Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Made with Kling 3.0 Omni. I have no doubt that Kling will keep excelling in this raw, amateurish, candid, and natural style. But now I’m just curious whether Seedance 2.0 can achieve the same aesthetic. The problem is that I haven’t seen a use case yet, since most of... show more

MXVDXN // DAN

21,629 subscribers

46,680 Aufrufe • vor 7 Monaten •via X (Twitter)

Kunst Bildung Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

I had the chance to test FLUX 3, and my goal was clear. I wanted to go straight into testing some local vernacular nuances, because that’s all I care about. I don’t bother doing cinematic or Hollywood stuff because I know that's what everyone will do 😆😁 So i let that to them so i can I just go straight into doing the raw stuff. And HOOLLLYYY FVVVKIN SH****T ANJAAAYYY GIILLAAAA!!! It looks soooo damn impressive!!! 😂😂 I’m shocked, like, literally shocked, because I underestimated FLUX 3. I’m genuinely shocked by how good the training data is. The nuances of the dialect, the gesture, the intonation and such were somehow much better than Seedance 2.0!!! Althooooo, in terms of dynamic performance, I still think Seedance 2.0 is still much better. But FLUX 3 is definitely above Kling 3.0 and below Seedance 2.0. In some parts, FLUX 3 can still get very glitchy or distorted, but regarding its raw and natural nuances, which is an aesthetic I’m always pushing, it’s sooooooooo damn good! I definitely need to test it more. I really hope we can have an Omni-References feature as well! I'm kinda happy because at least we have another strong alternative besides Seedance 2.0.

I had the chance to test FLUX 3, and my goal was clear. I wanted to go straight into testing some local vernacular nuances, because that’s all I care about. I don’t bother doing cinematic or Hollywood stuff because I know that's what everyone will do 😆😁 So i let that to them so i can I just go straight into doing the raw stuff. And HOOLLLYYY FVVVKIN SH****T ANJAAAYYY GIILLAAAA!!! It looks soooo damn impressive!!! 😂😂 I’m shocked, like, literally shocked, because I underestimated FLUX 3. I’m genuinely shocked by how good the training data is. The nuances of the dialect, the gesture, the intonation and such were somehow much better than Seedance 2.0!!! Althooooo, in terms of dynamic performance, I still think Seedance 2.0 is still much better. But FLUX 3 is definitely above Kling 3.0 and below Seedance 2.0. In some parts, FLUX 3 can still get very glitchy or distorted, but regarding its raw and natural nuances, which is an aesthetic I’m always pushing, it’s sooooooooo damn good! I definitely need to test it more. I really hope we can have an Omni-References feature as well! I'm kinda happy because at least we have another strong alternative besides Seedance 2.0.

MXVDXN // DAN

28,004 Aufrufe • vor 2 Monaten

Okay, this one is the Grok Imagine version. But here’s something you need to note: I uploaded the character sheet I made with Nano Banana Pro as the base image. So it feels like this fake “Omni reference” kind of style, but it works 😄 Somehow, it’s much more consistent than uploading a still image of your scene with your character, because there’s a chance your character will morph a bit. By using your character sheet as the base model, it helps maintain consistency. The only problem is that when you do the img2vid prompt, you need to retell the setting, the action, the vibe and so on. But for me, I kind of like that approach, LOL 😆 Like I said, I’m getting lazy about animating images one by one. With this approach, I can just focus on dividing the shots, like shot 1: blabla, shot 2: bliblibli, shot 3: blublu, etc. Now for the comparison: In comparison with the Kling 3.0 Omni version, I feel that Grok Imagine is much more dynamic. But in terms of the character performance, it feels a bit over the top. It’s like the AI characters are acting it out 😁 Meanwhile, Kling 3.0 Omni feels much more realistic in terms of the acting and a bit more atmospheric. I honestly love both. If I want to fool around, I guess I’ll use Grok Imagine. But if I want more subtle realism and a candid feel, I’ll go with Kling 3.0.

