Sensitive content

This media may contain sensitive content.

Загрузка видео...

Не удалось загрузить видео

На главную

Be Better Next Time~ Art: cloudburn.🔞Comms CLOSED Jax/Video Editor: me Ribbit: MissJayJayVA #tadc #ribbitrabbit #nsfw #comic #comicdub

DemiPanVA's profile picture

 Jackie/Samuel

7,186 subscribers

60,457 просмотров • 3 месяцев назад •via X (Twitter)

NSFW#tadc#ribbitrabbit#nsfw#comic#comicdub
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

🎪🐸 Reminders - TADC Comic Dub 🐸🎪 Comic by: panysulocura| Ribbit: fleur Jax: Myself I hope you enjoyed this video! Thank you for watching! #tadc #comicdub #voiceacting
1:43

🎪🐸 Reminders - TADC Comic Dub 🐸🎪 Comic by: panysulocura| Ribbit: fleur Jax: Myself I hope you enjoyed this video! Thank you for watching! #tadc #comicdub #voiceacting

Sano │ Voice Actor │【IRIAM Pre-Debut】

95,874 просмотров • 2 месяцев назад

🐸🎪 Ribbit - TADC Comic Dub 🎪🐸 Comic: @/Gingerpines Pomni: fleur Jax: Myself I hope you enjoy the video! (Realized I didnt post it) < My YT for more vids :) #TADC #voiceacting #comicdub
1:36

🐸🎪 Ribbit - TADC Comic Dub 🎪🐸 Comic: @/Gingerpines Pomni: fleur Jax: Myself I hope you enjoy the video! (Realized I didnt post it) < My YT for more vids :) #TADC #voiceacting #comicdub

Sano │ Voice Actor │【IRIAM US Debut: August 06】

66,499 просмотров • 1 месяц назад

Marie's Lair | Fap Nights At Frenni's Comic Dub --- [VOICE ACTING] Nightguard - Mastermax888 Ballsack Boy - "B_deLuna" Marie - Jean Myna • Voice Actor🎙️🍵 Bonfie - JellyfishJubilee 🔞COMMS OPEN🫧 --- [CREDITS] Story by Fatal Fire Studios🔞 Art by Commodu NSFW🔞 & zolegan --- #marieslair #fapnightsatfrennis #comicdub
3:25

Sensitive content

Marie's Lair | Fap Nights At Frenni's Comic Dub --- [VOICE ACTING] Nightguard - Mastermax888 Ballsack Boy - "B_deLuna" Marie - Jean Myna • Voice Actor🎙️🍵 Bonfie - JellyfishJubilee 🔞COMMS OPEN🫧 --- [CREDITS] Story by Fatal Fire Studios🔞 Art by Commodu NSFW🔞 & zolegan --- #marieslair #fapnightsatfrennis #comicdub

DragonWaifu 🐉🔞

101,973 просмотров • 8 месяцев назад

🔞 NSFW COMIC DUB 🔞 Episode 2 of 4 Artist: Stripen (commissions full!)🐧🔞 Main Male VA: Ambrose Kincaid / Comms OPEN Main Female VA: (Me!) Just Dex Sound design: (Me!) Just Dex ~~~ Next episode drops next Friday unless we can get this to 200 likes this time 👀 Thank you for the support so far!
1:15

Sensitive content

🔞 NSFW COMIC DUB 🔞 Episode 2 of 4 Artist: Stripen (commissions full!)🐧🔞 Main Male VA: Ambrose Kincaid / Comms OPEN Main Female VA: (Me!) Just Dex Sound design: (Me!) Just Dex ~~~ Next episode drops next Friday unless we can get this to 200 likes this time 👀 Thank you for the support so far!

Just Dex

105,044 просмотров • 2 лет назад

Know what its nearly midnight, have a not a cowards version of that one terrible boy from Elden Ring people for some reason like me doing a lot! Art from CEO of CUM 🔞 comms closed! (Account lewd be at your own risk.)
0:28

Know what its nearly midnight, have a not a cowards version of that one terrible boy from Elden Ring people for some reason like me doing a lot! Art from CEO of CUM 🔞 comms closed! (Account lewd be at your own risk.)

