Loading video...

Video Failed to Load

Go Home

This is crazy! With LTX 2 in ComfyUI i was able to keep my original camera movement + it did a full lip-sync on the singing haha. All running locally. I made the original video back in 2021 when Metahumans first came out and we were working in Unreal...

insaneUEFN's profile picture

Jerome | InsaneUnreal

3,968 subscribers

41,375 views • 5 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

In this experiment I wanted to try something with facial expressions and have it work with native Unreal Engine tools. I did find that generating the head with an open mouth helped to get some extra details. Creating those blend shapes was still not easy and this result is far from perfect. Ideally i want 58 generated expression references and have AI figure that out haha. btw first time baking the high poly details onto the low poly generated character. That worked surprisingly well! Endresult has 34k triangles! Built this character in 4 separate parts in Blender and generated each part in Hunyuan 3D Studio. The original references came from Nano Banana 2 and Grok. Trellis 2 in ComfyUI for the texturing. The animation was done with Control Rig in UEFN / Unreal Engine. With all the experiments so far, file and version management start to become a challenge. Getting files from different platforms with each platform having their own filename logic. I’ll have to find something to keep it more organized. Any suggestions?
1:26

In this experiment I wanted to try something with facial expressions and have it work with native Unreal Engine tools. I did find that generating the head with an open mouth helped to get some extra details. Creating those blend shapes was still not easy and this result is far from perfect. Ideally i want 58 generated expression references and have AI figure that out haha. btw first time baking the high poly details onto the low poly generated character. That worked surprisingly well! Endresult has 34k triangles! Built this character in 4 separate parts in Blender and generated each part in Hunyuan 3D Studio. The original references came from Nano Banana 2 and Grok. Trellis 2 in ComfyUI for the texturing. The animation was done with Control Rig in UEFN / Unreal Engine. With all the experiments so far, file and version management start to become a challenge. Getting files from different platforms with each platform having their own filename logic. I’ll have to find something to keep it more organized. Any suggestions?

Jerome | InsaneUnreal

46,086 views • 4 months ago

i found the Actual first version of the gifted miku song i made!!! dr. hatsune was veeery deceiving and malicious in this version (this is an animation from the original scrapped music video!!)
1:34

i found the Actual first version of the gifted miku song i made!!! dr. hatsune was veeery deceiving and malicious in this version (this is an animation from the original scrapped music video!!)

bunnycat (solve my riddles)

18,356 views • 9 months ago

Like a lot of people my age my first adventures in storytelling was playing with Star Wars figures as a kid. So when I did this quick test of kinetix video I tested it out with a Star Wars theme. What you’re seeing on the left is the driving video and staring frame. Then you chose a camera action (Dolly in etc) and write a prompt. Then kinetix aimates your character and moves the camera. It’s great to see performance controled generations coming to AI video and the team have more control coming on the roadmap. I am looking forward to testing out with some original footage and images when I get sometime soon.
0:31

Like a lot of people my age my first adventures in storytelling was playing with Star Wars figures as a kid. So when I did this quick test of kinetix video I tested it out with a Star Wars theme. What you’re seeing on the left is the driving video and staring frame. Then you chose a camera action (Dolly in etc) and write a prompt. Then kinetix aimates your character and moves the camera. It’s great to see performance controled generations coming to AI video and the team have more control coming on the roadmap. I am looking forward to testing out with some original footage and images when I get sometime soon.