Okay, this one is the Grok Imagine version. But here’s something you need to note: I uploaded the character sheet I made with Nano Banana Pro as the base image. So it feels like this fake “Omni reference” kind of style, but it works 😄 Somehow, it’s much more consistent than uploading a still image of your scene with your character, because there’s a chance your character will morph a bit. By using your character sheet as the base model, it helps maintain consistency. The only problem is that when you do the img2vid prompt, you need to retell the setting, the action, the vibe and so on. But for me, I kind of like that approach, LOL 😆 Like I said, I’m getting lazy about animating images one by one. With this approach, I can just focus on dividing the shots, like shot 1: blabla, shot 2: bliblibli, shot 3: blublu, etc. Now for the comparison: In comparison with the Kling 3.0 Omni version, I feel that Grok Imagine is much more dynamic. But in terms of the character performance, it feels a bit over the top. It’s like the AI characters are acting it out 😁 Meanwhile, Kling 3.0 Omni feels much more realistic in terms of the acting and a bit more atmospheric. I honestly love both. If I want to fool around, I guess I’ll use Grok Imagine. But if I want more subtle realism and a candid feel, I’ll go with Kling 3.0.

MXVDXN // DAN

16,961 Aufrufe • vor 7 Monaten

Seedance 2.0 VS Kling 3.0! 🔥 Essential comparison to understand the two best models on the market Conclusions and prompt: The generations are radically different, using the same initial and final frames and spaceship elements. I specified that it's a fast-paced, cinematic action scene. But Seedance has created a beautiful, relaxing, high-quality scene. The rendering of the ship's movements is sublime with Seedance; it's a dynamic, cinematic-quality 3D element. The Kling scene conveys the message better; I specified that it should splash in the water. The sounds are good; in Seedance, the sound quality is cinematic. I've added a third shot with Kling and a giant. I used Kling 3.0 at Higgsfield Prompt in comment:

Seedance 2.0 VS Kling 3.0! 🔥 Essential comparison to understand the two best models on the market Conclusions and prompt: The generations are radically different, using the same initial and final frames and spaceship elements. I specified that it's a fast-paced, cinematic action scene. But Seedance has created a beautiful, relaxing, high-quality scene. The rendering of the ship's movements is sublime with Seedance; it's a dynamic, cinematic-quality 3D element. The Kling scene conveys the message better; I specified that it should splash in the water. The sounds are good; in Seedance, the sound quality is cinematic. I've added a third shot with Kling and a giant. I used Kling 3.0 at Higgsfield Prompt in comment:

hedoήist

43,990 Aufrufe • vor 6 Monaten

No but this is actually the most RANDOM crossover I’ve ever seen but I can’t say I’m surprised because that’s very on brand for Duo Lingo lol

🤠Caroline

10,540,340 Aufrufe • vor 2 Jahren

Okay! WAN 3.0 let's go! Whenever I test a new video model, the first thing I always do is test how well it handles language nuance. And yup, WAN 3.0 did it pretty well. I tested it via Venice And nope, this is not sponsored content. I use my own money. I’ve always used Venice for some of my more erotic video work because it’s uncensored and awesome. As simple as that. 👍😎 The reason i quote this post because people keep asking like heeey where do you generate uncensored stuff. Only two places right now, either Venice or D-zine. So there you go! bUTTTT!!!! If there's more, let me know 👍 I guess I could say that WAN 3.0 is probably the closest model to Seedance 2.0 in terms of quality right now. For my very specific needs, I love making dialogue-driven scenes, and WAN 3.0 is absolutely fine for that. In fact, I have to say it’s much better than MiniMax H3 in some ways. But of course, keep in mind that every model has its own strengths and flaws. Unfortunately, when it comes to very precise, extremely dynamic scenes, like what I usually do with my Sari & Ploy series, especially fight scenes, it’s not quite there yet. The only other problem is that sometimes, if you’re unlucky, WAN 3.0 can produce this weird audio artifact. I don’t really know how to explain it. It’s kind of like that flanger-like sound you sometimes get when generating with Seedance. Yeah, WAN 3.0 can occasionally have the same problem, LOL 😆 But performance-wise, for my use case, especially conversational scenes, candid moments, and the kind of raw camera movement I’ve always loved, WAN 3.0 really delivers. For me personally, this is where things start to get really exciting, especially when I think about series production. I can now be much more strategic about which model I use for each type of scene. For example, I’ll still use Seedance 2.0 and 2.5 mainly for more extreme, dynamic fight scenes, while conversational scenes are something I can comfortably do with WAN 3.0. MiniMax H3, meanwhile, feels more like the experimental option. I personally think H3 is a very unique model. Maybe it’s not as powerful for conversational scenes, but it definitely has its own flavor and can produce things that feel different from the others. But you know what, I can’t help it. I really need to say this LOL. It’s funny how a model like Grok Imagine Video used to be sooo good, and I praised it a lot, but now it feels like an extreme slot machine. At this point, I sometimes feel like it’s mostly being hyped by people who just want to glaze Elon Musk. Somehow, it actually went backwards. 😅 And it’s interesting how models like Seedance 1.5 and the previous WAN versions have improved so much over time. It feels very ironic because I wasn’t even a fan of Seedance back then, and the same goes for WAN. But yeah, at the end of the day is the output quality that matters for me.