Echo Sen / GingerSid ✨🎙️

31,924 просмотров • 1 год назад

It's done! It's a mess with a bunch of mistakes... But hey, I learned a lot from this :p Will try to be better next time Special thanks to Redd 雷得, Spoops 🔞+ ➡️ Mare Fair 2026, and Crazy Water 🔞 for helping me
0:38

It's done! It's a mess with a bunch of mistakes... But hey, I learned a lot from this :p Will try to be better next time Special thanks to Redd 雷得, Spoops 🔞+ ➡️ Mare Fair 2026, and Crazy Water 🔞 for helping me

MorningBullet

15,576 просмотров • 1 год назад

When You Accidentally Expose your Hand Kink 😅 🎬: Video and Mixing was done by Me 🎨: Art was created by teru! Be sure to check out their work! 🎙️: HUGE thank you to Dayz ☀️ (n)sfw VA 🔞 I'M BACK! 2026 💙 for voicing over this with me! Be sure to check out her work! #nsfw_twt #nsfwaudio #nsfw
0:23

Sensitive content

When You Accidentally Expose your Hand Kink 😅 🎬: Video and Mixing was done by Me 🎨: Art was created by teru! Be sure to check out their work! 🎙️: HUGE thank you to Dayz ☀️ (n)sfw VA 🔞 I'M BACK! 2026 💙 for voicing over this with me! Be sure to check out her work! #nsfw_twt #nsfwaudio #nsfw

🔞Solar at Night🔞

163,041 просмотров • 2 лет назад

And here is, why the Trump campaign was denied to forensically examine the Dominion voting machines in the Nov 3, 2020 election, “Two Clark County technical employees came forward completely independent of each other and explained that they discovered that the number of votes recorded by Dominion voting machines stored on USB drives would change between the time the polls were closed at night and when they were reopened the next morning.” “We have video tape of Jackie Amos inserting thumb drives into machines” “I personally observed USB cards uploaded to machines 24 times, as of today 47 USB cards are missing and no where to be found” FOLLOW ME, THE NEXT DROP WILL BE SHOCKING.
0:39

And here is, why the Trump campaign was denied to forensically examine the Dominion voting machines in the Nov 3, 2020 election, “Two Clark County technical employees came forward completely independent of each other and explained that they discovered that the number of votes recorded by Dominion voting machines stored on USB drives would change between the time the polls were closed at night and when they were reopened the next morning.” “We have video tape of Jackie Amos inserting thumb drives into machines” “I personally observed USB cards uploaded to machines 24 times, as of today 47 USB cards are missing and no where to be found” FOLLOW ME, THE NEXT DROP WILL BE SHOCKING.

Trust In Trump 47🇺🇸

47,260 просмотров • 1 месяц назад

Not the flashiest demos, but what’s under the hood represents a foundational shift for general-purpose robotics. World models are the next-gen foundation of Physical AI, not the VLM backbones found in typical VLAs. DreamZero is a 14B-parameter World Action Model (WAM) by NVIDIA that treats robotics as a joint video-and-action prediction task. Unlike traditional Vision-Language-Action (VLA) models that map images directly to motor commands, DreamZero leverages a pretrained video diffusion backbone to predict future world states and actions simultaneously. - achieves 2× better zero-shot generalization to unseen tasks and environments compared to state-of-the-art VLAs. - learns effectively from heterogeneous, non-repetitive data (500 hours), breaking the need for thousands of repeated demonstrations. - adapts to new robot embodiments with just 30 minutes of play data. - enables 7Hz closed-loop control via system optimizations and "DreamZero-Flash," making high-capacity diffusion models viable for real-time use.
1:01

Not the flashiest demos, but what’s under the hood represents a foundational shift for general-purpose robotics. World models are the next-gen foundation of Physical AI, not the VLM backbones found in typical VLAs. DreamZero is a 14B-parameter World Action Model (WAM) by NVIDIA that treats robotics as a joint video-and-action prediction task. Unlike traditional Vision-Language-Action (VLA) models that map images directly to motor commands, DreamZero leverages a pretrained video diffusion backbone to predict future world states and actions simultaneously. - achieves 2× better zero-shot generalization to unseen tasks and environments compared to state-of-the-art VLAs. - learns effectively from heterogeneous, non-repetitive data (500 hours), breaking the need for thousands of repeated demonstrations. - adapts to new robot embodiments with just 30 minutes of play data. - enables 7Hz closed-loop control via system optimizations and "DreamZero-Flash," making high-capacity diffusion models viable for real-time use.

