This is very cool. That is how I imagine working with AI. Writing a prompt and hoping for the best doesn't excite me. Directing the AI is where it is at! Thanks for the video and resources!
The biggest observation I made was how well you transition from a singular to an inclusive perspective. It really makes me feel like I am a part of a Community.
if your having trouble finding freestyle, go back too the setting he set to standard just before that, at 3:06. make sure freestyle option is checked above that. then freestyle options he uses later will show up.
This is the way - the tricky part is temporal consistency. You can obtain it by breaking down your movement into parts, train motion LORAs and match them to the final output using a schedule.
If it ever learns to finally stabilize and actually concentrate on keeping a real, consistent shot without so much warping designs, it might finally be of some use as a tool for indie creators.
I went to do this when I realized you could put 'None' for the preprocessor and use your own depth images, but was a little surprised how hard it was to get a depth image from Blender. The Map Range node idea is new, as well as the Freestyle mode for Canny nodes, which I've never seen before in any tut. Thank you for creating such useful SD x Blender content! I laughed out loud when you said ComfyUI was easy to install. Maybe easy for a genius like yourself... Then again, it's probably easier to use than Deforum, but I like Blender -> Deforum -> Video AI -> Resolve for this sort of thing, as Deforum has a tools for controlling keyframing changes across time, interpolation and diffusion from frame to frame, like color coherence and frame blending. Also, the new Forge version is super fast.
Just a minor suggestion on your workflow… I would pass the end result as a latent on another ksampler with really low denoising to improve the final comp… Also maybe sd1.5 animatediff with lcm is a more interesting approach for your followers since it’s lower bandwidth, better consistency, better controlnets etc
It would be nice to have a 'temporal coherence' checkbox in comfy that would force it to keep things consistent over the length of the video and not be so random.
I like the speed and versatility that this Workflow using AI offers, but knowing and being able to do everything myself is more satisfying. This method can be used more in an abstract sense, in that it doesn't matter as long as it looks good, but it can't be used to get very specific results, well, it can, but it can take a long time to get the exact “Shader” of that we need instead of using a procedural or even hand-painted one. Furthermore, AI art is not really art and before the haters start commenting, think about this argument: If you go to a pizzeria, order a pizza and start taking out ingredients or adding extras, does that make you the cook? No, and by that same logic, going to a website or an app and asking for or removing “ingredients” that you want or don't want to see in an image doesn't make you an artist and generating images with AI shouldn't be called art. AI is a good aid tool and should not be used to overload the market and artists' websites such as ArtStation, which there was a huge protest some time ago on this exact subject.
Art isn't a pizza. Art (from the American Heritage Dictionary): "The conscious use of the imagination in the production of objects intended to be contemplated or appreciated as beautiful, as in the arrangement of forms, sounds, or words." Does that definition apply to AI art? I would say so. You can try to redefine the term "art" all you want, but at the end of the day, my definition of art comes from the dictionary, and yours exists in your head. It's very true that AI art is not completely original. But the thing many fail to realize is that so is just about everything else. Hell, one of the most famous paintings of all time is a can of soup. At the end of the day, all you're doing is shooting yourself in the foot. AI is here to stay, and could probably be extremely useful to artists if they let it. But instead, they've chosen to throw a hissy fit. It's really a shame. "AI is hurting arists ability to..." yeah, until a "real artist" is using AI, and then the art community starts attacking them. It's honestly sad.
@@bbrainstormer2036"imagination", therefore no, under the narrow definition you posited, Ai generated images do not fit it. They have no living author, you can't reduce the creative process to the abstractions of gradient descent and backpropagation. It ain't no tool by default: it can be used as one, but it can also be used as automation. Within the market of capital and attention, the later has infinitely more of an incentive advantage than the former, so people using it as a "tool" will find the web scape completely saturated with fully automated content. Read Heidegger on technology. And remember "technology is a useful tool but a dangerous master", considering the lack of meaningful input in ai generated content, it falls more into the later, the user is far more used than he uses.
@@BinaryDood Just because the latter, to use your explanation, exists, doesn't mean that the former somehow doesn't or should be ignored. And your point about "incentives" is confusing, when lots of people don't make art in the hopes of some external reward, instead making it simply because they want to be creative.
@@bbrainstormer2036 indeed, and those people share the same world as those with extrinsic incentives, including resources. Stuff the individual can never be completely separate from. And since AI targets every field, it's not unfathomable to think too many will be distituted, their own willingness to create genuinely being what deprives them of what is deemed productive. This does not create an environment for people to be educated on intrinsic motivation and positive liberty, hence, being molded by a socioeconomic sphere of narrow and short term reward functions: not the stuff which feeds creativity, but which clogs it.