Sensitive content

Okay! WAN 3.0 let's go! Whenever I test a new video model, the first thing I always do is test how well it handles language nuance. And yup, WAN 3.0 did it pretty well. I tested it via Venice And nope, this is not sponsored content. I use my own money. I’ve always used Venice for some of my more erotic video work because it’s uncensored and awesome. As simple as that. 👍😎 The reason i quote this post because people keep asking like heeey where do you generate uncensored stuff. Only two places right now, either Venice or D-zine. So there you go! bUTTTT!!!! If there's more, let me know 👍 I guess I could say that WAN 3.0 is probably the closest model to Seedance 2.0 in terms of quality right now. For my very specific needs, I love making dialogue-driven scenes, and WAN 3.0 is absolutely fine for that. In fact, I have to say it’s much better than MiniMax H3 in some ways. But of course, keep in mind that every model has its own strengths and flaws. Unfortunately, when it comes to very precise, extremely dynamic scenes, like what I usually do with my Sari & Ploy series, especially fight scenes, it’s not quite there yet. The only other problem is that sometimes, if you’re unlucky, WAN 3.0 can produce this weird audio artifact. I don’t really know how to explain it. It’s kind of like that flanger-like sound you sometimes get when generating with Seedance. Yeah, WAN 3.0 can occasionally have the same problem, LOL 😆 But performance-wise, for my use case, especially conversational scenes, candid moments, and the kind of raw camera movement I’ve always loved, WAN 3.0 really delivers. For me personally, this is where things start to get really exciting, especially when I think about series production. I can now be much more strategic about which model I use for each type of scene. For example, I’ll still use Seedance 2.0 and 2.5 mainly for more extreme, dynamic fight scenes, while conversational scenes are something I can comfortably do with WAN 3.0. MiniMax H3, meanwhile, feels more like the experimental option. I personally think H3 is a very unique model. Maybe it’s not as powerful for conversational scenes, but it definitely has its own flavor and can produce things that feel different from the others. But you know what, I can’t help it. I really need to say this LOL. It’s funny how a model like Grok Imagine Video used to be sooo good, and I praised it a lot, but now it feels like an extreme slot machine. At this point, I sometimes feel like it’s mostly being hyped by people who just want to glaze Elon Musk. Somehow, it actually went backwards. 😅 And it’s interesting how models like Seedance 1.5 and the previous WAN versions have improved so much over time. It feels very ironic because I wasn’t even a fan of Seedance back then, and the same goes for WAN. But yeah, at the end of the day is the output quality that matters for me.

MXVDXN // DAN

322,565 Aufrufe • vor 1 Monat

Dolly Parton says she was never a “natural beauty” “It is true that I look artificial, but I believe that I’m totally real, and my look is really based on a country girl’s idea of glam.” “I wasn’t naturally pretty, so I make the most of anything I’ve got.” Interviewer: “Hold on a second.” Dolly Parton: “I’m telling you, I’m not.” Interviewer: “You were not naturally pretty?” Dolly Parton: “No.” Interviewer: “I’ve seen the pictures, Dolly. I’m sorry. I have to disagree with that.” Dolly Parton: “You should have seen me this morning before I got ready to see you.” “I’m not like a natural beauty. Uh, but I can enhance it. Whatever. Whatever it takes, I do.” “I try to make the most of everything.”

