I've watched many ComfyUI tutorials and encountered numerous errors and methods that didn't work. However, yours was flawless. Everything from the file organization to the installation guide and the detailed, easy-to-follow tutorial was perfect. I wish you all the best in your endeavors. Thank you so much!
This will work best when you can draw the poses and fill in mismatch frames your self also you can use exaggeration anticipation, animators are getting upset but actually they are the best equipped to make content, their works will be so much better than the non artist prompters, I hope more of them experiment and push this,
@@bake-io1cf 50/50.yes , but also can save time if you are an animator and want faster results (for fan animations, or for fun, just draw keyframes, color them in, and don't have to color each breakdown and inbetweens, (only for simple animations like headturns, smaller movements,etc.)
@@tr1pod623 I'm in 3d animation for around 16 years now my Linked-in is sprawling with frantically anxious concept artist animators motion designers worried about jobs, the market is not great for them right now, which is not all to do with Ai but there have been some layoffs because of it. games industry contracting, also the writers guild strikes halting productions, tax breaks for media production being stopped, but also studios with very limited budgets are modifying pipelines for ai lowering staff hires, I'm currently in a 33 man team of animators which I know did not hire any more this past year because it was not deemed necessary despite us having more projects than before & deploying AI. it's especially bad for 18- 23 age bracket of less experienced animators.
What the anti-AI crowd don’t understand is that AI is simply a tool, it is not replacing artists or creators. But really at the core of most AI hate is that it is another tool that democratizes an art form that was had an expensive entry point in addition to a steep learning curve.
I'm getting less of that from the artists than the fact that generative models were trained on their copyrighted works under an assumption of "fair use" that is not yet legally tested. There's some gatekeeping, but most of it is that they're not getting paid for the use of their work to train the AIs in the first place. There's too much black-box stuff going on. Bloggers are complaining that some models are live-scraping their sites, disguising their User Agents and ignoring robots.txt, and have proved it. OpenAI is not open about what was used in their training sets. It'll take another 3-5 years for any cases to progress to SCOTUS for a definitive ruling of what constitutes "fair use" for training for-profit AI models. Essentially, too many creators of gen AI models are "getting rich" off of potentially illegally training their models to copy the work of artists whose works are being used for training without compensation. Even Adobe, which claims to work with artists for Firefly, is being accused of appropriating art off Adobe Stock for training without honoring an opt-out. The biggest concern is whether you'll be able to trademark or copyright a character created with Gen AI. Last I read, the Library of Congress stripped an AI comic book of its copyright, then issued a new copyright just for the story and layout, but the art was not allowed to be copyrighted.
nah it’s not just a tool. i used to hire artists for my products and now i don’t. no need. ai is cheaper, faster and better than any artist working traditionally at this point. at least for digital art.
This is amazing. I am an artist and therefore wouldn‘t have an issue with those messed up frames or keyframes, the ai didn‘t do so well and just draw those myself. This just speeds up time so immensely. I always wanted to create an animated short film but the amount of work, I would have needed to perform, simply was way too much for my disabilities. With such tools and workflows I have hopes again. AI tools are such a godsend and help removing barriers. Either the barriers of not being able to draw or paint or whatever, or like in my case the barrier of partially paralysed hands, chronic pain and a severe fatigue. These are just amazing times.
True, this is the first AI tool that could actually be helpful for real artists. It isn't really that useful for people with no animation background unless they think the animations featured in this video are good enough.
@@derrygorl Like all AI tools you should know what you are doing. Like a photo-camera doesn‘t make you a photographer-artist or the video App on your phone doesn‘t make you a movie producer. As an artist who faces some bodily challenges, I can tell you that those systems really helped starting with disco diffusion over two(?) years ago. „Real“ artists usually use everything to their disposal when creating artworks, at least those non gatekeeping ones, who take art serious and not put themselves on any sort of pedestal. I have seen just amazing animations using early stages of stable diffusion, but if you are looking for any one click solutions, you probably won‘t find it with this or other animation and video ai tools - to get them onto a level of midjourney it will take two or three more years, I assume.
@@NoPhilospher in the long run I plan of making an hand drawn animation of my hamster (I usually make pictures of Hamsters) and yes, I tried this workflow with some keyframes I drew. But it didn‘t work satisfyingly good, because my hamster design is quite specific and so this wasn‘t that successful. I guess I would first need to train the ai on my own works and then try again. Or I first use the 3D right of my hamster and then use this workflow to change the aesthetics towards my 2D style. I suppose in the end it will just involve all the tools I got to my disposal. 😅
Only problem is you dont own anything the AI generates unless you trained it yourself which means = People can legally profit off of your work since it isnt copyrighted.