@@BinaryDood At this point, it's a red herring. Whether AI will have a positive effect on art as a whole (which seems to be the point you're making here) is very different from claiming that the use of AI disqualifies a work from being art. I'd also push back against the arguments you've made, but honestly, I don't feel like spending this much time on a red herring
Been working very hard to work with blender and understand it. As a 3d artist, as a short film writer, as an animator… then all this “AI does it for you and does it better” BS comes along. Feels like a huge slap in the face. Worst part is that I don’t understand it. Like… At all. Reply 💯 if you feel me 😔
I cant tell you how to feel, but my suggestion is that you add one more hat, that is director. AI is as good as its training data, and the person using it.
Everything I'm seeing needs to be fixed by humans in the final product and all of it has that 'dream state' A.I. look about it. Ultimately this video shows me the power of A.I. speeding up the traditional workflow process for conceptualization, however it doesn't look like we are anywhere near the point this is going to replace traditional artists. I say, stick with it. Learn the traditional methods as Blenders long term plan is to start implementing a lot of this stuff natively to help artists create more art faster. In the end, it will probably just end up being another tool in the tool box that lets you speed-ball ideas quickly, so you can eliminate bad ideas quickly, but ultimately the hard work to finalize everything will still need to be done by humans and that might be true for a long, long time.
@@reasonsreasonably Last time I post anything like that on UA-cam. But thankfully I found out how limited AI is in its current state when it comes to these sorts of things. I posted this a while ago and my current animations make this one look like a 3rd grader did it. Yeah, I get that you were trolling but still, what you said holds some truth. AI will eventually get to that point and I will eventually have to learn it. But as I revisit this video and your post I’m quite proud of the fact that my work now looks rather professional and this looks like another “choppy, hard on the eyes AI driven mess”. AI is good for some things, but animation isn’t one of them yet. I’m nearly done producing a web series that I will happily give you the link to when completed. Have a good day, friend 👍
Of course yes, it applies to literally everything and its inevitable. But... sooner you start learning and embracing it, the bigger advantage you will have :)
@@MrFrost-xh6rf seemed like the first thing they went for was art, and I'm surprised how quickly it got good at advanced 3D art. I admit I used meshy to create a strawberry shortcake model for me when I needed a food model. Can you imagine drawing realistic food in blender?
ComfyUI Manager wasn't working until I put the extracted folder ComfyUI-Manager-main into the folder ComfyUI_windows_portable/ComfyUI/custom_nodes. I think it might be good to adjust the instructions on this point. Looking forward to playing with it!
This was fantastic! Super inspiring. I don't use Blender, but the CONCEPT is what I needed. I'm sure there's got to be a way to make those render pass videos from within comfy from one video and not have to use image sequences. The segmentation of the elements and being able to prompt each of them separately is what I've been trying to find a simple demonstration of! Thanks!
2:50 the correct way of outputting passes like zdepth is to render image in linear format! not srgb, you set it in color management rollout panel. thanks for the tutorial!
Amazing gift my friend thanks à lot. I find if you use the view render from wireframe view and change the color setting, you win time (also i didn't manage to succes with freestyle/line render on 3.6) Thanks you a lot Mr Mumpitz !!
90% will not be needed anymore. Because 98% of the people don't care if a artist made it or AI. Apple, Google , Amazon will all come with a AI cloud thing. Where you can make games, movies, images what ever in a simple click.
Wow this is amazing. so it doesn't mind coloring outside the lines (so to speak) I noticed the generation doesn't exactly match the alpha of the RGB mattes. Good to know! Keep it up!
Incredibly great work, dear Mick! Your video edits alone are evidence of detailed diligence and precision. One of the most amazing channels in the UA-cam ocean - fun to follow your workflows. Unfortunately - super ambitious and probably still too time-consuming for most enthusiasts. But - on a weekly basis - technology is evolving. The question is probably the skillful use and intellectual penetration of this potential. My sincere admiration for your perseverance, your diligence and the excellent presentation of your results! Ultimately, that is what it is: the optimization of the interface between "imagination" and the "digital world". Thank you!!
