Fair. The AI 3D model generations have improved since this was made... it was very much a ... 'what can you do right now' type of approach, with a workflow that could be refined more now as the tools all improve pretty rapidly.
Funny cause this takes almost as long as doing it yourself but looks far worse. Maybe one day will be useful wouldn’t mind using Ai for some of the more mundane tasks .
I think it could be done a little bit easier now. Plus, I 100% could and should have made the final result here a little more polished or made a longer clip, which would have been easy. But it was more of a... this is what you can do right now, kinda thing.
You're not taking into mind the months to possibly years it would take to acquire all the relevant individual skills needed to do everything in this video by yourself. You're also not taking into mind that this is a RUclips tutorial where practicality is usually favoured over perfection.
@@LostBots I say years because researchers say it takes approximately 10,000 hours to master a skill. If you do the maths, 10,000 continuous hours is a little over a year(416.667 days). Therefore 10,000 hours of learning and experience is multiple years, factoring for sleep, breaks, travel and hiatus. It's worth noting that not everyone has the same entry point or can retain information the same level bro. Slightly off topic but I'm trying to learn Unreal Engine and 3D in general and I'm struggling to get to grips with 3D.
Yeah it is. Albeit motion capture using machine learning/AI to turn a 2D video source into 3D motion capture data. I'll be sharing a cool alternative to the motion capture approach soon.
Ai is going to kill craftsmanship. In a few years everyone and their mother will be able to create anything with their phone and no idea of anything or skill of any kind.
... Thanks for the comment. 100%, it looks fake. It's a tutorial much more about AI techniques rather than how to completely composite a full image. It shows the process of turning a 2D image into a 3D character model with AI, rigging it with AI and animating it with AI and motion tracking it into a background video (also created from a still image with AI). All things you could integrate into a full animation production workflow to create something decent. You could/should definitely spend more time on compositing shadows/lighting/reflections than a 30-minute Tutorial can touch on.
Wow! CSM looks amazing! I mean, obviously it's still rough, but it seems way ahead of most 3d model generating AI programs I've seen
Yep, really impressive and will hopefully get better over time. You could also try breaking your image up into components to get a higher res mesh generation and then spend time joining bits together in Blender... but that was a bit too involved for the tutorial.
Pretty cool tutorial. By the way, CSM can now export in OBJ file format, which can be uploaded directly into Mixamo, so you can skip the file conversion step with Blender.
Nice... good to know. I definitely want to revisit CSM in the new year. 👍
The 2d to 3d tool will become a lot better if it allows for multiple reference image, especially front-side-back.
Awesome! When the software giants bring this all together into one single pipeline instead of jumping between different software apps, I'll be jumping in and making my feature film and immersive game world!
Yeah, like every untalented person in this world with a PC is going to. Like trying to sell books on amazon. Or doing Indie games since everything has become so easy for unskilled normies to do. And then no one is interested in entertainment anymore.
Because every average joe is putting his boring crap online and there is so much crap on the internet that you barely find the good stuff :D
the same happen to RPG maker and now any game that is made in hated because of simple joes that mass produced "games"
@@waldau8986then it all ends up getting demonetized LMAO
If you’re not motivated enough to learn the skills to do it now your def never doing it. even when it’s almost done for you.
this is simply unrealistically cool, you have opened a new world for me, please continue, I watch your lessons in one breath ❤❤❤
It is amazing to witness how AI can transform a 2D image into a fully rigged and animated 3D character.
3:12 if im not mistaken this isnt actually AI. They say its AI but really its just people quickly approximating a model that looks somewhat similar to the image.
At the very least there are websites out there that advertise themselves as AI when its not really AI at all.
The biggest tell is usually if it takes hours to generate, if its AI I shouldnt take very long at all. Also if the typology is nearly perfect (not rough looking) it can often mean it was just generic assets meshed together.
Amazing. Best RUclips channel. Thank you.
I don't think I've learnt so much in one tutorial before. Fantastic job. I'll be referencing this for years to come. Thank you.
This be useful for the artist who provide their own images, and not take from many online.
looking at the mesh i had internal screaming. I thought this would be of any greater use but i guess when you want cheap, low quality characters and assets it could still be useful.
And dude.. just use blender for the animation work rather than after effects. Put ground as shadow catcher and use a HDRI of similar colours and shapes and you're gold. You could even tweak the animation as you go.
awesome video. Amazing, how much time you spend as well creating it. I really like the output, but'd love to see an update with the shadows of the robot falling in front of it, aligning with the other shadows of the jungle scene. I think it would even more increase the realistic feel
As an animator I'd say it's better to learn to, ya know... Actually animate. It's a shame AI is making people so lazy
I get it, and agree that being able to animate is a key skill, as motion capture limits the style of animation, and can't be applied to all animation styles. i.e. double bounce mickey mouse style, stylistic stunning over the top animation like Ren and Stimpy.