The Humanoid Hub

35,204 просмотров • 7 месяцев назад

All this talk about AGI destroying moats and everything made me want to ship again One of the conclusions from all of you was, if you can use AI to ship faster and better, you should just ship way more complex things, like things you could not imagine making before For me personally I'd never imagine making Adobe Premiere, Final Cut Pro or Capcut but on the web, it'd simply be too difficult for me, where do I even start? So today I just tried and vibecoded them into Photo AI! A fully functional video editor but the cool twist is this one can actually generate videos with you or your trained models in it directly in your video editor I'm personally less interested in the AI influencers etc, but more fun to make actual kinda cinematic short films with yourself and other people in it, so I made this Likeness in video models is now good enough so that gives lots of cool opportunities, but most AI platforms just let you generate 10 second clips but then you're stuck with that and have to put it together yourself in Final Cut Pro So now you can just [ Send to video editor ] inside Photo AI and you end up here And the next thing I'll add is the AI Agent sidebar I have in Photo AI's main app too, which lets an agent take control of the interface. In this case you'll be able to say "make a short film of me in Bangkok", it'll ask you some questions, then write a script of prompts, which are then generated as videos with you or other people as the actors in it and automatically edited into a short film on your time Then you can right click on any video you don't like (some videos just suck or have bad resemblance to you, shit happens), and click [ Regenerate], adjust the prompt a bit and the new video will show up in the same place on your video timeline In this case I did try to make a short film of me arriving in Bangkok as a digital nomad the first time and being dazed, lost and disillusioned as I am on the other side of the world 🤯 Featuring Lorn's song "The Slow Blade"
2:37

All this talk about AGI destroying moats and everything made me want to ship again One of the conclusions from all of you was, if you can use AI to ship faster and better, you should just ship way more complex things, like things you could not imagine making before For me personally I'd never imagine making Adobe Premiere, Final Cut Pro or Capcut but on the web, it'd simply be too difficult for me, where do I even start? So today I just tried and vibecoded them into Photo AI! A fully functional video editor but the cool twist is this one can actually generate videos with you or your trained models in it directly in your video editor I'm personally less interested in the AI influencers etc, but more fun to make actual kinda cinematic short films with yourself and other people in it, so I made this Likeness in video models is now good enough so that gives lots of cool opportunities, but most AI platforms just let you generate 10 second clips but then you're stuck with that and have to put it together yourself in Final Cut Pro So now you can just [ Send to video editor ] inside Photo AI and you end up here And the next thing I'll add is the AI Agent sidebar I have in Photo AI's main app too, which lets an agent take control of the interface. In this case you'll be able to say "make a short film of me in Bangkok", it'll ask you some questions, then write a script of prompts, which are then generated as videos with you or other people as the actors in it and automatically edited into a short film on your time Then you can right click on any video you don't like (some videos just suck or have bad resemblance to you, shit happens), and click [ Regenerate], adjust the prompt a bit and the new video will show up in the same place on your video timeline In this case I did try to make a short film of me arriving in Bangkok as a digital nomad the first time and being dazed, lost and disillusioned as I am on the other side of the world 🤯 Featuring Lorn's song "The Slow Blade"

@levelsio

563,774 просмотров • 1 месяц назад

WHO ELSE DROPPING A LAUNCH VIDEO FOR A NEWSLETTER!!!!! I left Substack ~6 months ago to take some time off, shitpost, and think about the next leg of my career. But it was never actually complicated: when I was 11 my friends started a rock band, and they asked me to be their manager. For better or worse my entire life has been downstream of that — I want to become the best in the world at commercializing art. There are plenty of ways that'll come to life in the coming years, but for now I'm starting off by launching a newsletter on branded entertainment. Brands and tech companies are uniquely equipped to help artists take big creative swings, and I'm going to explore the intersection of those worlds. These companies are effectively modern entertainment studios, so how can they build better media properties? If you're curious about stunts, shows, or new media, I'm confident you'll enjoy this. Change is afoot on the internet, and it'd be wise to pay attention. Subscribe for free in the place one usually does that sort of thing <3
0:20