I've been hoping someone would make an AI that does this because it would a couple problems. The big two: 1 this AI does not use one prompt for the entire scene. That means you get a dog boy in a red jacket running in the woods, not a red jacket-dog-boy in a red dog boy jacket running in the red boy dog woods. Even the best single prompt AIs I have used use the same prompt for every part of a picture. This is probably why even the best AIs I have used sometimes produce hideous mutant monsters even with simple prompts like your request for an anime girl resulting in a woman with a second face in her chest. 2 using the 3D models I not only would be able to designate objects within the scene but have multiple characters in the scene and each character can have a full description without their apearances blending together as per the first point. I have wanted these two features since AI art aps first started flooding the internet. Some honerable mentions; AI I've used have struggled to understand certain anatomical concepts like "tusks" but with this the existence of the tusk is practically baked into the code. This isn't a payed website ap but a worklow on my own computer that I'm totally going to try.
My comfyui does not run the mask preview node. For some unknown reason, I'm going to turn off the preview node and try to work with it. Thanks for sharing such a nice tutorial.
Awesome! I already thought about this, but you have finally done it ... It works quite well, but the flickering is this there. You may have to integrate animation workflow like animateDiff or something. The next step is to ask a LLM to code a Blender script or addon to automate the export of frames to a Comfy worlflow ;)
@@sams3493 This wont be enought, LoRAs are good for several still images and to have a character (or anything) consistency, but you can acheive this with IPAdapters too nowadays... Here the probleme is a temporal coherence between each frames and a video model is needed (animateDiff, SVD, ...) but I don't know exactly how to plug this with frames coming from Blender
An error message appears when importing color mask and depth map sequence frames: Error occurred when executing VHS_LoadImagesPath: No files in directory 'C:\tmp\color'. File "E:\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute What might I have done wrong?
You need to change values in the every node - "Load Images (Path)": skip_first_images - "0" (this count means, that you start generation from first frame in you sequence, it can be start from any frame you want) select_every_nth - "1" Also set yor frames count in the node "ImageLoadCap" - at first to "20", for a test. And change the resolution: higher resolution - longer time of waiting.
@@AxiomXXXliterally the only purpose for it right now is ideation and even that is kinda narrow especially when you actually have an idea in mind it’s only really good for exploring ideas you would have never thought of otherwise. The funny thing is non-artists don’t even know how to use it and I don’t blame them it’s pretty hard to control and they have no idea how to construct an image in the first place and have never thought of the variables so they basically just spray and pray and cherry pick whichever ones it spits out that they like
@@SwoleKitchen everyone knows how to use ai to generate images. The problem is not that they don't know how to use "ai art". It's that they don't know hot to use art. These people are not needed by the industry and no one cares about their brainfarts. I mean prompts.
This is wonderful. I’m actually an illustrator who would like to aggressively speed up my workflow by putting my own designs in and using 3D models to generate (largely finished, line art only) images that I can then go on and tweak by hand for finishes. How would I, instead of pulling these prompts from just the general Ai system, use my own art work as the…Lora? I think it’s called? Do you have a tutorial on that using this same workflow? The workflow is perfect, but I just need an ability to upload my own pencils and inks. Thanks!
Blender has had an ai render plug in for a year now. It's called stable diffusion. You have to pay to use the ai renderings. You start with x amount of credits, after used..you pay for more.
Supporting you on Patreon is there also a file where there are more than 4 masks? Sorry I am thinking a bit crazy, like 40 for a complex scene 🙈 Probably I could take some time to set it up... My inital thought: It would be very cool to do this per object. The AI style kind of the material per object.
Oh yes, a normal pass would work fantastically. I have actually tested this with SD 1.5. The problem is that there is no "normal" control net for Stable Diffusion XL yet. The videos generated by SD1.5 were extremely coherent, but unfortunately also pretty ugly. So I gave up on it and focused on SDXL for this video. But as soon as there is a control net for it, this workflow should work even better
Hey Mick, great video! I've been learning Blender for a while and I'm interested in trying your approach of combining it with AI. I'm planning to build a new PC for this purpose. Do you mind sharing your PC's specifications? It would be helpful for me to know what kind of hardware can handle this type of workflow.
You made the pre-rendering process way harder than it should be. I've been doing this exact thing with a single render pass and deforum. The resut is just as inconsistent so using an outine and a depth map is pointess because there is no benefit to it (At this point you might just feed it a recorded video). My take is that until AI reaches the Sora level of frame consistency there is no point in using these flows, for anything that isn't abstract visuals at least. Also having to export/import frames from one soft to another is brainrotting, given how poor the result is.