Smartest kid on the block! I mean it! Your workflows are always so innovative and clever. Thanks again for another great demo of what can be achieved to create animated films.
@@mickmumpitz Hi please help me I lose the consistent character when I switch to the position of the perssonage yet I copy my positive and negative prompt use before
@mickmumpitz Dumbest kid on the block, I mean it... Your workflow is non-existant and uninspiring, Unappreciation for the first time for making such an unfulfilling demo of what weapons can be used to destroy the passion and creativity of humans.
Why is there so much hate on something that could be legitimately helpful for artists? This is just the same type of interpolation a lot of digital animation already uses but significantly more sophisticated. Someone who understands posing and timing could use this to phase out the tedious "tweening" process without utilizing puppet animation. This is the sort of thing we WANT AI tools for. Lol
Animators have been using digital tools that speed up the workflow for years, so I don't see this as a bad thing for animators. For example a very popular tool in the animation industry would automatically fill in vectors for in between frames roughly and then the animators would fix the mistakes the software made and then move on. So I feel like anyone complaining about potential AI tools for animation probably aren't actually in the animation industry at all.
Or they never tried it for fun. I tried animating a lot of times in total just for fun and it took so long just to make 1 second of animation which was about 15 frames and that was with simple clothing and stuff, plus i'm not good at backgrounds so i cant design backgrounds that well. And everyone that says "just learn it" doesnt know a thing cuz to animate u have to have high art skills which is NOT SOMEthing easy to just "get" like what everyone pretends it to be. So its easier to just use ai
This series of workflows is great! I have an anime-style music video that I want to create, and I thought it was probably going to be another year before the quality and temporal coherence of these tools reached an adequate level. This isn’t perfect, but it’s close enough that doing some touch-up in Photoshop becomes viable. Thanks again for figuring all of this out!
Not convinced the amount of work to set this up is worth it. Whats really getting me is the difficulty on posing the character. When you make a pose and render the image you are not guaranteed to get what you wanted, complex pose gets messed up with that 3d poser as to depth maps for the hands... thats alot of work for each and every pose you may want. When you can take that 3d poser and make 3d animations as you would in maya and then be able to apply any character to that reliably, and be able to tweak timing of animations add in or remove frames, then I think you have something. Until then keep up the good work.
Damn! You are really pushing the whole nascent AI animation industry forward! Been following for a while and every video you come up with a more sofisticated approach! Congrats!
Well that was complicated. I wish this could all be done in one application. Also, I’m still waiting to be able to use AI to create scenes with ‘multiple consistent characters’ interacting with each other.
While it's useless as a final product, for those unfamiliar with animation principles, particularly timing, it can be helpful to trace over the animation to fix consistency issues. For animators, it can speed up workflows, like figuring out the in-betweens needed to adjust the animation speed (for your sanity, keep it on twos, don't try to do 24 fps in ones with this process XD). I'll definitely not use Tooncrafter in its current state, but I'll keep an eye on it for sure. Thanks for this tutorial!
You know what, I am going to try this. Mess around with it a bit. Might not be perfect but the possibilities for creating proof of concepts with this intrigues me. It would give me something to do with all this writing that has built up over the years.
Traditional forms of animation would be great for some scenes but it would definitely cut down on time for moments that are quite locked of or simple shots
I'm more interested in the tweens. That feature looks most promising. Not having to make walk cycles or tween poses could be awesome. I'm interested in using face tracking for emotions and mouths though could be a game changer
This is really awesome I could help you with a combiner program which would allow you to combine all those photo outputs onto a single sheet automatically
Hello and thanks for this tutorial! One question i have: Is it possible to go straight from selfdrawn keyframes into animation? Your answer, or maybe some hints, sources etc. would help me alot to realize the dream of an selfmade anime.
It can reduce the amount of frames needed to be drawn but I don't think we can just not do the in-betweens entirely since the thing still produces garbled frames.
I'd rather do everything by hand rather than using AI. I believe in "hard work makes the product better" even if it hurts, through diligence and patience. I'm not saying this is wrong, I just like doing stuff traditionally instead of having to rely on tech like AI.