WHO ELSE DROPPING A LAUNCH VIDEO FOR A NEWSLETTER!!!!! I left Substack ~6 months ago to take some time off, shitpost, and think about the next leg of my career. But it was never actually complicated: when I was 11 my friends started a rock band, and they asked me to be their manager. For better or worse my entire life has been downstream of that — I want to become the best in the world at commercializing art. There are plenty of ways that'll come to life in the coming years, but for now I'm starting off by launching a newsletter on branded entertainment. Brands and tech companies are uniquely equipped to help artists take big creative swings, and I'm going to explore the intersection of those worlds. These companies are effectively modern entertainment studios, so how can they build better media properties? If you're curious about stunts, shows, or new media, I'm confident you'll enjoy this. Change is afoot on the internet, and it'd be wise to pay attention. Subscribe for free in the place one usually does that sort of thing <3

SHAIYAN

16,423 просмотров • 10 месяцев назад

I’ve never posted this video. This was me 2 years ago. I was full of fluid. They pump 20-30 pounds of fluid in. It hurt when I was finally awake. This was when my sister was allowed to see me. She took a video to show the girls so they wouldn’t be scared if they wanted to come see me. Lexi wasn’t sure, Cortana (The AI) couldn’t wait to go sit next to me. If it wasn’t for Damin Toell , Siraj Hashmi , @assliken , (The Habibi Bros) and so many of you…I would not have made it to year 2. This has been the hardest and most horrific thing I have ever gone through. My heart is doing really really well, the rest of my body and organs are still having a hard time. Thank you all for loving me and never giving up on me. Thanks for all the financial support and the prayers. The girls and I are doing a little better each day because of all of you! We love you all! #HeartTransplant #CHD
0:26

I’ve never posted this video. This was me 2 years ago. I was full of fluid. They pump 20-30 pounds of fluid in. It hurt when I was finally awake. This was when my sister was allowed to see me. She took a video to show the girls so they wouldn’t be scared if they wanted to come see me. Lexi wasn’t sure, Cortana (The AI) couldn’t wait to go sit next to me. If it wasn’t for Damin Toell , Siraj Hashmi , @assliken , (The Habibi Bros) and so many of you…I would not have made it to year 2. This has been the hardest and most horrific thing I have ever gone through. My heart is doing really really well, the rest of my body and organs are still having a hard time. Thank you all for loving me and never giving up on me. Thanks for all the financial support and the prayers. The girls and I are doing a little better each day because of all of you! We love you all! #HeartTransplant #CHD

Stacy

81,478 просмотров • 1 год назад

When I asked Grok if these modern swings were in danger of hurting players over time, this was the response: “Yes, the swing shown in this video carries a higher-than-average risk of contributing to lower back problems over time, especially if continued with high frequency and volume into middle age and beyond (50s and older).” That’s exactly why I believe so strongly in the classic golf swing. It’s more efficient, more balanced, and far easier on the body—especially the lower back. Done correctly, it’s a swing you can play for a lifetime, not just your 30s and 40s. If you want to learn how to protect your body and play better golf, I’ll be teaching my next Classic Swing Golf School on February 28th. Email me for details: christo@classicswing.golf
0:36

When I asked Grok if these modern swings were in danger of hurting players over time, this was the response: “Yes, the swing shown in this video carries a higher-than-average risk of contributing to lower back problems over time, especially if continued with high frequency and volume into middle age and beyond (50s and older).” That’s exactly why I believe so strongly in the classic golf swing. It’s more efficient, more balanced, and far easier on the body—especially the lower back. Done correctly, it’s a swing you can play for a lifetime, not just your 30s and 40s. If you want to learn how to protect your body and play better golf, I’ll be teaching my next Classic Swing Golf School on February 28th. Email me for details: [email protected]

Classic Golf Swing

67,680 просмотров • 7 месяцев назад

A video wrap up of the events from yesterday. I’m still on top of the world from meeting everyone, getting to be in the same room with the greatest President of our lifetime, and spend time with amazing people like John K. Amanchukwu Sr., Delano Squires, Jeffery Mead, King Randall, I., and Joseph Pinion III. This is just the beginning. Time to keep working an pressing forward so I can go to next year’s event as well. Keep me posted on CPAC AND TPUSA as well. I want to meet as many of you as I can. God is real and He is good. Got your six! P.S. All those sistagirls in the house and I didn’t see ONE untamed weave. Conservative Black women just do it better! Jasmine Crockett could never…
1:51