Hello, after I drag the workflow to Comfy, I go to "ComfyUI Manager -> Install missing Custom Nodes." but do not see an option to install missing Custom Nodes. Any suggestions? THANKS.
If I’m not mistaken, the blender bit can be removed entirely, no? Can’t you do the same separation in photoshop with an image? Or after effects with a video?
we did there called custom loras. this guy just showed you a work flow without using a custom lora. you want a specific character make a lora of one, you ewant a specific building make a lora for one, you want a certain water make a lora for one, you want a specific robot octopus make a lora for one. it will be as consistant as your lora work is
hello. looks cool, but only the question if for each masked aread was generated separate image, and the it was just combined togetether, or ComfyUI can understand masks and promts on this masks and combine them in single generation?
Man if you could get consistent character i would be sold. I managed to do th same exact thing just using pika and runway ai and animating models in unity.
But you can! Use the same prompt for the character in every scene. Create one image of your character (full body or face). Load it into the ipAdapter and connect the mask for your character into the "attn mask" input in your ipAdapter. ...I should make a video about this haha
@@mickmumpitz if you could that would be great becauee the one thing i neee is consistency in the character models. One other thing i managed to do was taking a sub par 3d model and passing it through krea ai, it makes the character super nice then combing frames from unity into that to out put a nicer imagr
I can't remember you. But the only video which was similar was about a woman in a kitchen and some ogre, which was about creating a movie using only AI. If that was you, you came far very quickly.
Hey, this is absolutely amazing! I'm really looking forward to the incredible results we'll see with Blender and AI working together in the future. Just think about the endless possibilities for VR environments (Omniverse) - it's going to be a blast! And imagine AI-driven SFX for various renderings. It's like giving multipass rendering a supercharge! 😄
when hitting 'que prompt' it throws a ton of errors. It woudl be great if you could go over how to solve those. I find that's the biggest issue of comfy. Downloading and install missing models etc for %70 of the time.
This is very cool. That is how I imagine working with AI. Writing a prompt and hoping for the best doesn't excite me. Directing the AI is where it is at! Thanks for the video and resources!
Hmmmm.. do I bookmark this under "AI" or under "Blender"?
ahh 😂
Ha ha! The same for me!
Both! ;)
YES!!😂
The answer is Yes
Insert “Why not both?” Meme
The biggest observation I made was how well you transition from a singular to an inclusive perspective. It really makes me feel like I am a part of a Community.
if your having trouble finding freestyle, go back too the setting he set to standard just before that, at 3:06. make sure freestyle option is checked above that. then freestyle options he uses later will show up.
The knowledge you make with blender might actually be around and functional in a decade or two
This is the way - the tricky part is temporal consistency. You can obtain it by breaking down your movement into parts, train motion LORAs and match them to the final output using a schedule.
is there a particular tutorial that shows this method?
Wow very cool. Also love the way you just did a separate render with flat emmissive materials to Roll your own version of Cryptomatte !!! Brilliant
It's so crazy how advanced this stuff is getting.
This really seems like the future of 3D work flows
If it ever learns to finally stabilize and actually concentrate on keeping a real, consistent shot without so much warping designs, it might finally be of some use as a tool for indie creators.
I went to do this when I realized you could put 'None' for the preprocessor and use your own depth images, but was a little surprised how hard it was to get a depth image from Blender. The Map Range node idea is new, as well as the Freestyle mode for Canny nodes, which I've never seen before in any tut. Thank you for creating such useful SD x Blender content! I laughed out loud when you said ComfyUI was easy to install. Maybe easy for a genius like yourself... Then again, it's probably easier to use than Deforum, but I like Blender -> Deforum -> Video AI -> Resolve for this sort of thing, as Deforum has a tools for controlling keyframing changes across time, interpolation and diffusion from frame to frame, like color coherence and frame blending. Also, the new Forge version is super fast.
should I use Deforum for cycles animation passes? I totally failed with eevee and could not even manage to add missing nodes in ComfyUI 😅
Just a minor suggestion on your workflow… I would pass the end result as a latent on another ksampler with really low denoising to improve the final comp…
Also maybe sd1.5 animatediff with lcm is a more interesting approach for your followers since it’s lower bandwidth, better consistency, better controlnets etc
Absolutely. Mind blowing. Bravo. Man. Bravo.
This method seems great to create some NPR style squences. That last one with the forest and the moss looks amazing at 9:59
This channel is an absolute gem!
It would be nice to have a 'temporal coherence' checkbox in comfy that would force it to keep things consistent over the length of the video and not be so random.