Great Video, I love the mixed media approaches you are working with here, its fantastic. One thing that still stands out to me is all the steps in the sausage factory you still need to get results. I beg to question why wouldn't someone still work in a more traditional animation manner to create something without maybe some of the quirks? Regardless, the final effect you achieved is awesome, I just feel like if you're young watching this and diving into all this tech, maybe also learn toonboom or maya as well. It will only serve you well when mixing with comfy,etc..
the camera movement, if the camera movement can remain the same, or controlled, for example stop it from zooming in/out or panning (unless speceifiec) the animation would be better. Another thing, animation smear, I think the keyframes that one puts as an input if they are too far apart causes more noticible animaiton smearing. Smearing is nice if used correctly, specially in higly dynamic action scenes, but in calm slow scenes it looks off. I think maybe adding either more keyframe for slow scenes, maybe not more keyframes but psace them aout accordingly. its gonna be an iterative test until we figure out how much 'time' or 'frames' is best to put as reference
This is insane! I've always wanted to make my own anime, but my drawing skills are basically nonexistent. This workflow seems like a game-changer, even if it means spending way too much time tweaking prompts. What do you guys think, is this the future of animation or just another AI fad?
i think there will be more to it. this is obviously a workflow that will be iteratively improved upon however i feel like 3d models will have something to do with the craft, like youl generate an image, then use a workflow like this to get different angles, then make a 360 video, then gausian splatting to get a near perfect 3d model with perfect textures, then auto rig and animate, then tell ai what you want from the videos and it will use the model and rigging to get perfect outputs with zero errors, not even extra strands of hair or limbs,. something like that i reckon, and eventually itl be all behind the scens so u just generate an image and ask for the video
@@j.2512 @RiiahTV 0 seconds ago @j.2512 what does art mean to you? if you dont mind me asking you the definition. to me art is how humans use tools to express their thoughts. i believe people like yourself fall in love with the tool itself. and forget that at one point the tool that you use for art was once looked at like it wasn't. remember this "there once was a finger painter in a cave, a man came with a paint brush and he hated how it didn't do what his hands could do. there was a painter painting a photographer comes and takes a picture of the woman. the painter didn't like how he couldn't control the camera like he could his paintbrush. the photographer was taking pictures a man with a reel begins taking multiple images to make film. the photographer didn't like how he had to put together images to make movement. the videographer and the photographer are working together now and a guy with a computer shows them photoshop. they call it blasphemous. it's not real photography. a guy that uses videography and photoshop is doing his work when a person that uses an animation program shows him what he's capable of without any physical tools like a camera. the guy with the cam like real footage and really getting out there to capture real settings. the animator meets ai. the animator embraces change because animators know when new tools are introduced it only means progress in art. young blood remember artists use tools to create art. just because your not smart enough to use a hammer doesnt mean some one cant grab a chisel and make an ice sculpture of mona lisa. wake up are is everything. art is perspective. art is life. you are a blackhead on the face of idiocracy.
At least those tools didn't need to be trained on works of art of real artists without permission and proper compensation. Those tools you mentioned didn't have to be fed existing art in order to produce another!
This is a very interesting showcase of the cutting edge of AI applied to animation. However, given the massive room for error & need to learn a nee program, I'm not sure it's currently worth it to spend the time learning this v.s. spending the time improving your skills & using proven tools like Mojo for easier 2d animation in the long run.
First off, thank you so much! You made it so simple to install and to play around with it. My first results show up as images without much animation between, character moving lips then jump to the next image. Any idea what I may be missing here?
Reporting back after more testing - So I managed to get the animation to come out! Just chose images that look more similar to eachother. My first tests were too different key frames so it didn't even try to animate between them. I would like to experiment to try and 'force' it to interpolate even if the keyframes are very different (like getting one character to turn into something else)
Got this error when executing the tooncrafter workflow, it happens when it passes through tooncrafter interpolation node: "Error occurred when executing ToonCrafterInterpolation: No operator found for `memory_efficient_attention_forward` with inputs (...)"
how everyone is saying this is good, when the hands are always ruined. proportions of the body suffer too. it is so far away from the production-grade animation, that I don't understand whom it is for. I am very bullish on the AI assistance tools for technical work in animation pipelines, like inbetweening or coloring, but this would require a clear process of how an animator can edit and improve on the generated images and clean up all the artifacts easily. as soon as it is easier that drawing these shots from scratch, this becomes a viable production tool for animators.
Can I suggest using something like FlowFrames to do the final clean up of interpolation? Maybe it is better to have less frames per second using your method and then interpolate the remaining frames(15 to 25 for example or 25 to 60) with software really dedicated to this. There is also paid software namely video ai 5 but it's expensive.