A video wrap up of the events from yesterday. I’m still on top of the world from meeting everyone, getting to be in the same room with the greatest President of our lifetime, and spend time with amazing people like John K. Amanchukwu Sr., Delano Squires, Jeffery Mead, King Randall, I., and Joseph Pinion III. This is just the beginning. Time to keep working an pressing forward so I can go to next year’s event as well. Keep me posted on CPAC AND TPUSA as well. I want to meet as many of you as I can. God is real and He is good. Got your six! P.S. All those sistagirls in the house and I didn’t see ONE untamed weave. Conservative Black women just do it better! Jasmine Crockett could never…

Zeek Arkham 🇺🇸

547,568 просмотров • 1 год назад

Good morning everyone. For just about 6 years now I've been working full-time with Thomas Frank for the "Thomas Frank" and "Thomas Frank Explains" channels - and have loved my time. I consider Thomas one of my best friends and am very blessed to have someone like him in my life - but as of now, I am officially looking for my next full-time job. Tom and I will still be working together until the end of August (unless I find my next job sooner) so until then, I will be exploring my options and seeing where my next endeavor can be. I've been thinking a lot about what I want to do next and while I still love Video Editing, I would like to consider bigger roles - such as being a Video Producer since I have an understanding of all aspects of production, or maybe management. Those aren't the only roles I would like to explore - just ones that "feel right". It's also important to me to feel I am "growing" in my field or helping a company grow, rather than just maintain what's there. It's part of why I love working with team Thomas Frank, we always have goals. Whether that's producing better content, better organization in Notion, creating "Thomas Frank Explains" (which I am so proud of given how many people love our Notion videos), creating Flylighter - it's always exciting to see what we can do by taking risks and even if I am no longer helping Tom's growth, I can't wait to see what they cook up moving forward. Attached to this is my updated Reel but feel free to check out my website at for more info about me. Thanks for reading, retweets are appreciated for more reach, and God bless. Here's some people who I've done work with: Thomas Frank, Nebula, Ben Marriott, Hayden Hillier-Smith, TheEditingPodcast, Noah Kagan.
1:06

Good morning everyone. For just about 6 years now I've been working full-time with Thomas Frank for the "Thomas Frank" and "Thomas Frank Explains" channels - and have loved my time. I consider Thomas one of my best friends and am very blessed to have someone like him in my life - but as of now, I am officially looking for my next full-time job. Tom and I will still be working together until the end of August (unless I find my next job sooner) so until then, I will be exploring my options and seeing where my next endeavor can be. I've been thinking a lot about what I want to do next and while I still love Video Editing, I would like to consider bigger roles - such as being a Video Producer since I have an understanding of all aspects of production, or maybe management. Those aren't the only roles I would like to explore - just ones that "feel right". It's also important to me to feel I am "growing" in my field or helping a company grow, rather than just maintain what's there. It's part of why I love working with team Thomas Frank, we always have goals. Whether that's producing better content, better organization in Notion, creating "Thomas Frank Explains" (which I am so proud of given how many people love our Notion videos), creating Flylighter - it's always exciting to see what we can do by taking risks and even if I am no longer helping Tom's growth, I can't wait to see what they cook up moving forward. Attached to this is my updated Reel but feel free to check out my website at for more info about me. Thanks for reading, retweets are appreciated for more reach, and God bless. Here's some people who I've done work with: Thomas Frank, Nebula, Ben Marriott, Hayden Hillier-Smith, TheEditingPodcast, Noah Kagan.

Tony Santos 🕸

15,100 просмотров • 2 лет назад

23082025 ziyu qingdao music festival vlog “OK! we’ve just returned to the hotel from the music festival. i’m really happy, still immersed in the excitement and joy right after the performance ended. i feel like this time’s stage was one of the performances that was closest to my own personality — very free, very lively. greeting everyone, playing happily together with you all, the whole atmosphere made me feel completely released. last time at the music festival i said i would quickly adjust myself back to being the energetic xiao yu from before. i don’t know if, through this performance and its outcome, everyone was able to find that familiar feeling of me again. that’s the first thing. the second thing is — during this period, i’ve been taking vocal lessons continuously, learning music theory, vocal knowledge, and vocal techniques. i think this performance was also a kind of report on the results of my studies during this time. i hope everyone is satisfied. personally, i feel compared to last time, there has been some progress. going forward, i’ll continue to maintain this pace of vocal classes and other lessons, to keep learning more about how to sing better live on stage. hopefully by the time we meet next, i’ll be able to bring an even more exciting, more passionate, more energetic me. i’m really, really happy this time. especially during the last song — i could feel the tiny raindrops falling on my face, and as i looked at the audience below the stage, what i felt was pure happiness. full, overflowing happiness. so in that final moment, i closed my eyes to feel it all. of course, there were still some little imperfections — like my clothes being pulled open while dancing, or the lift platform not syncing with the music. it was supposed to rise for 3 seconds, counting “1, 2, 3,” then the music intro would start, so that my upper-body entrance would match perfectly, and then the dance would’ve looked really cool. but… it’s fine. i feel like every imperfection is just preparation for the most perfect performance to come. so yes, there were regrets, but we’ll take those regrets with us and keep moving toward the next stage. next time will definitely be even better, even more perfect, even more lively, even more full of energy. alright — welcome everyone to “the adventures of blonde xiao yu.” today’s chapter comes to an end. even though i’m reluctant for it to be over, it’s okay. we’ll see each other again next time.” #ZIYU #梓渝
2:35