That’s exactly what animatediff tries to do… it’s improving a lot lately
Yah not quite mind blowing yet
one of those great videos that you found once in a decade on youtube
I like the speed and versatility that this Workflow using AI offers, but knowing and being able to do everything myself is more satisfying.
This method can be used more in an abstract sense, in that it doesn't matter as long as it looks good, but it can't be used to get very specific results, well, it can, but it can take a long time to get the exact “Shader” of that we need instead of using a procedural or even hand-painted one.
Furthermore, AI art is not really art and before the haters start commenting, think about this argument:
If you go to a pizzeria, order a pizza and start taking out ingredients or adding extras, does that make you the cook?
No, and by that same logic, going to a website or an app and asking for or removing “ingredients” that you want or don't want to see in an image doesn't make you an artist and generating images with AI shouldn't be called art.
AI is a good aid tool and should not be used to overload the market and artists' websites such as ArtStation, which there was a huge protest some time ago on this exact subject.
Art isn't a pizza.
Art (from the American Heritage Dictionary): "The conscious use of the imagination in the production of objects intended to be contemplated or appreciated as beautiful, as in the arrangement of forms, sounds, or words."
Does that definition apply to AI art? I would say so. You can try to redefine the term "art" all you want, but at the end of the day, my definition of art comes from the dictionary, and yours exists in your head.
It's very true that AI art is not completely original. But the thing many fail to realize is that so is just about everything else. Hell, one of the most famous paintings of all time is a can of soup.
At the end of the day, all you're doing is shooting yourself in the foot. AI is here to stay, and could probably be extremely useful to artists if they let it. But instead, they've chosen to throw a hissy fit. It's really a shame.
"AI is hurting arists ability to..." yeah, until a "real artist" is using AI, and then the art community starts attacking them. It's honestly sad.
@@bbrainstormer2036"imagination", therefore no, under the narrow definition you posited, Ai generated images do not fit it. They have no living author, you can't reduce the creative process to the abstractions of gradient descent and backpropagation. It ain't no tool by default: it can be used as one, but it can also be used as automation. Within the market of capital and attention, the later has infinitely more of an incentive advantage than the former, so people using it as a "tool" will find the web scape completely saturated with fully automated content. Read Heidegger on technology. And remember "technology is a useful tool but a dangerous master", considering the lack of meaningful input in ai generated content, it falls more into the later, the user is far more used than he uses.
@@BinaryDood Just because the latter, to use your explanation, exists, doesn't mean that the former somehow doesn't or should be ignored. And your point about "incentives" is confusing, when lots of people don't make art in the hopes of some external reward, instead making it simply because they want to be creative.
@@bbrainstormer2036 indeed, and those people share the same world as those with extrinsic incentives, including resources. Stuff the individual can never be completely separate from. And since AI targets every field, it's not unfathomable to think too many will be distituted, their own willingness to create genuinely being what deprives them of what is deemed productive. This does not create an environment for people to be educated on intrinsic motivation and positive liberty, hence, being molded by a socioeconomic sphere of narrow and short term reward functions: not the stuff which feeds creativity, but which clogs it.
@@BinaryDood At this point, it's a red herring. Whether AI will have a positive effect on art as a whole (which seems to be the point you're making here) is very different from claiming that the use of AI disqualifies a work from being art.
I'd also push back against the arguments you've made, but honestly, I don't feel like spending this much time on a red herring
Been working very hard to work with blender and understand it. As a 3d artist, as a short film writer, as an animator… then all this “AI does it for you and does it better” BS comes along. Feels like a huge slap in the face. Worst part is that I don’t understand it. Like… At all. Reply 💯 if you feel me 😔
hi
I cant tell you how to feel, but my suggestion is that you add one more hat, that is director. AI is as good as its training data, and the person using it.
i feel that too now, and this shit is confusing lmao
Everything I'm seeing needs to be fixed by humans in the final product and all of it has that 'dream state' A.I. look about it. Ultimately this video shows me the power of A.I. speeding up the traditional workflow process for conceptualization, however it doesn't look like we are anywhere near the point this is going to replace traditional artists. I say, stick with it. Learn the traditional methods as Blenders long term plan is to start implementing a lot of this stuff natively to help artists create more art faster. In the end, it will probably just end up being another tool in the tool box that lets you speed-ball ideas quickly, so you can eliminate bad ideas quickly, but ultimately the hard work to finalize everything will still need to be done by humans and that might be true for a long, long time.