Uncanny Harry AI

45,447 views • 10 months ago

Firstly, my work isn’t AI GENERATED PROMPT. The reason why I privated my account was because I was busy yesterday and couldn’t explain things. Fonts that I used: • For the “HAMKU” I used PECKHAM PRESS, I rasterized the letters a bit to achieve a close font from the official account. • For the texts I used CHANTAL medium in lower case. • For my username I used CHALKDUSTER. Brushes that I used: • Studio Pen • HB Pencil (for sketching) • Shale Brush For the colors I won’t list it, kindly check the third photo to see the palettes. I have to admit that I get lazy to use it and even lost in the palettes, so I mainly use the eyedropper tool. Here is the original version, as you can see my original version is so low quality, the lines are too pixelated and not clean—that is why I chose to post the ai enhanced version. Since I used ai to enhanced the lines of my original work, it definitely generated a new version which I still decided to post as the lines are cleaner. I really don’t know the way around on procreate. If you have suggestions on how to avoid the pixelated lines on procreate, kindly please tell me. This is my first time using it for line art cause I mostly use it for painting. I actually don’t know how many layers I exactly have as I already deleted some layers during the process. I didn’t expect I had to provide it. I spent hours on making it from ideas down to the final product. I really wanted it to be similar to the official design. This is my first and last explanation regarding this because if you are still not convinced that I made it, I don’t know what else to say.
0:34

Firstly, my work isn’t AI GENERATED PROMPT. The reason why I privated my account was because I was busy yesterday and couldn’t explain things. Fonts that I used: • For the “HAMKU” I used PECKHAM PRESS, I rasterized the letters a bit to achieve a close font from the official account. • For the texts I used CHANTAL medium in lower case. • For my username I used CHALKDUSTER. Brushes that I used: • Studio Pen • HB Pencil (for sketching) • Shale Brush For the colors I won’t list it, kindly check the third photo to see the palettes. I have to admit that I get lazy to use it and even lost in the palettes, so I mainly use the eyedropper tool. Here is the original version, as you can see my original version is so low quality, the lines are too pixelated and not clean—that is why I chose to post the ai enhanced version. Since I used ai to enhanced the lines of my original work, it definitely generated a new version which I still decided to post as the lines are cleaner. I really don’t know the way around on procreate. If you have suggestions on how to avoid the pixelated lines on procreate, kindly please tell me. This is my first time using it for line art cause I mostly use it for painting. I actually don’t know how many layers I exactly have as I already deleted some layers during the process. I didn’t expect I had to provide it. I spent hours on making it from ideas down to the final product. I really wanted it to be similar to the official design. This is my first and last explanation regarding this because if you are still not convinced that I made it, I don’t know what else to say.

Wyn 🐧; EN⁷- (💤/busy = priv)

30,000 views • 2 months ago

The unvaccinated are frequently asked, “How did you know the COVID vaccines were dangerous when they first came out?” The answer is simple: we didn’t. However, we quickly figured out that the people pushing the shots were LIARS. Watch Tucker Carlson explain this brilliantly. “The behavior of the people selling me that [vaccine] was so transparently dishonest. I didn’t know that the vax wouldn’t work, which it didn’t, of course. I didn’t know that it would cause harm, which it did. But I did know that the people selling it were liars. Like, I knew that instantly. And I know some of them, but I could just tell by their behavior [that] they’re lying. “And I was like, ‘I don’t know what this is. No one in my family is getting this ... period.’ Like I figured that out the first day ... I felt [something was wrong] so strongly, and I just obeyed [my instincts]. And I think that works.”
1:04

The unvaccinated are frequently asked, “How did you know the COVID vaccines were dangerous when they first came out?” The answer is simple: we didn’t. However, we quickly figured out that the people pushing the shots were LIARS. Watch Tucker Carlson explain this brilliantly. “The behavior of the people selling me that [vaccine] was so transparently dishonest. I didn’t know that the vax wouldn’t work, which it didn’t, of course. I didn’t know that it would cause harm, which it did. But I did know that the people selling it were liars. Like, I knew that instantly. And I know some of them, but I could just tell by their behavior [that] they’re lying. “And I was like, ‘I don’t know what this is. No one in my family is getting this ... period.’ Like I figured that out the first day ... I felt [something was wrong] so strongly, and I just obeyed [my instincts]. And I think that works.”