23082025 ziyu qingdao music festival vlog “OK! we’ve just returned to the hotel from the music festival. i’m really happy, still immersed in the excitement and joy right after the performance ended. i feel like this time’s stage was one of the performances that was closest to my own personality — very free, very lively. greeting everyone, playing happily together with you all, the whole atmosphere made me feel completely released. last time at the music festival i said i would quickly adjust myself back to being the energetic xiao yu from before. i don’t know if, through this performance and its outcome, everyone was able to find that familiar feeling of me again. that’s the first thing. the second thing is — during this period, i’ve been taking vocal lessons continuously, learning music theory, vocal knowledge, and vocal techniques. i think this performance was also a kind of report on the results of my studies during this time. i hope everyone is satisfied. personally, i feel compared to last time, there has been some progress. going forward, i’ll continue to maintain this pace of vocal classes and other lessons, to keep learning more about how to sing better live on stage. hopefully by the time we meet next, i’ll be able to bring an even more exciting, more passionate, more energetic me. i’m really, really happy this time. especially during the last song — i could feel the tiny raindrops falling on my face, and as i looked at the audience below the stage, what i felt was pure happiness. full, overflowing happiness. so in that final moment, i closed my eyes to feel it all. of course, there were still some little imperfections — like my clothes being pulled open while dancing, or the lift platform not syncing with the music. it was supposed to rise for 3 seconds, counting “1, 2, 3,” then the music intro would start, so that my upper-body entrance would match perfectly, and then the dance would’ve looked really cool. but… it’s fine. i feel like every imperfection is just preparation for the most perfect performance to come. so yes, there were regrets, but we’ll take those regrets with us and keep moving toward the next stage. next time will definitely be even better, even more perfect, even more lively, even more full of energy. alright — welcome everyone to “the adventures of blonde xiao yu.” today’s chapter comes to an end. even though i’m reluctant for it to be over, it’s okay. we’ll see each other again next time.” #ZIYU #梓渝

tati .ᐟ

23,580 просмотров • 1 год назад

My upcoming release of "Cinematic AI" has made me think about how bodies of work are formed. I think some are manifested and some are revealed. I think "Cinematic AI" falls into the latter category. It was not something I had a clear vision for and then created, but it was something that was revealed to me over time. I thought I saw a glimmer of it early on, but only after some time had past, could I see the body of work emerge. With a bit more context and watching great artists and how they work and think, it finally came to me that this series of 15-20 pieces that I had created could be a worthy collection to mint. AI art has been going through so many transformations from the early GAN work to Collaborative AI to now AI being widely accessible through platforms like MidJourney, Stable Diffusion, and many others. But one area that I have seen explode in recent months is cinematic AI. I distinguish this from animated AI, which has been around for a while, but cinematic AI is where the movements created by AI are getting closer to what you'd see in a movie or captured on a video camera. It still has a long way to go but it is getting more real than surreal as the technology develops. And this is where I seem to have found my groove, my home, my little corner in the artistic landscape. After Runway launched their image-to-video tool, it just blew my mind and I went down a deep rabbit hole and have created a new cinematic AI piece almost every other day for the past few months. I initially saw many of these pieces as just experiments, but with some time to reflect, I am seeing them as having the potential of being relevant pieces of artwork to mark this time in the development of AI. In some cases, I'm not sure if I'll ever be able to create a similar piece again, since the tools I use are not in my control, but in the control of the AI platforms, who are constantly improving and evolving the tools. Given all of this, there is no better way to mark my place in time than on the blockchain. I truly believe that this body of work has the potential to be an important artifact of this era in AI and AI art. It is always hard to judge ones own work, but what I can do is permanently etch in time on an immutable public database saying that I created this. Only time will tell if the work has any value or is of any significance, but who created it and what was created cannot be disputed. I hope this gives you and especially collectors some perspective on the work I'll be releasing next week. I'm still very early in my artistic journey, but hopefully some of you will see promise in what I'm doing and maybe even put in a early bet on my art practice by bidding on a piece next week. Thanks to all of you who have supported me, taught me, advised me, been a friend to me. Much love and respect.🙏 ------------------------------------- CINEMATIC AI October 25, 2023 Marking on the blockchain, establishing historical provenance for a cinematic AI body of work. Minting on Transient Labs ERC-721TL Listing on SuperRare
0:27