Dolly Parton says she was never a “natural beauty” “It is true that I look artificial, but I believe that I’m totally real, and my look is really based on a country girl’s idea of glam.” “I wasn’t naturally pretty, so I make the most of anything I’ve got.” Interviewer: “Hold on a second.” Dolly Parton: “I’m telling you, I’m not.” Interviewer: “You were not naturally pretty?” Dolly Parton: “No.” Interviewer: “I’ve seen the pictures, Dolly. I’m sorry. I have to disagree with that.” Dolly Parton: “You should have seen me this morning before I got ready to see you.” “I’m not like a natural beauty. Uh, but I can enhance it. Whatever. Whatever it takes, I do.” “I try to make the most of everything.”

‏ً

214,004 Aufrufe • vor 1 Monat

I’m still not quite sure why this type of video is trending, but I gave it a try and made my own version with Kling 3.0. You can also get it here

I’m still not quite sure why this type of video is trending, but I gave it a try and made my own version with Kling 3.0. You can also get it here

BubbleBrain

12,409 Aufrufe • vor 1 Monat

New body-physics test for the best AI video tools: The newly released Grok Imagine 1.5, the king Seedance 2.0, Google’s “revolutionary super-duper” Gemini Omni Flash, and the old-timer Kling 3.0 Pro. This time I tested how each model handles realistic running motion, body movement, fabric physics, and natural secondary motion. And the result was much less obvious than I expected. Believe it or not, I can’t call Seedance the clear winner this time. Each model got several attempts. - Grok Imagine 1.5: The new version is finally available on the official Grok website, so I could properly test it. Honestly, I didn’t notice a massive improvement over the previous version. Still, the result was acceptable. It produced the most cartoonish image, and the woman runs as if she’s wearing heels, but the body physics were decent enough. It also understood the instructions quickly and followed them correctly. - Kling 3.0 Pro: The old man decided to test my patience. It repeatedly blocked a simple running scene as adult content, then misunderstood the instructions several times. The successful result has the most realistic lighting and frame rate, but the actual body physics look strange. It almost feels like loose foam padding is bouncing inside the leggings. There are also several visible artifacts and unnatural movements. - Gemini Omni Flash: As usual, it gave me that strange slow-motion, low-FPS look that Google models seem to love. But it didn’t censor anything, understood the instructions immediately, and produced a beautiful, realistic result. Surprisingly, this is the output I liked the most in this test. - Seedance 2.0: Seedance also blocked a couple of generations, just like Kling, but eventually produced a strong result. It delivered the most beautiful and visually appealing footage, but I honestly expected better physics. The video looks great, yet I can’t confidently call it the most physically accurate result. - My ranking: 1. Gemini Omni Flash — not perfect, but the best overall result for me 2. Seedance 2.0 — visually stunning, but I preferred Omni’s physics 3. Grok Imagine 1.5 — cartoonish look and strange running, but still acceptable 4. Kling 3.0 Pro — the longest wait, the strangest physics, and the most inconsistent result Do you agree with my ranking? #AIVideo