Yeah, dont get me wrong, i think this a cool tool to use, and a great tutorial fyi. It's just not for finished product animation as it is right now. in the future i could see this as maybe early pre-vis workflow.@@AIAnimationStudio
You're biased. I'd say you dont have as long as you think.
@@nigelcrits I don't have as long as I think for what?
@memoreearts until the need for your services is largely diminished. Learning these AI methods will prove to be the only pertinent tools.
Thanks very much for your tutorial. It is very much appreciated. 👌👌👌
Holy shit, this is amazing. Definitely going to use this kind of workflow in the future, so THANK YOU VERY MUCH :D
holy F*ck!! A model from an image? Impressive
I saw this tutorial 5 months ago. I now know how to use blender pretty well, and use so many other AI apps. My question is after all you did can you download it as an MP4 to upload to Facebook or RUclips? Thanks as I look forward to doing this too!?
Hey, yeah via Adobe after effects you can add the composition to the ‘render queue’ and save out to an mp4. (Or other video formats)
I would change lens flare layer to screen mode :)
Mind = Blown!
Only thing lacking atm is the textures on the character which look crap but I'm guessing ai will improve it soon 😮
Stellar tut, my head´s brimming with ideas on how to apply this knowledge, thank you.
Great contribution. Great tutorial. You have my like. Thank you so much. Greetings
Cheers @3DW3D-TetKaneda. Glad you liked it and greetings too.
Inspiring video.
This is awesome!
Hoping in the future any of these would consider cloth and hair physics as well. I'd presume some people would want long-haired (or long-clothed) characters to be processed this way and it would look weird if the hair and clothes are too stiff while the entire body is animating naturally.
Thanks. Yeah absolutely. Even things like glasses on a character would need to seperately created and added to a model at the moment to give that seperation from the face... but it's useful for lots of other cases.
The Character Creator and iClone from RealIllusion, can do some crazily good stuff that would cover alot of this right now though ... but the software cost and learning curve is considerably higher.
Yes this is awesome, but it is more scary than awesome. In this video you could have employed 30 people specialized for separated stuff. Now youre going to need only one.
@@viktortoleskiand it looks like one person cobbled it together. While it's neat it is still SO limited and not worth replacing anyone. That base mesh is garbage, the lights are baked into the textures, the tracking is bad because it isn't a real camera so the points aren't actually accurate. It's very cool that someone can make their own 3d shorts with this, but it's still way far off from replacing most of the artists.
@@viktortoleski It's never as simple as "new tech->less jobs->more poverty", that's just plain naive.
I mean, the less work is needed to produce something, the more you can make in the same time window and you can sell it for cheaper too! That is awesome if you ask me :D.
🔥Very cool tutorial! as always 🤩thank you for sharing this 🙏 Like👍
Ah beautiful. This is gonna put film studios out of business and I'm here for it.
Yes VFX artists, far less of them with far less training. What a horrible argument my Lord I'm so tired of morons using this "it's just another tool in the tool belt" argument.@Thefan
HI !
can i use a character IMAGE to create a T POSED MODEL of it ?
좋아.. 아주 좋아.
Far from a professional result but i bet it will do a big favor for a lot of indie devs.
Amazing. Super cool video.
So how much time did this "creation" consumed in real time versus making it from "hand", if typing, pushing mouse and clicking on it, and holding a graphics tablet, whilst already using a computer, software, can be considered hand work or crafting?
Not actually sure, as was testing/learning and then making the tutorial soon after.
Still lots of arguments for modelling the character manually depending what you wanted to depict in the scene but there's definitely use cases for these tools.
You could model and texture a similar robot using basic modelling techniques comfortably in a day and have a better quality model and rig.
But for speed and a simple 1 button press and walking away the CSM version is already impressive.
The background scene in runway ML would take ages to create unless you paid for stock footage or flew to a rain forest.
Once setup you could expand on the small clip I created using more motion capture, traditional 3d rig animation and various camera cuts.
Very nice! but the shadow is going the wrong way in the end :)
Yep.👍.. could and should have spent more time refining the composite.. but it was already a bloomin long video ... next time..👍
Nice topology
I subscribed, thanks you sharing!
Tutorials for mobile for this same type of ai animation is there ?
What are the terms and conditions for using the 3d-model in a commercial product, a game for example?
AI generated art is not copyrightable
So incredible!
