You are amazing! I'm worried about saving up for a rtx 5090 while I've been using a rtx 4070ti. I keep telling myself I need more vram to actually produce anything but you blow that idea out of the window! You're doing everything I dream of doing with a 8 gb vram card. I should be ashamed of myself. Thanks for all of the hard work you're doing bro!
Bro you are a beast! I am just learning in the space and this is really helpful. Im more of a story teller and artist though (songwriter and musician). Im trying to connect to more people like yourself. Great work, seriously.
Mind-blowing work! The narration itself took 31 minutes, so I can only imagine how much time you spent creating the workflow, developing the story plot, generating images and videos, and waiting for everything to render. It must have taken at least 2 days-around 40 hours of effort. Your patience and dedication are truly admirable. With an 8GB graphics card, the results are already impressive, but I can only imagine the potential output with a 32GB card. Even so, ComfyUI stands out compared to Kling or Minimax due to its ability to provide consistent customization across the board. Great work. And thanks for ComfyUI.
I'm impressed with this workflow so far. I'm curious about the storyboard with images. Is it primarily a visual aid or does it serve a more functional purpose? Keep up the excellent work!
The embedded version of ComfyUI comes with Python 3.12.7 doesn't it? Are you suggesting that we downgrade it? I can't get PulID installed to save my life.
Wow I'm looking too. I'm really skilled in breakdown, been on photoshop 25+ yes and after fx 10. I found out it's not runway . They dont allow celebs. So it could be kling because minimax loses the realism. They also use deel fake.(in their biggest vid has 4mil views). U can see it in the hillary wearing blk tracksuit. They use a trick with depth of field I personally think this is post fx done with depth map. The shot of putin where camera tilts up?? That could be luma. They obviously use trained loras for faces. I'm stuck on how they get the men in background. I tried it last night and it's so hard. That scene where kim jon is eating chips and his henchmen behind. Oof. It's off the chart , so so good.
Hi! if I have >10 images of my character from different angles how can I train and generate "Pose preview" image file like in this video? (7:41) (for some reason I`m getting diagonal poses every time, not from left/right side) Do you have tutorial video about that?
![Shoot EPIC MOVIES with this FREE AI Tool! [ComfyUI Tutorial + Free Workflow]](http://i.ytimg.com/vi/gHI6PjTkBF4/mqdefault.jpg)
You are amazing! I'm worried about saving up for a rtx 5090 while I've been using a rtx 4070ti. I keep telling myself I need more vram to actually produce anything but you blow that idea out of the window! You're doing everything I dream of doing with a 8 gb vram card. I should be ashamed of myself. Thanks for all of the hard work you're doing bro!
Bro you are a beast! I am just learning in the space and this is really helpful. Im more of a story teller and artist though (songwriter and musician). Im trying to connect to more people like yourself. Great work, seriously.
Thanx,, Really appreciate it
Mind-blowing work! The narration itself took 31 minutes, so I can only imagine how much time you spent creating the workflow, developing the story plot, generating images and videos, and waiting for everything to render. It must have taken at least 2 days-around 40 hours of effort.
Your patience and dedication are truly admirable. With an 8GB graphics card, the results are already impressive, but I can only imagine the potential output with a 32GB card. Even so, ComfyUI stands out compared to Kling or Minimax due to its ability to provide consistent customization across the board. Great work. And thanks for ComfyUI.
wow man, I'm only 2 mins in at this looks great. and put a lot of effort into it, thanks!.
perfect work and smart workflow combination
right clinking on a node and rebuilding it has fixed 80% of my problems
We need an AI to fix dependency hell.
I need this. Subscribed!
I'm impressed with this workflow so far. I'm curious about the storyboard with images. Is it primarily a visual aid or does it serve a more functional purpose? Keep up the excellent work!
Thanks mate !
The embedded version of ComfyUI comes with Python 3.12.7 doesn't it? Are you suggesting that we downgrade it? I can't get PulID installed to save my life.
hello Sneaky, I m Stuck at
PulidModelLoader
Error(s) in loading state_dict for IDEncoder:
i am not able unsderstand why am i getting this error
Hi, thanks for this amazing tutorial and workflow. The workflow in the link is for SDXL model. May I know where I can get the FLUX model workflow?
Please tell me how to achieve the same quality as The Dor Brothers do?
Wow I'm looking too.
I'm really skilled in breakdown, been on photoshop 25+ yes and after fx 10.
I found out it's not runway . They dont allow celebs.
So it could be kling because minimax loses the realism.
They also use deel fake.(in their biggest vid has 4mil views). U can see it in the hillary wearing blk tracksuit.
They use a trick with depth of field I personally think this is post fx done with depth map.
The shot of putin where camera tilts up?? That could be luma.
They obviously use trained loras for faces.
I'm stuck on how they get the men in background. I tried it last night and it's so hard. That scene where kim jon is eating chips and his henchmen behind. Oof. It's off the chart , so so good.
Heres the biggy... they said they are starting a course on their site...
Last course I enquired was $900 which is waaay too expensive.
Can't get my head around these massive workflows. Can you release the pieces as separate workflows? Great work!
The tutor : it's not that difficult.
Also tutor: shows us a map more complex than the wiring in space x rocket launch.
Ongoing Series Will eventually make it simpler
Thank you so much!
How much would charge for 1 on 1 consultation?
great job
Whoa.. this is good, but still alot of effort for setting things up.
Thanx, Looking for a simpler way get everything done
Hi!
if I have >10 images of my character from different angles how can I train and generate "Pose preview" image file like in this video? (7:41) (for some reason I`m getting diagonal poses every time, not from left/right side) Do you have tutorial video about that?
Not yet but will look into it