My upcoming release of "Cinematic AI" has made me think about how bodies of work are formed. I think some are manifested and some are revealed. I think "Cinematic AI" falls into the latter category. It was not something I had a clear vision for and then created, but it was something that was revealed to me over time. I thought I saw a glimmer of it early on, but only after some time had past, could I see the body of work emerge. With a bit more context and watching great artists and how they work and think, it finally came to me that this series of 15-20 pieces that I had created could be a worthy collection to mint. AI art has been going through so many transformations from the early GAN work to Collaborative AI to now AI being widely accessible through platforms like MidJourney, Stable Diffusion, and many others. But one area that I have seen explode in recent months is cinematic AI. I distinguish this from animated AI, which has been around for a while, but cinematic AI is where the movements created by AI are getting closer to what you'd see in a movie or captured on a video camera. It still has a long way to go but it is getting more real than surreal as the technology develops. And this is where I seem to have found my groove, my home, my little corner in the artistic landscape. After Runway launched their image-to-video tool, it just blew my mind and I went down a deep rabbit hole and have created a new cinematic AI piece almost every other day for the past few months. I initially saw many of these pieces as just experiments, but with some time to reflect, I am seeing them as having the potential of being relevant pieces of artwork to mark this time in the development of AI. In some cases, I'm not sure if I'll ever be able to create a similar piece again, since the tools I use are not in my control, but in the control of the AI platforms, who are constantly improving and evolving the tools. Given all of this, there is no better way to mark my place in time than on the blockchain. I truly believe that this body of work has the potential to be an important artifact of this era in AI and AI art. It is always hard to judge ones own work, but what I can do is permanently etch in time on an immutable public database saying that I created this. Only time will tell if the work has any value or is of any significance, but who created it and what was created cannot be disputed. I hope this gives you and especially collectors some perspective on the work I'll be releasing next week. I'm still very early in my artistic journey, but hopefully some of you will see promise in what I'm doing and maybe even put in a early bet on my art practice by bidding on a piece next week. Thanks to all of you who have supported me, taught me, advised me, been a friend to me. Much love and respect.🙏 ------------------------------------- CINEMATIC AI October 25, 2023 Marking on the blockchain, establishing historical provenance for a cinematic AI body of work. Minting on Transient Labs ERC-721TL Listing on SuperRare

Chikai

21,517 просмотров • 2 лет назад

This is how I think modern social teams should be structured 👇 Effective social media for established brands is not "a person". It's not just that it's too much of a workload for one person (it is), it's that the skills needed for social media management and for creating content are different and both time consuming. Small and new brands have to work with what they got, but for any growing or established brands, social media needs two person attention. Then growing a larger team can focus on: Creator - focused on daily performing content creation Social media manager - Posting, moderation (before community management hire), analytics, strategy and shoot support, and company comms. Second creator - more content creation in a different style, for another network, with a different approach, or enabling better content working as a group Editor (creator support + repurposing and editing other content, ad cuts etc) Community manager (moderation, first level of spport, customer research, influencer and UGC outreach) and many savvy brands build an army of creators and community managers, especially with tiktok shop, but that's another video…
0:40

This is how I think modern social teams should be structured 👇 Effective social media for established brands is not "a person". It's not just that it's too much of a workload for one person (it is), it's that the skills needed for social media management and for creating content are different and both time consuming. Small and new brands have to work with what they got, but for any growing or established brands, social media needs two person attention. Then growing a larger team can focus on: Creator - focused on daily performing content creation Social media manager - Posting, moderation (before community management hire), analytics, strategy and shoot support, and company comms. Second creator - more content creation in a different style, for another network, with a different approach, or enabling better content working as a group Editor (creator support + repurposing and editing other content, ad cuts etc) Community manager (moderation, first level of spport, customer research, influencer and UGC outreach) and many savvy brands build an army of creators and community managers, especially with tiktok shop, but that's another video…