Always love your vids @mickmumpitz even when you were making sketchy blobby 3d chars. There are similarities to the way sketch animation on paper works, but the ai is filling in the blanks
Guys, I have an easier workflow ! Instead of downloading, posing, arranging the poses, transforming yourself into ai, arranging the flows... You can just open procreate and draw it yourself .
Hey all, I am a game developer and I stumbled upon this video. To make a 2D fighting game like Mortal Kombat or Guilty Gear, one could potentially create the model sheet in ComfyUI and then then the various poses in Open Pose AI. Then, in Unity you could just create the animations, VFX, juice etc. to get it all working and feeling like a completely original fighting game. Is anyone interested in connecting on Discord to go through this and collaborate on a project like this? I have about 4 years of experience working in Unity for a few games that are live and in production. I am really interested in diving into this, but would love to do it with a team!
I'm using the anime character model sheet and I can't seem to get it to follow my hair style prompts. It always seems to give me a very similar style, I'll put: ((short messy hair)), and it'll give me medium, typical anime hair. If the style changes, it's never short and for the multiple angle headshots, the hair is nearly always the same no matter what. Changing through the seed didn't help
Excellent video, thank you for sharing. My art style is kind of like Invader Zim. I wonder would it be possible for me to create a model sheet in that kind of style, and then shoot my own video reference footage. I would like to think regardless of model style it should still work well. Hope to experiment this weekend, and I'll find out I guess
Hey mate - great video! I was curious if you know any websites that have a filter or can convert a long form 5-10 minute video from real life Podcasters to anime in good quality? Starting an AI Podcast, and all the tools I've found only seem to do quick 10 second or under 1 minute videos - thanks!
anybody else getting an error message during the pose step? I can't generate the character poses for some reason. The load ControlNet Model Nodes under the Character BG section are red and the process stops
Your video are Amazing, i would like to ask you a question. Is it possibile to generate the model sheet of the character without using the prompt? For example if i draw a character myself in front view, is it able to create the rest of the model?
I've watched many ComfyUI tutorials and encountered numerous errors and methods that didn't work. However, yours was flawless. Everything from the file organization to the installation guide and the detailed, easy-to-follow tutorial was perfect. I wish you all the best in your endeavors. Thank you so much!
i create better animations on my channel than AI "generates" 😎
This will work best when you can draw the poses and fill in mismatch frames your self also you can use exaggeration anticipation, animators are getting upset but actually they are the best equipped to make content, their works will be so much better than the non artist prompters, I hope more of them experiment and push this,
what animator has been upset about this
cringe, this is for larpers
@@bake-io1cf 50/50.yes , but also can save time if you are an animator and want faster results (for fan animations, or for fun, just draw keyframes, color them in, and don't have to color each breakdown and inbetweens, (only for simple animations like headturns, smaller movements,etc.)
@@tr1pod623 if you were a professional this would only make the end result worse without actually improving efficiency at all
@@tr1pod623 I'm in 3d animation for around 16 years now my Linked-in is sprawling with frantically anxious concept artist animators motion designers worried about jobs, the market is not great for them right now, which is not all to do with Ai but there have been some layoffs because of it. games industry contracting, also the writers guild strikes halting productions, tax breaks for media production being stopped, but also studios with very limited budgets are modifying pipelines for ai lowering staff hires, I'm currently in a 33 man team of animators which I know did not hire any more this past year because it was not deemed necessary despite us having more projects than before & deploying AI. it's especially bad for 18- 23 age bracket of less experienced animators.
What the anti-AI crowd don’t understand is that AI is simply a tool, it is not replacing artists or creators. But really at the core of most AI hate is that it is another tool that democratizes an art form that was had an expensive entry point in addition to a steep learning curve.
I'm getting less of that from the artists than the fact that generative models were trained on their copyrighted works under an assumption of "fair use" that is not yet legally tested. There's some gatekeeping, but most of it is that they're not getting paid for the use of their work to train the AIs in the first place.
There's too much black-box stuff going on. Bloggers are complaining that some models are live-scraping their sites, disguising their User Agents and ignoring robots.txt, and have proved it. OpenAI is not open about what was used in their training sets. It'll take another 3-5 years for any cases to progress to SCOTUS for a definitive ruling of what constitutes "fair use" for training for-profit AI models.
Essentially, too many creators of gen AI models are "getting rich" off of potentially illegally training their models to copy the work of artists whose works are being used for training without compensation. Even Adobe, which claims to work with artists for Firefly, is being accused of appropriating art off Adobe Stock for training without honoring an opt-out.