The Vigilant Fox 🦊

3,076,588 views • 2 years ago

The unvaccinated are frequently asked, “How did you know the COVID vaccines were dangerous when they first came out?” The answer is simple: we didn’t. However, we quickly figured out that the people pushing the shots were LIARS. Watch Tucker Carlson explain this brilliantly. “The behavior of the people selling me that [vaccine] was so transparently dishonest. I didn’t know that the vax wouldn’t work, which it didn’t, of course. I didn’t know that it would cause harm, which it did. But I did know that the people selling it were liars. Like, I knew that instantly. And I know some of them, but I could just tell by their behavior [that] they’re lying. “And I was like, ‘I don’t know what this is. No one in my family is getting this ... period.’ Like I figured that out the first day ... I felt [something was wrong] so strongly, and I just obeyed [my instincts]. And I think that works.”
1:04

The unvaccinated are frequently asked, “How did you know the COVID vaccines were dangerous when they first came out?” The answer is simple: we didn’t. However, we quickly figured out that the people pushing the shots were LIARS. Watch Tucker Carlson explain this brilliantly. “The behavior of the people selling me that [vaccine] was so transparently dishonest. I didn’t know that the vax wouldn’t work, which it didn’t, of course. I didn’t know that it would cause harm, which it did. But I did know that the people selling it were liars. Like, I knew that instantly. And I know some of them, but I could just tell by their behavior [that] they’re lying. “And I was like, ‘I don’t know what this is. No one in my family is getting this ... period.’ Like I figured that out the first day ... I felt [something was wrong] so strongly, and I just obeyed [my instincts]. And I think that works.”

The Vigilant Fox 🦊

1,865,542 views • 1 year ago

Pushed another 2021 Unreal Engine experiment through LTX in ComfyUI! Not perfect, but look at those free waves! 🌊 Back in 2021, I was exploring the first version of Metahumans and ray tracing, trying to figure out how to generate water displacement. It’s crazy to see this extra layer of detail now on top of it. Although not all shots resulted in good waterflow direction . Combined a line-art + depth pre-processor to generate the shot guide. Also used these line-art generations in Nano Banana 2 to get the new first and last frames. Some shots are still tricky to get right if you want to keep control over the shot, especially the last shot with nothing in the end frame.
0:55

Pushed another 2021 Unreal Engine experiment through LTX in ComfyUI! Not perfect, but look at those free waves! 🌊 Back in 2021, I was exploring the first version of Metahumans and ray tracing, trying to figure out how to generate water displacement. It’s crazy to see this extra layer of detail now on top of it. Although not all shots resulted in good waterflow direction . Combined a line-art + depth pre-processor to generate the shot guide. Also used these line-art generations in Nano Banana 2 to get the new first and last frames. Some shots are still tricky to get right if you want to keep control over the shot, especially the last shot with nothing in the end frame.

Jerome | InsaneUnreal

20,275 views • 4 months ago

So I was watching a Newsnation clip right now.....and I noticed something, that I have NOT seen before. The NEST camera was WIRED and it does tie into the doorbell of her older home!! Mine is a RING camera, and it too is powered and tie to the original wiring of my home doorbell!! I clipped this, and paused the video and circled with my mouse the actual green wire from the doorbell system from inside the home!!
0:42

So I was watching a Newsnation clip right now.....and I noticed something, that I have NOT seen before. The NEST camera was WIRED and it does tie into the doorbell of her older home!! Mine is a RING camera, and it too is powered and tie to the original wiring of my home doorbell!! I clipped this, and paused the video and circled with my mouse the actual green wire from the doorbell system from inside the home!!

Capt KEVman!!!

40,813 views • 4 months ago

I've been making music videos and commercials for over a decade. This video is the first time I was able to mimic my camera style with ai.
1:23

I've been making music videos and commercials for over a decade. This video is the first time I was able to mimic my camera style with ai.