Is it possible to perform this process (motion capture) for two or more characters at the same time?
you blowed my mind!
amazing work
Great video thank you
A good artist can do that quality in 5min
more difficult than i imagined
@@dharmaverse_io . New video out later this week (maybe next week) . Things have got better
Incredible
We would do better with the image to 3d mesh if we were using Nvidia NERF directly?
NERF requires several consistent images from multiple directions - something you can't currently get with AI generated images.
@@travissmith5994 Thanks. It would be interesting to see if we could get the same images but in rotation by using image weights in order to create a panorama. Might be worth a try.
Good day, I've tried to use Mid-Journey - How do you install it and make it work? Do you maybe have a tutorial please? Thanks!
You can use it via Discord. I've covered it in a few videos. I think one of my older ones still holds true... ruclips.net/video/t5Vq4ahmn74/видео.htmlsi=zILv30Fn3mqJduln&t=117
Great
Thanks for the video. I just want to point out that "FEASIBLE" is very different than "POSSIBLE". This workflow is definitely possible but is it feasible for creating good looking game assets without bugs? A big NO.
WAUUU, esto nos quitara el empleo a muchos en blender :v
You have to pay 60$ for CSM that you own your model which has a bad topology. Every AI wants your money when all you want is earning money.😅 But lets hope SD is great and free mit automatic. Lets hope AI will become free for every use.
Yeah, these A.I. things are just scamming users for their money. It's messed up. I'll just wait for A.I. to be implemented in official software I already use but I am not paying for these tools.
It is not AI.
Wow, I just learned how to create and rig a character recently(which takes forever) and just the fact that I can spin up and rig a character with little effort is dope. Definitely can speed up my blender workflow. Probably won’t do the parts from after effects portion and on, but dope nonetheless.
Yeah just using Mixamo to get a basic rig for a character is bloomin handy.
is there a video to rigged animation for stable diffusion?
Imagine the new fnaf fan games with this
I have a laptop but I have a question to ask Will I need to get a better computer or do I need to get flash drives or anything with downloading so many things could it over power my computer making it to full or do I need a better computer also how much does it cost for all these subscriptions that you're mentioning and if I cannot follow or see the pixels cuz they are kind of small even with my computer on full blow can I get a tutor and get him or her paid by a Pell Grant I'm just asking so that I can know how to do I'm more of a Hands-On person I hear what you're saying but hearing it and doing it it's two different things and I feel that I might need that extra so what would you recommend for a live tutor
it's great vedio but that's ,eans 3d animation will be end Or will demand decrease in the future?
becouse that's make me afriad from this position at the future .
nice jobe! How did you get such an accurate model at CSM?
The key question is- can I freely use such assets created in CSM in commercial projets, ex. own game made in Unreal or Unity? I assume after some tuning in ex.Blender I can call them my own assets,with full commercial rights?
The workflow is pretty amazing I must admit. The result, not so much unfortunately. I feel like every step could be improved. For example the topology of the mesh is terrible, the texture is very approximated. The animation from the video reference is meaningless and the comp is far from a vfx production quality. That said it's impressive to see the tool evolving and the leap it took since last year. By no mean this comment is to attack the artist or the creative process. It's just an honest reflection on how people are talking about AI like it's the new big thing but as of right now I don't think the quality is there to compete with any artist in terms of quality.
Hey, thanks for commenting.
I 100% agree.
It's more a showcase of what you can do right now with the different bits of tech to show how far it's come. Much like the text or image to video AI generators like Pika Labs and Runway ML that are booming. The tech is amazing but the use cases for professional work are limited, but for creating content worthy of sharing and entertaining online they're already arguably good enough for lots of use cases.
I do find the AI tech fascinating though and it's evolving so quickly and helping (rather than replacing) creative processes. CSM continues to improve with the image to model generation (*plus other upcoming alternatives) but I think there's a long long way to go before it can come close to rivalling manual modelling for professional work. i.e. a proper rig, that works close up. A robot model for example would benefit so much more with rigged articulated pistons in the arms/legs/neck. Differnet textures, semi-transparent piping, LED lights, all sorts of intricacies that you might want to add to a robot require real, skilled time modelling, texturing and rigging. But for a one-click solution it's surprisingly impressive and no doubt has it's place in basic game assets, social media content, early production animatics. I actually used some CSM generated models for client work recently, but only cause I wanted basic 3D models, that were then used as an emitter for particles in a VFX project.
Deep motion (whilst oldest) seems to be the best of the bunch at the moment for easy motion capture (at least in terms of feet sliding), but a better filming setup and more takes, would have helped. The tech used in Wonder Dynamics, Wonder Studio is impressive too. There are other apps appearing in this space too that I want to check out when I get time. But real mocap suits or manual animation still wins out but it obviously takes more money / time.