The biggest concern is whether you'll be able to trademark or copyright a character created with Gen AI. Last I read, the Library of Congress stripped an AI comic book of its copyright, then issued a new copyright just for the story and layout, but the art was not allowed to be copyrighted.
nah it’s not just a tool. i used to hire artists for my products and now i don’t. no need. ai is cheaper, faster and better than any artist working traditionally at this point. at least for digital art.
This is amazing. I am an artist and therefore wouldn‘t have an issue with those messed up frames or keyframes, the ai didn‘t do so well and just draw those myself. This just speeds up time so immensely. I always wanted to create an animated short film but the amount of work, I would have needed to perform, simply was way too much for my disabilities. With such tools and workflows I have hopes again. AI tools are such a godsend and help removing barriers. Either the barriers of not being able to draw or paint or whatever, or like in my case the barrier of partially paralysed hands, chronic pain and a severe fatigue. These are just amazing times.
What exactly are you trying to make?
Did you try this workflow ?
True, this is the first AI tool that could actually be helpful for real artists. It isn't really that useful for people with no animation background unless they think the animations featured in this video are good enough.
@@derrygorl Like all AI tools you should know what you are doing. Like a photo-camera doesn‘t make you a photographer-artist or the video App on your phone doesn‘t make you a movie producer. As an artist who faces some bodily challenges, I can tell you that those systems really helped starting with disco diffusion over two(?) years ago. „Real“ artists usually use everything to their disposal when creating artworks, at least those non gatekeeping ones, who take art serious and not put themselves on any sort of pedestal. I have seen just amazing animations using early stages of stable diffusion, but if you are looking for any one click solutions, you probably won‘t find it with this or other animation and video ai tools - to get them onto a level of midjourney it will take two or three more years, I assume.
@@NoPhilospher in the long run I plan of making an hand drawn animation of my hamster (I usually make pictures of Hamsters) and yes, I tried this workflow with some keyframes I drew. But it didn‘t work satisfyingly good, because my hamster design is quite specific and so this wasn‘t that successful. I guess I would first need to train the ai on my own works and then try again. Or I first use the 3D right of my hamster and then use this workflow to change the aesthetics towards my 2D style. I suppose in the end it will just involve all the tools I got to my disposal. 😅
Only problem is you dont own anything the AI generates unless you trained it yourself which means = People can legally profit off of your work since it isnt copyrighted.
Smartest kid on the block! I mean it! Your workflows are always so innovative and clever. Thanks again for another great demo of what can be achieved to create animated films.
Thank you so much!
@@mickmumpitz Hi please help me I lose the consistent character when I switch to the position of the perssonage yet I copy my positive and negative prompt use before
@mickmumpitz Dumbest kid on the block, I mean it... Your workflow is non-existant and uninspiring, Unappreciation for the first time for making such an unfulfilling demo of what weapons can be used to destroy the passion and creativity of humans.
i create better animations on my channel than AI "generates" 😎
Why is there so much hate on something that could be legitimately helpful for artists? This is just the same type of interpolation a lot of digital animation already uses but significantly more sophisticated. Someone who understands posing and timing could use this to phase out the tedious "tweening" process without utilizing puppet animation.
This is the sort of thing we WANT AI tools for. Lol
i create better animations on my channel than AI "generates" 😎
Animators have been using digital tools that speed up the workflow for years, so I don't see this as a bad thing for animators. For example a very popular tool in the animation industry would automatically fill in vectors for in between frames roughly and then the animators would fix the mistakes the software made and then move on. So I feel like anyone complaining about potential AI tools for animation probably aren't actually in the animation industry at all.
Or they never tried it for fun. I tried animating a lot of times in total just for fun and it took so long just to make 1 second of animation which was about 15 frames and that was with simple clothing and stuff, plus i'm not good at backgrounds so i cant design backgrounds that well. And everyone that says "just learn it" doesnt know a thing cuz to animate u have to have high art skills which is NOT SOMEthing easy to just "get" like what everyone pretends it to be. So its easier to just use ai
That's it, I'm moving over to Comfy
I think I'm about to do the same. And I hate Comfy...
Yeah, this video made me do it as well
i create better animations on my channel than AI "generates" 😎
This series of workflows is great! I have an anime-style music video that I want to create, and I thought it was probably going to be another year before the quality and temporal coherence of these tools reached an adequate level. This isn’t perfect, but it’s close enough that doing some touch-up in Photoshop becomes viable. Thanks again for figuring all of this out!
i create better animations on my channel than AI "generates" 😎
Not convinced the amount of work to set this up is worth it. Whats really getting me is the difficulty on posing the character. When you make a pose and render the image you are not guaranteed to get what you wanted, complex pose gets messed up with that 3d poser as to depth maps for the hands... thats alot of work for each and every pose you may want. When you can take that 3d poser and make 3d animations as you would in maya and then be able to apply any character to that reliably, and be able to tweak timing of animations add in or remove frames, then I think you have something. Until then keep up the good work.