TUPACABRA

17,605 views • 3 months ago

Everybody speak about consistent character for video generation as Minimax, Kling etc... But nothing looking super stable. And so I trained for the first time a LoRA model on Hunyuan video model (open source) on a real person. It take approximatly 15h of training on a A100 GPU with 50 videos. the result is pretty good !! With more training it will allow to have even better result. The result was generated inside ComfyUI. All this video have been generated in AI. Check at , we are doing cool stuff :)
0:21

Everybody speak about consistent character for video generation as Minimax, Kling etc... But nothing looking super stable. And so I trained for the first time a LoRA model on Hunyuan video model (open source) on a real person. It take approximatly 15h of training on a A100 GPU with 50 videos. the result is pretty good !! With more training it will allow to have even better result. The result was generated inside ComfyUI. All this video have been generated in AI. Check at , we are doing cool stuff :)

Lovis Odin

93,560 views • 1 year ago

Seedance 2.0 is allowing us to enter a new era of music video creation. Here is how I created HONEY. It was a quick test to see how well this workflow holds up. 🐝 1 - Write your song and generate the music with Suno 5.5. 2 - Use an image generator of your choice. For HONEY I combined both Grok Imagine for aesthetics and Nano Banana Pro for refined editing. 3 - In Capcut I import my audio and just save out a blank video video containing the audio. This step is important because this video file containing audio will now be used with Seedance 2.0 as a video reference with Omni. This allows the AI to apply automatic and realistic lipsync and movement to the music, it's extremely powerful! 4 - Once I have a both my image and video with audio as reference, I use Seedance 2.0 Omni and upload my starting image and then the video reference with the audio. 5 - From here I'm simply prompting like normal, specifying what's happening in my scene with detailed instructions, mentioning multi shots and camera angle changes and then specifying that the person is singing along to the song. I type out the lyrics that are present to have better lipsync accuracy. 6 - Once I have generated a video and like the result, I do video to video, so i upload that video that just got generated and type "The scene continues" and prompt new actions to take place. This allows you to expand on a narrative. These new shots can be used as B-ROLL and since I uploaded my video as reference I have full consistency of everything it saw in the video. This is also extremely powerful. 7 - This is actually the most difficult part. Edit in Capcut. This is where you need to understand pacing and shot selection from all the scenes you generated to bring it all together. You must be strategic with the editing. Goodluck! I'll probably record a video tutorial at some point as it's easier to see what is being done.
0:46

Seedance 2.0 is allowing us to enter a new era of music video creation. Here is how I created HONEY. It was a quick test to see how well this workflow holds up. 🐝 1 - Write your song and generate the music with Suno 5.5. 2 - Use an image generator of your choice. For HONEY I combined both Grok Imagine for aesthetics and Nano Banana Pro for refined editing. 3 - In Capcut I import my audio and just save out a blank video video containing the audio. This step is important because this video file containing audio will now be used with Seedance 2.0 as a video reference with Omni. This allows the AI to apply automatic and realistic lipsync and movement to the music, it's extremely powerful! 4 - Once I have a both my image and video with audio as reference, I use Seedance 2.0 Omni and upload my starting image and then the video reference with the audio. 5 - From here I'm simply prompting like normal, specifying what's happening in my scene with detailed instructions, mentioning multi shots and camera angle changes and then specifying that the person is singing along to the song. I type out the lyrics that are present to have better lipsync accuracy. 6 - Once I have generated a video and like the result, I do video to video, so i upload that video that just got generated and type "The scene continues" and prompt new actions to take place. This allows you to expand on a narrative. These new shots can be used as B-ROLL and since I uploaded my video as reference I have full consistency of everything it saw in the video. This is also extremely powerful. 7 - This is actually the most difficult part. Edit in Capcut. This is where you need to understand pacing and shot selection from all the scenes you generated to bring it all together. You must be strategic with the editing. Goodluck! I'll probably record a video tutorial at some point as it's easier to see what is being done.