The compositing could absolutely do with more time (and skill 🙂) to perfect the lighting/shadows/diffuse/specular. A real HDR image, and higher quality model would go along way too. But these videos are side projects to the day job.
Cool!
Question what if you want to give your character a voice or a Pacific voice how do I add a voice to my animation
You can generate some great AI voices using something like ElevenLabs. It's really very good, and you can optionally record you're own voice for improved control over emphasis, then swap in one of the AI voices. As for animating lip syncing, there's a few options (I need to explore these more soon). Things like DiD, Hey Gen are one approach. Lalamu Studio has a free lipync demo, which is low res b ut can work well. Plus there's sync labs new platform.
Imagine paying for mid journey when stable diffusion is a thing
Wait so midjorney can use your picture as reference?
What will you learn from this ?
So how much did this all cost in the end? seems like an expensive set of toys where you need to pay for every step, is getting a 3d model with a rig free at least?
To be honest, there is so much jumping into different software, and, as you mentioned, they can be quite expensive. It is simply much faster to do it all by hand. Additionally, I love to know what will happen if the person who makes the request asks for changes :)
LOVE ✊🏿
In the end result the robot only moved 2 steps, where your movement in deepmotion was quite a bit longer, why is that?
Simply cause my Deepmotion output was a bit poor. Largely due to my poor input video, messy scene and poor lighting, which didn't give Deepmotion the best input to work with. So, I'd simply cherry-picked that part of the motion for the purposes of the tutorial.
In hindsight, had I known the video was going to get more than a few thousand views I would have spent a bit more time filming. 😆. Plus more time polishing the finished composition/shadow direction. etc etc... and maybe done a few different shots to tell a short narrative story. (Which was the goal at the time, before I get distracted by the next shiny AI process.)
That's amazing, you no longer need mocap with wires, just a video. Now just research how to get rid of that pesky human.....
Thank you, great job! subscribe and like!
PS: Sorry, but the light source is behind the figure, as can be seen from the leaves, and for some reason the shadow falls back, although nothing in the environment has highlights or shadows from there. If the figure casts a shadow forward, the picture will be more perfect.
Thanks so much. Glad you liked it. Deffo would benefit from a good bit more time improving where the shadow is cast and tweaking the levels/curves a bit so it sits within the environment a lot better. I mention something like that toward the end of the video but as it was already over 30 mins long I decided that'll do. 😆.
I wonder how AI is impacting the pricing of creating AI generated videos and film?
Sometimes AI makes the process longer.
Yeah this process could have been more refined, but admittedly was just working on ways to use the existing tools then. But with the same process (and time spent refining) you could use it to make a much longer piece of content relatively quickly. I should revisit this one soon.
my image does convert. I just shows "training preview" and nothing else. Do I have to get the paid verson for the 3d model?
Or you can do the entire thing in Blender for free and without 10 different application.
How did you manage to get a image of the front and back of your character in one generation?
I think in this instance I think it was pure luck. I did'nt actually use the rear view for the CSM process. But if you want it, you can try including the prompt 'character sheet' in Midjourney to encourage it to produce multiple views of the same character in its generations.
This is really wonderfrul for people without any talent or imagination. It's great that talentless people can pretend this way, WHILE destroying their own futures. Thank you ! :)
This guy gatekeeps
Hmm, sad that it creates so much polys, not very useful for (mobile) game devs, only maybe useful for movie creators, where poly numbers don't counts. Would like to find an AI that can construct with less chaotic vertices/polys. Seems I still need to create such by hand, but thank you for info.
Yeah, agree. I think it's improved a good bit since I made this video but need to revisit and check it out when I get time. 👍
Can I do this only in python open source?
Can you add a link to your discord server?
Thanks for asking, I've added it to the video description, it's also available on the channels 'about' page.
Here's the link... cheers.
discord.gg/r77JDPEMs5
Why not use ue5?
Hey.. yep you 100% could. 👍
Plus the quick rendering would be there and definitely comparable (better) than via Element 3D and After Effects and you wouldn't need OBJ sequences and could use an FBX or the newer USD format. The main benefit of using AE is that it does open up other visual approaches, plus the real main benefit is that I know After Effects a lot better than I know my way around Unreal. 😅
Looked good till I seen how much the programs cost but I'm just a hobbyist 🤑😱
Working on a cheaper (kinda different) approach. But yeah Adobe Creative Suite (and in particualr After Effects) is really useful for compositing the scene, motion graphics etc etc.. but there are less developed alternatives.