Oren John

11,188 просмотров • 2 лет назад

Claude Code can ship a 45-second animated explainer ad in 30 minutes. No video editor needed, just CC + skills. Here's how I made this video for Soteri Skin 👇 1. /plan Concept Brief (Claude Code) I handwrite a concept brief, then chat with the agent to iterate on it. The agent gathers any raw materials we might need - context about the brand, product images, end card, etc. The concept brief details the concept, characters, visual style, script, etc 2. /prepare a moodboard (CC + GPT Image 2 + ElevenLabs) After reviewing the script, generate: - character reference images - voiceover samples for the characters / narrator - the storyboard (scene by scene grid) - a few keyframe scenes 3. /generate Keyframes for each scene (CC uses Nano Banana or GPT Image 2) Uses the character references from the previous step to generate keyframes for each scene. I probably should have done a round of iteration at this step – there's some character drift and the pH meter representation could have been better. 4. /animate Keyframe → Animated Clip (CC uses Fal Seedance) Generate 2-4 representative scenes first to see a preview. If it looks good, then generate everything. 5. /stitch (CC + ffmpeg + ElevenLabs) - Stitch clips together with hard cut - Add a music score + SFX - Sync clips to the VO - Add captions - Review and edit timing / pacing issues 6. /watch the final cut and review it - as a video editor for technical errors (mismatched voiceover and visuals, AI hallucinations, etc) - as a viewer (ICP). I delegate most of the review to the agent because it catches more things and keeps me out of the loop as much as possible. It also fixes any issues found in the review. That's it. This video took me 30 minutes because I have already created skills for everything I described above. Some day, this will be < 5 minutes. I just review and chat to provide direction and feedback. The skills do all the technical work. 7. /learn Extracts learnings and updates the skills. This final step is really important. It turns this process into a closed loop system that makes the next video much easier to create because all the learnings from the human-in-the-loop process get encoded into code. Skills are code too. If you want access to the skill, drop a comment, and I'll DM it to you (must be following). If you want to make AI video ads like this, DM me.
0:45

Claude Code can ship a 45-second animated explainer ad in 30 minutes. No video editor needed, just CC + skills. Here's how I made this video for Soteri Skin 👇 1. /plan Concept Brief (Claude Code) I handwrite a concept brief, then chat with the agent to iterate on it. The agent gathers any raw materials we might need - context about the brand, product images, end card, etc. The concept brief details the concept, characters, visual style, script, etc 2. /prepare a moodboard (CC + GPT Image 2 + ElevenLabs) After reviewing the script, generate: - character reference images - voiceover samples for the characters / narrator - the storyboard (scene by scene grid) - a few keyframe scenes 3. /generate Keyframes for each scene (CC uses Nano Banana or GPT Image 2) Uses the character references from the previous step to generate keyframes for each scene. I probably should have done a round of iteration at this step – there's some character drift and the pH meter representation could have been better. 4. /animate Keyframe → Animated Clip (CC uses Fal Seedance) Generate 2-4 representative scenes first to see a preview. If it looks good, then generate everything. 5. /stitch (CC + ffmpeg + ElevenLabs) - Stitch clips together with hard cut - Add a music score + SFX - Sync clips to the VO - Add captions - Review and edit timing / pacing issues 6. /watch the final cut and review it - as a video editor for technical errors (mismatched voiceover and visuals, AI hallucinations, etc) - as a viewer (ICP). I delegate most of the review to the agent because it catches more things and keeps me out of the loop as much as possible. It also fixes any issues found in the review. That's it. This video took me 30 minutes because I have already created skills for everything I described above. Some day, this will be < 5 minutes. I just review and chat to provide direction and feedback. The skills do all the technical work. 7. /learn Extracts learnings and updates the skills. This final step is really important. It turns this process into a closed loop system that makes the next video much easier to create because all the learnings from the human-in-the-loop process get encoded into code. Skills are code too. If you want access to the skill, drop a comment, and I'll DM it to you (must be following). If you want to make AI video ads like this, DM me.

Shiv

11,723 просмотров • 3 месяцев назад