Travis Davids

19,081 views • 3 months ago

Michael "Venom" Page reflects on his showing at UFC London: "There were things I was met with in the cage that I didn’t think I would face. Patterson was a bit more on his back foot, and I actually really wanted to be aggressive in this fight. I didn’t readjust or rethink how to work it out — how to press, how to close the gap. I was actually getting frustrated, and I think this is the first time someone’s gotten me frustrated in the cage. I was looking at myself and thinking, I need to do way better. It wasn’t good enough. Fans have expectations of me, but I have massive expectations of myself — and I didn’t deliver."
3:57

Michael "Venom" Page reflects on his showing at UFC London: "There were things I was met with in the cage that I didn’t think I would face. Patterson was a bit more on his back foot, and I actually really wanted to be aggressive in this fight. I didn’t readjust or rethink how to work it out — how to press, how to close the gap. I was actually getting frustrated, and I think this is the first time someone’s gotten me frustrated in the cage. I was looking at myself and thinking, I need to do way better. It wasn’t good enough. Fans have expectations of me, but I have massive expectations of myself — and I didn’t deliver."

Ariel Helwani

98,424 views • 4 months ago

I came across this video on Ig when I was about 7 months pregnant and coincidentally there were tiny strains of mold visible on the POP in our room. I was so scared and did alot of research. We found out that we could clean it with vinegar and bleach. My husband did and everyday when I woke up in the midnight, the first thing I would do is check to see if it’d come back. Thankfully there’s no signs of mold in our house since then! I still unconsciously check it cos that video really scared and scarred me😭
2:44

I came across this video on Ig when I was about 7 months pregnant and coincidentally there were tiny strains of mold visible on the POP in our room. I was so scared and did alot of research. We found out that we could clean it with vinegar and bleach. My husband did and everyday when I woke up in the midnight, the first thing I would do is check to see if it’d come back. Thankfully there’s no signs of mold in our house since then! I still unconsciously check it cos that video really scared and scarred me😭

Oluwatosin of Jesus || Virtual Assistant🤍

627,569 views • 5 months ago

Something strange happened in the mid-noughties... I made three different music videos for Suddenly I See ⚡️ 20 years ago today I first released this song, so I thought it'd be a good opportunity to tell a story... The story starts in the summer of 2005, when our protagonist (moi!) has just agreed that ‘Suddenly I See’ would be the 3rd single from Eye To The Telescope. We set to work on the music video: a performance battle between light KT and dark KT! This version was perhaps the closest to how people were discovering me - through my live television performances and gigs. We shot this version where I am battling another version of myself, with a cool result. This was the video fans in the UK got, and the song wove some magic out on the radio waves. NEXT…my US label decided we needed to make a new video, especially for the US fans. This was a super-cool opportunity which I jumped at, as it meant creatively a whole new take on the song, and I got to work with a Director whose work I loved, Patrick Daughters. I particularly loved his ‘Gold Lion’ video for Yeah, Yeah, Yeahs ✨ We flew to Bucharest, Hungary, to shoot this video, which is circus-themed. This video is definitely one of the most-out there ones I ever shot…parachuting dogs, me as a show girl, me on a trapeze?! I absolutely loved making this video, and also really loved the result, so imagine my surprise when the label told me they didn't want to release it! They felt the old crumbling apartment building shots were just too bleak. It was around the time when the song was used in the movie ‘The Devil Wears Prada’ and had taken on a shiny new meaning. So…we made a THIRD video, which replaced the circus video in the USA. This new, animated version sees me as a 50 foot woman journeying through an animated pop-up world. It's really colourful and reflects that new life the song was taking on. It was a very fun video to make. If you had to ask me to pick my favourite...I’d have to go with parachuting Jack Russells, Top Hat and moustache!!
0:20