"I want my character to be kind of like me" (prompt: Masterpiece, award winning). Gotta agree with that tbh
this AI tool is absolutely amazing! I can't believe we can actually create our own anime now! The tutorial is super helpful too.
One of the best tutorials I've seen in a while. Thanks a lot for creating all of this and sharing literally everything with us!
i create better animations on my channel than AI "generates" 😎
Damn! You are really pushing the whole nascent AI animation industry forward! Been following for a while and every video you come up with a more sofisticated approach! Congrats!
Finally. I don't have to draw the wholesome myself. Wohoooo.
Dude your intro is epic straight up
Well that was complicated. I wish this could all be done in one application.
Also, I’m still waiting to be able to use AI to create scenes with ‘multiple consistent characters’ interacting with each other.
While it's useless as a final product, for those unfamiliar with animation principles, particularly timing, it can be helpful to trace over the animation to fix consistency issues. For animators, it can speed up workflows, like figuring out the in-betweens needed to adjust the animation speed (for your sanity, keep it on twos, don't try to do 24 fps in ones with this process XD).
I'll definitely not use Tooncrafter in its current state, but I'll keep an eye on it for sure.
Thanks for this tutorial!
MAPPA BE NEEDING THIS BADLY!
Once again, amazing workflow, working smoothly for low gpu. you're the best
You know what, I am going to try this. Mess around with it a bit. Might not be perfect but the possibilities for creating proof of concepts with this intrigues me. It would give me something to do with all this writing that has built up over the years.
Very thankful to u, i really need this kind of video
Traditional forms of animation would be great for some scenes but it would definitely cut down on time for moments that are quite locked of or simple shots
And the staff needed as well
No this is awful lol
@@Tchbldd I mean it’s like 1 year old technology what do you expect?
i create better animations on my channel than AI "generates" 😎
amazing work. thanks for sharing!!
WOW!!!! Thank you so much!
Add MuseTalk to your workflow and you have lipsync to finalize it. Always enjoying your tutorials!
ai lip sync + ae face tracking would be perfect to the intro with the characters talking
so so good, thank you
What's the day! I learned new things to day
Your doing some Genius level SHIZZZ bruh thank you
thank you for making these workflows free, you could have easily pay-walled all this information so i do appreciate it much!
Super impressive! Really appreciate the information. Your workflows are some of the best I’ve used, if not the best.
I'm more interested in the tweens. That feature looks most promising. Not having to make walk cycles or tween poses could be awesome. I'm interested in using face tracking for emotions and mouths though could be a game changer
Ooooh and tooncrafter is apache license. Nice!
This is really awesome I could help you with a combiner program which would allow you to combine all those photo outputs onto a single sheet automatically
Hello and thanks for this tutorial! One question i have: Is it possible to go straight from selfdrawn keyframes into animation? Your answer, or maybe some hints, sources etc. would help me alot to realize the dream of an selfmade anime.
this is amazing, thank you so much for puting this all together! definitely worth a sub
Most amazing work i ever seen.. great job on this one.. 💪
Imagine how much this will help artists who can just fix a bit the main animation and get a masterpiece!
It can reduce the amount of frames needed to be drawn but I don't think we can just not do the in-betweens entirely since the thing still produces garbled frames.
I thought we were a year away from something like this. This is incredible
I would love to see what real animators/artists can do with this
Yeah man you are really smart, thanks for share what you neuron cook with us to cook better!!
Cool, but i do art and animate because i like it.not for the results but for the process,and its why all these AI methods don't feet me but nice vid 🔥
I'd rather do everything by hand rather than using AI. I believe in "hard work makes the product better" even if it hurts, through diligence and patience. I'm not saying this is wrong, I just like doing stuff traditionally instead of having to rely on tech like AI.
I was hoping you would release this one ! Just started watching but it looks promising 🤩🥰
I think you'd get better results animating in 3d and using AI img2img to convert it to 2D. You'd skin half these steps.