@@reasonsreasonably Last time I post anything like that on UA-cam. But thankfully I found out how limited AI is in its current state when it comes to these sorts of things. I posted this a while ago and my current animations make this one look like a 3rd grader did it. Yeah, I get that you were trolling but still, what you said holds some truth. AI will eventually get to that point and I will eventually have to learn it. But as I revisit this video and your post I’m quite proud of the fact that my work now looks rather professional and this looks like another “choppy, hard on the eyes AI driven mess”. AI is good for some things, but animation isn’t one of them yet. I’m nearly done producing a web series that I will happily give you the link to when completed. Have a good day, friend 👍
Guess I have to learn this if I am going to be able to live and keep my job.
Well, you'll need to learn SOMETHING new. This is going to be old news pretty soon I'd think.
I wish they would keep Ai out of art too..
Of course yes, it applies to literally everything and its inevitable. But... sooner you start learning and embracing it, the bigger advantage you will have :)
@@MrFrost-xh6rf seemed like the first thing they went for was art, and I'm surprised how quickly it got good at advanced 3D art. I admit I used meshy to create a strawberry shortcake model for me when I needed a food model. Can you imagine drawing realistic food in blender?
i hope you undertand that this is all just alpha stage software and workflows and you cannot keep up with the pace of ai advancements in the end.
Awesome video 😃👍
I am very excited to try this out! 😃
That's what I also thought about... AI with control 😊 Thanks for sharing!
Amazing work, thank you for sharing! Does this workflow exist for Mac or only PC?
very powerful tips and workflow
Unglaublich!! :D so so nice danke für deine filme und der tollen inspiration!
ComfyUI Manager wasn't working until I put the extracted folder ComfyUI-Manager-main into the folder ComfyUI_windows_portable/ComfyUI/custom_nodes. I think it might be good to adjust the instructions on this point. Looking forward to playing with it!
This was fantastic! Super inspiring. I don't use Blender, but the CONCEPT is what I needed. I'm sure there's got to be a way to make those render pass videos from within comfy from one video and not have to use image sequences. The segmentation of the elements and being able to prompt each of them separately is what I've been trying to find a simple demonstration of! Thanks!
there is a node called Oneformer Coco Segmenter, which colors different objects in the video and then you can use a mask by color node
2:50 the correct way of outputting passes like zdepth is to render image in linear format! not srgb, you set it in color management rollout panel. thanks for the tutorial!
Amazing gift my friend thanks à lot. I find if you use the view render from wireframe view and change the color setting, you win time (also i didn't manage to succes with freestyle/line render on 3.6) Thanks you a lot Mr Mumpitz !!
I've been saying this since last year- this is going to be the render pipeline of the future.
It's amazing but scary, this might end up putting a lot of lighting artists, comp artists and rendering artists out of work very soon.
90% will not be needed anymore. Because 98% of the people don't care if a artist made it or AI. Apple, Google , Amazon will all come with a AI cloud thing. Where you can make games, movies, images what ever in a simple click.
The only jobs not in danger from AI are on the forefront of science... Everybody else is going to get wrecked.
not quite ready for prime time but cant wait to see when it gets there
Have you picked up on the excitement surrounding VideoGPT? It's reshaping the landscape of video creativity.
The the short really captures the feeling of being chased in a nightmare
With same amount of time I’d create a serious good render. It can be useful as concept generator.
Did you used openAi api? Can't understand why I have terrible results
Wow this is amazing. so it doesn't mind coloring outside the lines (so to speak) I noticed the generation doesn't exactly match the alpha of the RGB mattes. Good to know! Keep it up!
Absolutely incredible video. I've never subscribed to someone's Patreon faster. Great job
Bruh... this is godlike
Incredibly great work, dear Mick! Your video edits alone are evidence of detailed diligence and precision. One of the most amazing channels in the UA-cam ocean - fun to follow your workflows. Unfortunately - super ambitious and probably still too time-consuming for most enthusiasts. But - on a weekly basis - technology is evolving. The question is probably the skillful use and intellectual penetration of this potential. My sincere admiration for your perseverance, your diligence and the excellent presentation of your results!
Ultimately, that is what it is: the optimization of the interface between "imagination" and the "digital world".
Thank you!!
I could see this being used for independent artists music videos. Or media where less control is needed.
This is amazing. keep it up!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
Wow, nice workflow.