New body-physics test for the best AI video tools: The newly released Grok Imagine 1.5, the king Seedance 2.0, Google’s “revolutionary super-duper” Gemini Omni Flash, and the old-timer Kling 3.0 Pro. This time I tested how each model handles realistic running motion, body movement, fabric physics, and natural secondary motion. And the result was much less obvious than I expected. Believe it or not, I can’t call Seedance the clear winner this time. Each model got several attempts. - Grok Imagine 1.5: The new version is finally available on the official Grok website, so I could properly test it. Honestly, I didn’t notice a massive improvement over the previous version. Still, the result was acceptable. It produced the most cartoonish image, and the woman runs as if she’s wearing heels, but the body physics were decent enough. It also understood the instructions quickly and followed them correctly. - Kling 3.0 Pro: The old man decided to test my patience. It repeatedly blocked a simple running scene as adult content, then misunderstood the instructions several times. The successful result has the most realistic lighting and frame rate, but the actual body physics look strange. It almost feels like loose foam padding is bouncing inside the leggings. There are also several visible artifacts and unnatural movements. - Gemini Omni Flash: As usual, it gave me that strange slow-motion, low-FPS look that Google models seem to love. But it didn’t censor anything, understood the instructions immediately, and produced a beautiful, realistic result. Surprisingly, this is the output I liked the most in this test. - Seedance 2.0: Seedance also blocked a couple of generations, just like Kling, but eventually produced a strong result. It delivered the most beautiful and visually appealing footage, but I honestly expected better physics. The video looks great, yet I can’t confidently call it the most physically accurate result. - My ranking: 1. Gemini Omni Flash — not perfect, but the best overall result for me 2. Seedance 2.0 — visually stunning, but I preferred Omni’s physics 3. Grok Imagine 1.5 — cartoonish look and strange running, but still acceptable 4. Kling 3.0 Pro — the longest wait, the strangest physics, and the most inconsistent result Do you agree with my ranking? #AIVideo

Alpha Mom

157,932 Aufrufe • vor 3 Monaten

Midjourney v7 // Kling AI 2.0 → music: Suno v4.5 → editing: CapCut I've always loved it ever since Kling 1.6, for its very natural and candid appeal. With 2.0, it just gets even better. I'm a huge fan of the candid and handheld style. And always want to achieve that Wong Kar-wai vibe. The best thing to do is, in the negative prompt section, make sure to write "Slow Motion." For me, it works really well, as it avoids that typical slow-motion result you often get from generated videos. As for the prompt itself, it's very simple. Captured in handheld shaky camera, candid moments, [description here], natural gesture. And that's it. That's the only prompt formula I use.

Midjourney v7 // Kling AI 2.0 → music: Suno v4.5 → editing: CapCut I've always loved it ever since Kling 1.6, for its very natural and candid appeal. With 2.0, it just gets even better. I'm a huge fan of the candid and handheld style. And always want to achieve that Wong Kar-wai vibe. The best thing to do is, in the negative prompt section, make sure to write "Slow Motion." For me, it works really well, as it avoids that typical slow-motion result you often get from generated videos. As for the prompt itself, it's very simple. Captured in handheld shaky camera, candid moments, [description here], natural gesture. And that's it. That's the only prompt formula I use.

MXVDXN // DAN

12,105 Aufrufe • vor 1 Jahr

🚨 CANADA: No oncologist yet — but a MAID pamphlet arrived Kristin Logan: “I hadn’t even seen an oncologist yet before I got that pamphlet.” “As I’m waiting for even the first call from the oncology team, I get this pamphlet in the mail basically telling me that I can go and kill myself.” “At that point you realize what a DYSTOPIAN situation it is.”

🚨 CANADA: No oncologist yet — but a MAID pamphlet arrived Kristin Logan: “I hadn’t even seen an oncologist yet before I got that pamphlet.” “As I’m waiting for even the first call from the oncology team, I get this pamphlet in the mail basically telling me that I can go and kill myself.” “At that point you realize what a DYSTOPIAN situation it is.”

Laura Ingraham

1,167,392 Aufrufe • vor 8 Tagen

Dealing with the aftermath of abuse, and recovering from what I was using has been the hardest thing I’ve faced. I’m healing and I’m still here, I love you all (just in case you haven’t seen this yet)

Dealing with the aftermath of abuse, and recovering from what I was using has been the hardest thing I’ve faced. I’m healing and I’m still here, I love you all (just in case you haven’t seen this yet)

Sam Collins

32,328 Aufrufe • vor 8 Monaten

It’s been said before, but I have to repeat it. This is one of the most beautiful games that has stood the test of time. I’ve started to play it so many times but have yet to beat it. I decide to play the original on NSO even though I own the Wii U version 😅