Something strange happened in the mid-noughties... I made three different music videos for Suddenly I See ⚡️ 20 years ago today I first released this song, so I thought it'd be a good opportunity to tell a story... The story starts in the summer of 2005, when our protagonist (moi!) has just agreed that ‘Suddenly I See’ would be the 3rd single from Eye To The Telescope. We set to work on the music video: a performance battle between light KT and dark KT! This version was perhaps the closest to how people were discovering me - through my live television performances and gigs. We shot this version where I am battling another version of myself, with a cool result. This was the video fans in the UK got, and the song wove some magic out on the radio waves. NEXT…my US label decided we needed to make a new video, especially for the US fans. This was a super-cool opportunity which I jumped at, as it meant creatively a whole new take on the song, and I got to work with a Director whose work I loved, Patrick Daughters. I particularly loved his ‘Gold Lion’ video for Yeah, Yeah, Yeahs ✨ We flew to Bucharest, Hungary, to shoot this video, which is circus-themed. This video is definitely one of the most-out there ones I ever shot…parachuting dogs, me as a show girl, me on a trapeze?! I absolutely loved making this video, and also really loved the result, so imagine my surprise when the label told me they didn't want to release it! They felt the old crumbling apartment building shots were just too bleak. It was around the time when the song was used in the movie ‘The Devil Wears Prada’ and had taken on a shiny new meaning. So…we made a THIRD video, which replaced the circus video in the USA. This new, animated version sees me as a 50 foot woman journeying through an animated pop-up world. It's really colourful and reflects that new life the song was taking on. It was a very fun video to make. If you had to ask me to pick my favourite...I’d have to go with parachuting Jack Russells, Top Hat and moustache!!

KT Tunstall

11,433 views • 11 months ago

For the facial animations in my game, I use a technique that yields results similar to L.A. Noire. To keep it simple: I first generate a facial animation video using AI like LTX 2. Then, I create a video depth map from that animation and project it onto a face mask. Using vertex displacement, the depth map dynamically deforms the face as the character speaks. The result looks good in standalone VR. I actually created this workflow long time ago:
0:09

For the facial animations in my game, I use a technique that yields results similar to L.A. Noire. To keep it simple: I first generate a facial animation video using AI like LTX 2. Then, I create a video depth map from that animation and project it onto a face mask. Using vertex displacement, the depth map dynamically deforms the face as the character speaks. The result looks good in standalone VR. I actually created this workflow long time ago:

Alex

48,296 views • 4 months ago

Hello everyone, this is my latest personal project, an Attack on Titan short film. In this short film, I was responsible for all aspects of production. I experimented with building my own workflow and explored the integration of 2D and 3D animation. Since this is my first time creating such a large-scale project, most of the storyboards are based on the original work, with a few inspired by other films, and the rest are my own original attempts. I aimed to fully respect the original source while incorporating many of my own designs, such as character design, character effects, and original shots. This has been an extremely valuable experience for me. Although the short film is not perfect, it represents my best effort within the limited time available. Therefore, I have decided to share it, hoping you will enjoy it. I will now begin work on my next short film. #AttackOnTitan #aot #進撃の巨人
5:10

Hello everyone, this is my latest personal project, an Attack on Titan short film. In this short film, I was responsible for all aspects of production. I experimented with building my own workflow and explored the integration of 2D and 3D animation. Since this is my first time creating such a large-scale project, most of the storyboards are based on the original work, with a few inspired by other films, and the rest are my own original attempts. I aimed to fully respect the original source while incorporating many of my own designs, such as character design, character effects, and original shots. This has been an extremely valuable experience for me. Although the short film is not perfect, it represents my best effort within the limited time available. Therefore, I have decided to share it, hoping you will enjoy it. I will now begin work on my next short film. #AttackOnTitan #aot #進撃の巨人

XieBoli

643,428 views • 2 years ago

iShowSpeed reveals he made $1,000,000 at 16 while most kids were in class "I didn't know what to do, I didn't want a car, a chain, clothes, I didn’t want all of that" "It’s kind of crazy when I think back on it, I was genuinely as a 16 year old kid, I’m locked in just working on my craft. I didn’t have the realization on the position that I was in" "Right now I’m still locked in, but looking back as a junior in high school and I have all this money, definitely not take it for granted"
1:22

iShowSpeed reveals he made $1,000,000 at 16 while most kids were in class "I didn't know what to do, I didn't want a car, a chain, clothes, I didn’t want all of that" "It’s kind of crazy when I think back on it, I was genuinely as a 16 year old kid, I’m locked in just working on my craft. I didn’t have the realization on the position that I was in" "Right now I’m still locked in, but looking back as a junior in high school and I have all this money, definitely not take it for granted"

katsu

2,711,233 views • 2 months ago