I've been hoping someone would make an AI that does this because it would a couple problems. The big two: 1 this AI does not use one prompt for the entire scene. That means you get a dog boy in a red jacket running in the woods, not a red jacket-dog-boy in a red dog boy jacket running in the red boy dog woods. Even the best single prompt AIs I have used use the same prompt for every part of a picture. This is probably why even the best AIs I have used sometimes produce hideous mutant monsters even with simple prompts like your request for an anime girl resulting in a woman with a second face in her chest. 2 using the 3D models I not only would be able to designate objects within the scene but have multiple characters in the scene and each character can have a full description without their apearances blending together as per the first point. I have wanted these two features since AI art aps first started flooding the internet. Some honerable mentions; AI I've used have struggled to understand certain anatomical concepts like "tusks" but with this the existence of the tusk is practically baked into the code. This isn't a payed website ap but a worklow on my own computer that I'm totally going to try.
Wow! Amazing workflow that you worked out here! Thanks for all the inspiration!
My comfyui does not run the mask preview node.
For some unknown reason, I'm going to turn off the preview node and try to work with it.
Thanks for sharing such a nice tutorial.
Awesome! I already thought about this, but you have finally done it ...
It works quite well, but the flickering is this there. You may have to integrate animation workflow like animateDiff or something.
The next step is to ask a LLM to code a Blender script or addon to automate the export of frames to a Comfy worlflow ;)
Maybe also create a LORA (or whatever, I'm new to this) for more consistant subjects
@@sams3493 This wont be enought, LoRAs are good for several still images and to have a character (or anything) consistency, but you can acheive this with IPAdapters too nowadays...
Here the probleme is a temporal coherence between each frames and a video model is needed (animateDiff, SVD, ...) but I don't know exactly how to plug this with frames coming from Blender
An error message appears when importing color mask and depth map sequence frames:
Error occurred when executing VHS_LoadImagesPath:
No files in directory 'C:\tmp\color'.
File "E:\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute
What might I have done wrong?
You need to change values in the every node - "Load Images (Path)":
skip_first_images - "0" (this count means, that you start generation from first frame in you sequence, it can be start from any frame you want)
select_every_nth - "1"
Also set yor frames count in the node "ImageLoadCap" - at first to "20", for a test. And change the resolution: higher resolution - longer time of waiting.
ok lookdev lighting texturing copositing you are fired !!!!!!!!!!!!!!!!!!!!!
If Blender used ready-made AI models instead of calculating the physical behavior of lights and surfaces, it would certainly speed up rendering.
omg that is friggen awesome. :)
wow...thank you , you open the pandora box... implementing right now!
wow! It's look very promising!
Congrats! nice workflow
Thanks for share
Youre a wizard Harry!
AI graphics gives me migraine.
Kinda
@@ghfgh_not kinda. It does.
@@AxiomXXXliterally the only purpose for it right now is ideation and even that is kinda narrow especially when you actually have an idea in mind it’s only really good for exploring ideas you would have never thought of otherwise. The funny thing is non-artists don’t even know how to use it and I don’t blame them it’s pretty hard to control and they have no idea how to construct an image in the first place and have never thought of the variables so they basically just spray and pray and cherry pick whichever ones it spits out that they like
@@cranberrycanvas do you really think non-artist don’t know how to use AI art I mean it’s not that complicated
@@SwoleKitchen everyone knows how to use ai to generate images. The problem is not that they don't know how to use "ai art". It's that they don't know hot to use art. These people are not needed by the industry and no one cares about their brainfarts. I mean prompts.
Hi ! Amazing tutorial but I get stuck when I need to find "ComfyUI Manager -> Install missing Custom Nodes" to install the required nodes
This is amazing!
This is super cool. Depth and Height are oddly still red for me. Anyone else?
This is wonderful. I’m actually an illustrator who would like to aggressively speed up my workflow by putting my own designs in and using 3D models to generate (largely finished, line art only) images that I can then go on and tweak by hand for finishes.
How would I, instead of pulling these prompts from just the general Ai system, use my own art work as the…Lora? I think it’s called? Do you have a tutorial on that using this same workflow?
The workflow is perfect, but I just need an ability to upload my own pencils and inks. Thanks!
I Must try this!! Every Video is a hit!
This is by far the best workflow I have seen so far!! 🤩
I luv you , u just gave me the fire
AI stuff is amazing but still has many issues and limitations.
But anyway - the comfyUI process is truly amazing working with passes individually.
Blender has had an ai render plug in for a year now. It's called stable diffusion. You have to pay to use the ai renderings. You start with x amount of credits, after used..you pay for more.