Bro your literal name is aianimation. Just make it AnImation :P
Make the A the way you have it and the i slightly larger than the rest of the lower case letters and you’ve got gold. You literally already have AI in the name Animation. Just pop it out 😂
Thanks. I did consider that when first making the channel. But then got the domain name . So … 🤷♂️
Also caption if a person is hearing impaired
10:06 😂🙂
i just tried csm. 481 hours haahahah
👏👏❤️🔥👌👊
Promising technology but it won’t replace professional modelers and animators in the next 10+ years. At best it’s a toy to spice up social media content.
Lol, if you said in the next 2 years sure, possibly, 10 years means you haven't been paying attention.
@@AgispsiThe 80/20 rule will likely kick in with AI too, where 80% of the results are available in 20% of the time, but fine tuning the last 20% takes 80% of the time. 2 years time it'll be great for hobby/casual use, but it's not going to create Transformers level meshes and rigs in that time.
@@AgispsiYeah, people don’t seem to understand how far these tools have come from a year ago. It is honestly scary.
Mark my words if they aren't nerfed due to govt and people freaking out ... in one years they'll be able to produce disney level movies... Ai is growing exponentially not linearly!
@@siriobyy It would take far more progress in one year than Stable Diffusion has had for AI to produce Disney quality movies just one year from now.
👏👏👏👏
Awesome result of AI.
AI will take away jobs of artists in future..i don't have job now I am rigger and motion capture artist.😔
I think (hope) it will also create lots of jobs as well. Plus open up ways for creatives to tell untold stories in new ways.
Having been an animator and now studio owner for 20+ years ... The genie is definitely out the bottle and I think the best approach is to embrace the new tools, learn and create.
@@AIAnimationStudio 🙏
Thank you Ryan Reynolds
🤣🤣. I'll take it.
that topology 🤢🤮
okay but it looks bad
The 3D model looks really bad for any extensive use, what's the point spending a hour to have something kept away from being too close from the camera ? how can a viewer connect on a cinematographic level with something kept far away ? It would indicate distance which is a message to the viewer, it looks like something way too situational to make anything developped around it
Fair.
The AI 3D model generations have improved since this was made... it was very much a ... 'what can you do right now' type of approach, with a workflow that could be refined more now as the tools all improve pretty rapidly.
That's a great public domain work you DID NOT make.
da rb chaatha
I can't think of an actual use for this. It just looks janky, unappealing and really devoid of anything interesting. Lazy process, lazy outcome.
:)
Funny cause this takes almost as long as doing it yourself but looks far worse. Maybe one day will be useful wouldn’t mind using Ai for some of the more mundane tasks .
I think it could be done a little bit easier now. Plus, I 100% could and should have made the final result here a little more polished or made a longer clip, which would have been easy. But it was more of a... this is what you can do right now, kinda thing.
You're not taking into mind the months to possibly years it would take to acquire all the relevant individual skills needed to do everything in this video by yourself.
You're also not taking into mind that this is a RUclips tutorial where practicality is usually favoured over perfection.
@@-_-DatDude it would not take you years to get good enough to produce something this bad a couple months maybe at most
@@LostBots I say years because researchers say it takes approximately 10,000 hours to master a skill. If you do the maths, 10,000 continuous hours is a little over a year(416.667 days). Therefore 10,000 hours of learning and experience is multiple years, factoring for sleep, breaks, travel and hiatus.
It's worth noting that not everyone has the same entry point or can retain information the same level bro.
Slightly off topic but I'm trying to learn Unreal Engine and 3D in general and I'm struggling to get to grips with 3D.
bro... this is motion capture.....
Yeah it is. Albeit motion capture using machine learning/AI to turn a 2D video source into 3D motion capture data.
I'll be sharing a cool alternative to the motion capture approach soon.
It sucks but don't be sad, it's not actually your work.
It looks kinda cool though since people do this very quickly
CSM 3D is terrible. No clue how your model came out so decent. I waited an hour and mines looked like a smashed soda can. tf
Really. That's annoying. Check out their discord for any tips on getting better results. Some impressive results are being generated there.
Ai is going to kill craftsmanship. In a few years everyone and their mother will be able to create anything with their phone and no idea of anything or skill of any kind.
dystopia
the result looks super fake
... Thanks for the comment. 100%, it looks fake.
It's a tutorial much more about AI techniques rather than how to completely composite a full image. It shows the process of turning a 2D image into a 3D character model with AI, rigging it with AI and animating it with AI and motion tracking it into a background video (also created from a still image with AI). All things you could integrate into a full animation production workflow to create something decent. You could/should definitely spend more time on compositing shadows/lighting/reflections than a 30-minute Tutorial can touch on.