Love you brother. You are awesome :)
Great Video, I love the mixed media approaches you are working with here, its fantastic. One thing that still stands out to me is all the steps in the sausage factory you still need to get results. I beg to question why wouldn't someone still work in a more traditional animation manner to create something without maybe some of the quirks? Regardless, the final effect you achieved is awesome, I just feel like if you're young watching this and diving into all this tech, maybe also learn toonboom or maya as well. It will only serve you well when mixing with comfy,etc..
love your content. Always something interesting ❤
Thanks for making this video🙃
the camera movement, if the camera movement can remain the same, or controlled, for example stop it from zooming in/out or panning (unless speceifiec) the animation would be better. Another thing, animation smear, I think the keyframes that one puts as an input if they are too far apart causes more noticible animaiton smearing. Smearing is nice if used correctly, specially in higly dynamic action scenes, but in calm slow scenes it looks off. I think maybe adding either more keyframe for slow scenes, maybe not more keyframes but psace them aout accordingly. its gonna be an iterative test until we figure out how much 'time' or 'frames' is best to put as reference
This is insane! I've always wanted to make my own anime, but my drawing skills are basically nonexistent. This workflow seems like a game-changer, even if it means spending way too much time tweaking prompts. What do you guys think, is this the future of animation or just another AI fad?
i think there will be more to it. this is obviously a workflow that will be iteratively improved upon however i feel like 3d models will have something to do with the craft, like youl generate an image, then use a workflow like this to get different angles, then make a 360 video, then gausian splatting to get a near perfect 3d model with perfect textures, then auto rig and animate, then tell ai what you want from the videos and it will use the model and rigging to get perfect outputs with zero errors, not even extra strands of hair or limbs,. something like that i reckon, and eventually itl be all behind the scens so u just generate an image and ask for the video
amazing thank you, ill be sure to look into this soon
This is really cool!!!
Sibal... It's really amazing
Thank you for sharing this workflow! Do you mind sharing your PC configuration and how much time it took in total to complete this roughly?
Nice job!, thanks for sharing
Finally we can fix the battle between Escanor and Meliodas
awesome brother
ive been on it for about a week i have a dope workflow that creates some great art
"art" lmfao
@@j.2512
@RiiahTV
0 seconds ago
@j.2512 what does art mean to you? if you dont mind me asking you the definition. to me art is how humans use tools to express their thoughts. i believe people like yourself fall in love with the tool itself. and forget that at one point the tool that you use for art was once looked at like it wasn't. remember this "there once was a finger painter in a cave, a man came with a paint brush and he hated how it didn't do what his hands could do. there was a painter painting a photographer comes and takes a picture of the woman. the painter didn't like how he couldn't control the camera like he could his paintbrush. the photographer was taking pictures a man with a reel begins taking multiple images to make film. the photographer didn't like how he had to put together images to make movement. the videographer and the photographer are working together now and a guy with a computer shows them photoshop. they call it blasphemous. it's not real photography. a guy that uses videography and photoshop is doing his work when a person that uses an animation program shows him what he's capable of without any physical tools like a camera. the guy with the cam like real footage and really getting out there to capture real settings. the animator meets ai. the animator embraces change because animators know when new tools are introduced it only means progress in art. young blood remember artists use tools to create art. just because your not smart enough to use a hammer doesnt mean some one cant grab a chisel and make an ice sculpture of mona lisa. wake up are is everything. art is perspective. art is life. you are a blackhead on the face of idiocracy.
At least those tools didn't need to be trained on works of art of real artists without permission and proper compensation. Those tools you mentioned didn't have to be fed existing art in order to produce another!
@@derrygorl there goes that arrogance. i create my own checkpoints
with my data i create
Stable diffusion plugin for krita is also very helpful it's come a long way.
wow, really cool!
Dude! For me, this was like the 'Holy Grail!' Bless up, good sir! Thank you!
for the untalented hack is the holy grail
@@j.2512 Good thing I'm not. For the ignorant, grammar is whoopin' yo ass...
That's great! Are you selling a course on how to set all this up and how to work with it? I want to learn it. :-D
really coolll!!!! I love it!!!thanks for sharing!!!
I totally agree! There's no reason Professional animators have to exist now. 😁
you suck
Just wow!
I seriously need to relearn how to use comfyUI soon :3
amazing work
wow tht´s sooo cool!!! Thansk fot sharing!!
interesting thanks ^^
This is a very interesting showcase of the cutting edge of AI applied to animation.
However, given the massive room for error & need to learn a nee program, I'm not sure it's currently worth it to spend the time learning this v.s. spending the time improving your skills & using proven tools like Mojo for easier 2d animation in the long run.
First off, thank you so much! You made it so simple to install and to play around with it.