It’s been said before, but I have to repeat it. This is one of the most beautiful games that has stood the test of time. I’ve started to play it so many times but have yet to beat it. I decide to play the original on NSO even though I own the Wii U version 😅

Mike Odyssey

348,488 Aufrufe • vor 9 Tagen

Zara Larsson answers what was the key to getting out of the Khia Asylum. “I’ve always known I’m a cool girl. I think my taste is good or fun, it’s my taste. I like what I do. I just need to express it to the world so they can understand. And now I feel like I have, and people connect with it because I’m just being true to myself. But I kind of feel like I don’t like when people say that they’re a flop. I don’t say that, you know what I mean? Don’t manifest it. No, because it doesn’t matter, what even is that, you know?

Zara Larsson answers what was the key to getting out of the Khia Asylum. “I’ve always known I’m a cool girl. I think my taste is good or fun, it’s my taste. I like what I do. I just need to express it to the world so they can understand. And now I feel like I have, and people connect with it because I’m just being true to myself. But I kind of feel like I don’t like when people say that they’re a flop. I don’t say that, you know what I mean? Don’t manifest it. No, because it doesn’t matter, what even is that, you know?

Updates Zara Larsson

30,001 Aufrufe • vor 6 Monaten

I screened this latest AI short in Paris for the Prompt Club alongside a great showcase for French AI filmmaking talent. I think we have reached a tipping point where the quality of the models is no longer an obstacle to telling the story. Sure, there are problems with detail at distance, dynamic movement, and more than one character speaking or doing complex movement at the same time but nothing a director with awareness of the models can’t overcome. Kling motion control is a massive unlock, in this short I am playing all the characters so it’s quite broad because I am not an actor, but I have seen it used with professional actors and it captures real nuanced human performance, with everything that brings. I will be employing professional actors for my films in the future. This was made predominantly with Kling 2.5, and 2.6 motion with some seedance shots on the wider 2-shots. We are there, now go make your thing!

I screened this latest AI short in Paris for the Prompt Club alongside a great showcase for French AI filmmaking talent. I think we have reached a tipping point where the quality of the models is no longer an obstacle to telling the story. Sure, there are problems with detail at distance, dynamic movement, and more than one character speaking or doing complex movement at the same time but nothing a director with awareness of the models can’t overcome. Kling motion control is a massive unlock, in this short I am playing all the characters so it’s quite broad because I am not an actor, but I have seen it used with professional actors and it captures real nuanced human performance, with everything that brings. I will be employing professional actors for my films in the future. This was made predominantly with Kling 2.5, and 2.6 motion with some seedance shots on the wider 2-shots. We are there, now go make your thing!

Uncanny Harry AI

10,292 Aufrufe • vor 8 Monaten

🚨🚨🚨 I can’t guarantee that this is true and accurate, but I haven’t seen anything to the contrary, and based on another video, they were taking swift action! I’m hoping this is accurate and that Ilhan Omar will soon be in handcuffs!!!

🚨🚨🚨 I can’t guarantee that this is true and accurate, but I haven’t seen anything to the contrary, and based on another video, they were taking swift action! I’m hoping this is accurate and that Ilhan Omar will soon be in handcuffs!!!