Have you tried the native ComfyUi addon for blender? I wonder if that could speed this process.
Amazing work.
Supporting you on Patreon is there also a file where there are more than 4 masks? Sorry I am thinking a bit crazy, like 40 for a complex scene 🙈 Probably I could take some time to set it up...
My inital thought: It would be very cool to do this per object. The AI style kind of the material per object.
super cool, amazing work :)
mind blowing 😍🤖 the node map makes magic
Love your video. btw you can use looseControl which are able to turn cube to various objects :D
Amazing! Thank you!
Very cool, would the addition of normal passes help with the consistency of the render? Would adding in a lighting pass work as well?
Oh yes, a normal pass would work fantastically. I have actually tested this with SD 1.5. The problem is that there is no "normal" control net for Stable Diffusion XL yet. The videos generated by SD1.5 were extremely coherent, but unfortunately also pretty ugly. So I gave up on it and focused on SDXL for this video. But as soon as there is a control net for it, this workflow should work even better
Hey Mick, great video! I've been learning Blender for a while and I'm interested in trying your approach of combining it with AI. I'm planning to build a new PC for this purpose. Do you mind sharing your PC's specifications? It would be helpful for me to know what kind of hardware can handle this type of workflow.
'really like this.... good work.
Thanks, this is amazing!
I'm going to accomplish an awesome video with this by Morning 🌄 🙌 TY TY TY!!!!
Great content! Thanks for the time and effort! Subscribed!
You made the pre-rendering process way harder than it should be. I've been doing this exact thing with a single render pass and deforum. The resut is just as inconsistent so using an outine and a depth map is pointess because there is no benefit to it (At this point you might just feed it a recorded video). My take is that until AI reaches the Sora level of frame consistency there is no point in using these flows, for anything that isn't abstract visuals at least. Also having to export/import frames from one soft to another is brainrotting, given how poor the result is.
Hello, after I drag the workflow to Comfy, I go to "ComfyUI Manager -> Install missing Custom Nodes." but do not see an option to install missing Custom Nodes. Any suggestions? THANKS.
Hi, I was wondering how your apply the condition masking ? I'm trying with "Condition Set Mask" and I have very bad results.
If I’m not mistaken, the blender bit can be removed entirely, no? Can’t you do the same separation in photoshop with an image? Or after effects with a video?
Amazing work!
yo, thats dope
Brilliant Workflow! Thanks for sharing :)
nicely done
Really very cool 🎉
Love this! Will really help me save time once we figure out high consistency.
we did there called custom loras. this guy just showed you a work flow without using a custom lora. you want a specific character make a lora of one, you ewant a specific building make a lora for one, you want a certain water make a lora for one, you want a specific robot octopus make a lora for one. it will be as consistant as your lora work is
Great workflow! Thanks for sharing!
hello. looks cool, but only the question if for each masked aread was generated separate image, and the it was just combined togetether, or ComfyUI can understand masks and promts on this masks and combine them in single generation?
Man if you could get consistent character i would be sold. I managed to do th same exact thing just using pika and runway ai and animating models in unity.
But you can! Use the same prompt for the character in every scene. Create one image of your character (full body or face). Load it into the ipAdapter and connect the mask for your character into the "attn mask" input in your ipAdapter. ...I should make a video about this haha
@@mickmumpitz if you could that would be great becauee the one thing i neee is consistency in the character models.
One other thing i managed to do was taking a sub par 3d model and passing it through krea ai, it makes the character super nice then combing frames from unity into that to out put a nicer imagr
Where Can we found the link of free video workflow ? Also it would be great to have your initial input images for testing. Thanks much!!
Wow! This is amazing!
Wow great knowledge and content, this is sooo good
Geiler Workflow!
great job, well done :)
I can't remember you. But the only video which was similar was about a woman in a kitchen and some ogre, which was about creating a movie using only AI. If that was you, you came far very quickly.
epic stuff ❤
Beautifully done!! 💯🔥🔥🔥🔥🔥
Hey, this is absolutely amazing! I'm really looking forward to the incredible results we'll see with Blender and AI working together in the future. Just think about the endless possibilities for VR environments (Omniverse) - it's going to be a blast! And imagine AI-driven SFX for various renderings. It's like giving multipass rendering a supercharge! 😄
when hitting 'que prompt' it throws a ton of errors. It woudl be great if you could go over how to solve those. I find that's the biggest issue of comfy. Downloading and install missing models etc for %70 of the time.
What an amazingly complicated way to make something just look like Ai generated shit XD