My first results show up as images without much animation between, character moving lips then jump to the next image. Any idea what I may be missing here?
Reporting back after more testing - So I managed to get the animation to come out! Just chose images that look more similar to eachother. My first tests were too different key frames so it didn't even try to animate between them. I would like to experiment to try and 'force' it to interpolate even if the keyframes are very different (like getting one character to turn into something else)
Didn't have much luck with the upscaling workflow probably because I am not using an sdxl model. Any idea how to adjust it for sd1.5?
Got this error when executing the tooncrafter workflow, it happens when it passes through tooncrafter interpolation node: "Error occurred when executing ToonCrafterInterpolation:
No operator found for `memory_efficient_attention_forward` with inputs (...)"
how everyone is saying this is good, when the hands are always ruined. proportions of the body suffer too. it is so far away from the production-grade animation, that I don't understand whom it is for.
I am very bullish on the AI assistance tools for technical work in animation pipelines, like inbetweening or coloring, but this would require a clear process of how an animator can edit and improve on the generated images and clean up all the artifacts easily. as soon as it is easier that drawing these shots from scratch, this becomes a viable production tool for animators.
Thanks for the info
Can I suggest using something like FlowFrames to do the final clean up of interpolation? Maybe it is better to have less frames per second using your method and then interpolate the remaining frames(15 to 25 for example or 25 to 60) with software really dedicated to this. There is also paid software namely video ai 5 but it's expensive.
Always love your vids @mickmumpitz even when you were making sketchy blobby 3d chars. There are similarities to the way sketch animation on paper works, but the ai is filling in the blanks
Wow, you are smart an you know how to use alle the AI tools toghether
Could any of this stuff be used to make a vtuber model? If so which programs would you suggest? If not what would you suggest?
Wow amazing!
This thing is going to f*cking up animators and artists😢 damn it
yes damn it, but hope it wont get as good as real animators and artists do😔
When animators/artists take it on I think it’s gonna be the other way round. Those without drawing skills will be left in the dust
@@animationbydreamsketch It already did, bruh
@@dotayanim8 to me, nope
Make an anime show using this workflow
Guys, I have an easier workflow !
Instead of downloading, posing, arranging the poses, transforming yourself into ai, arranging the flows...
You can just open procreate and draw it yourself .
Великолепно, наконец я нашел что искал!
so nice. tks for sharing
Beautiful ❤
Hey man, that's amazing, would be great to see a short animated story via this tool. Any plans for this?
Hey all, I am a game developer and I stumbled upon this video. To make a 2D fighting game like Mortal Kombat or Guilty Gear, one could potentially create the model sheet in ComfyUI and then then the various poses in Open Pose AI. Then, in Unity you could just create the animations, VFX, juice etc. to get it all working and feeling like a completely original fighting game. Is anyone interested in connecting on Discord to go through this and collaborate on a project like this? I have about 4 years of experience working in Unity for a few games that are live and in production. I am really interested in diving into this, but would love to do it with a team!
I'm using the anime character model sheet and I can't seem to get it to follow my hair style prompts. It always seems to give me a very similar style, I'll put: ((short messy hair)), and it'll give me medium, typical anime hair. If the style changes, it's never short and for the multiple angle headshots, the hair is nearly always the same no matter what. Changing through the seed didn't help
Make full anime show using this method.
Great work! I think you forgot to add installation guide!
Working on it, give me a few more minutes haha
Incridible! Can i modify this to use a premade character without the "prompt" influence? it kinda mess up my input images
Excellent video, thank you for sharing.
My art style is kind of like Invader Zim. I wonder would it be possible for me to create a model sheet in that kind of style, and then shoot my own video reference footage.
I would like to think regardless of model style it should still work well.
Hope to experiment this weekend, and I'll find out I guess
Hey mate - great video! I was curious if you know any websites that have a filter or can convert a long form 5-10 minute video from real life Podcasters to anime in good quality? Starting an AI Podcast, and all the tools I've found only seem to do quick 10 second or under 1 minute videos - thanks!
anybody else getting an error message during the pose step? I can't generate the character poses for some reason. The load ControlNet Model Nodes under the Character BG section are red and the process stops
Lowk after learning to draw I think that would be easier and more flexible
can we run this on google collab? please can you check that?
Yes
Would be cool to have this as colab workflow
Thanks
Your video are Amazing, i would like to ask you a question. Is it possibile to generate the model sheet of the character without using the prompt? For example if i draw a character myself in front view, is it able to create the rest of the model?