NancyH

71,715 Aufrufe • vor 9 Monaten

My humble little work is finally complete. Somehow, it ended up becoming an epic 6 minutes and 24 seconds long. In my twenties, I dreamed of becoming a film director, but I failed. Since then, I haven’t really been able to make anything I could truly call a “work.” Now I live quietly as a poor, single, middle-aged man of 52. But in recent years — especially with the evolution of video-generating AI this year — I’ve found myself able to create something again, and that makes me truly happy. To everyone who has watched over the madness of this 52-year-old guy with such lukewarm kindness: thank you from the bottom of my heart. As long as luck stays on my side, I intend to keep making new works, so I hope you’ll continue to put up with me. For this piece, I aimed for the kind of taste found in films I personally love: Tarantino and Rodriguez’s Grindhouse. I wanted to make a ridiculous B-movie-style piece of entertainment — something stupid, wild, and only possible through AI. With the rapid evolution of video-generating AI, I think flashy, over-the-top imagery will soon become old hat. So before that happens, I wanted to make one completely outrageous work. Production period: just over one month Budget: I used so many credits that I’d rather not think about it. AI tools used: About 90% of the video was made with Kling 3.0 Omni. Seedance 2.0 was announced partway through production, which made me hesitate, but in the end I only used it very sparingly, for the few parts I just couldn’t express with Kling. From here on, it will become normal to create footage that looks incredibly natural and impressive. In that sense, I also feel that when I look back on this later, the slight traces of “AI-ness” that remain may actually give it a certain charm. I know that only a very rare and generous few will watch a video over six minutes long made by an amateur. But as the film goes on, I became more and more familiar with how to use Kling 3.0 Omni and how to work with its quirks, so I believe the quality improves toward the latter half. Nothing would make me happier than if you stayed with it until the very end.

My humble little work is finally complete. Somehow, it ended up becoming an epic 6 minutes and 24 seconds long. In my twenties, I dreamed of becoming a film director, but I failed. Since then, I haven’t really been able to make anything I could truly call a “work.” Now I live quietly as a poor, single, middle-aged man of 52. But in recent years — especially with the evolution of video-generating AI this year — I’ve found myself able to create something again, and that makes me truly happy. To everyone who has watched over the madness of this 52-year-old guy with such lukewarm kindness: thank you from the bottom of my heart. As long as luck stays on my side, I intend to keep making new works, so I hope you’ll continue to put up with me. For this piece, I aimed for the kind of taste found in films I personally love: Tarantino and Rodriguez’s Grindhouse. I wanted to make a ridiculous B-movie-style piece of entertainment — something stupid, wild, and only possible through AI. With the rapid evolution of video-generating AI, I think flashy, over-the-top imagery will soon become old hat. So before that happens, I wanted to make one completely outrageous work. Production period: just over one month Budget: I used so many credits that I’d rather not think about it. AI tools used: About 90% of the video was made with Kling 3.0 Omni. Seedance 2.0 was announced partway through production, which made me hesitate, but in the end I only used it very sparingly, for the few parts I just couldn’t express with Kling. From here on, it will become normal to create footage that looks incredibly natural and impressive. In that sense, I also feel that when I look back on this later, the slight traces of “AI-ness” that remain may actually give it a certain charm. I know that only a very rare and generous few will watch a video over six minutes long made by an amateur. But as the film goes on, I became more and more familiar with how to use Kling 3.0 Omni and how to work with its quirks, so I believe the quality improves toward the latter half. Nothing would make me happier than if you stayed with it until the very end.

落花生BOY【AI映画作家】

24,310 Aufrufe • vor 5 Monaten

Josh Allen says he isn’t surprised by his success “This is the only life that I’ve ever pictured for myself, being an NFL quarterback. So surprise maybe is not the right word.” “With all the stuff, I didn’t realize that it comes with a lot of different things,the fame, if you will. But I don’t really pay attention to that.” “I just love playing football and I love being around my teammates. I literally try to keep it as simple as that.” “I get to do what I’ve always loved doing for an actual job, and it’s the best job in the world. Meetings are intense, practice is intense, but the downtime that you have in the building is the most fun thing I can think of to actually get paid to do.” “I just love it. I just love it. So, not surprised, but I am grateful.”

Josh Allen says he isn’t surprised by his success “This is the only life that I’ve ever pictured for myself, being an NFL quarterback. So surprise maybe is not the right word.” “With all the stuff, I didn’t realize that it comes with a lot of different things,the fame, if you will. But I don’t really pay attention to that.” “I just love playing football and I love being around my teammates. I literally try to keep it as simple as that.” “I get to do what I’ve always loved doing for an actual job, and it’s the best job in the world. Meetings are intense, practice is intense, but the downtime that you have in the building is the most fun thing I can think of to actually get paid to do.” “I just love it. I just love it. So, not surprised, but I am grateful.”

Josh Chambers

259,209 Aufrufe • vor 21 Tagen