Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

i generated this video using two blurry pics of myself from two years ago at griffith observatory with the MiniMax H3 model. it's surprisingly natural and sounds really close to how i actually speak. i haven't followed video generation models enough in the past year, but i'm really curious...

VoidAsuka's profile picture

Asuka Zheng🎀

24,308 subscribers

20,068 görüntüleme • 10 gün önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

Hailuo / MiniMax H3 is here! 🚀 Just ran my first experiment with the new H3 model using an idea I previously tested on the 2.3 version — and the results are surprisingly impressive. This was a true one-shot generation: first attempt, no retries, no selecting the best take. More experiments coming soon as I explore what H3 can really do. 🔥 Diving deeper into Hailuo AI (MiniMax) ✨ #MiniMaxH3
0:12

Hailuo / MiniMax H3 is here! 🚀 Just ran my first experiment with the new H3 model using an idea I previously tested on the 2.3 version — and the results are surprisingly impressive. This was a true one-shot generation: first attempt, no retries, no selecting the best take. More experiments coming soon as I explore what H3 can really do. 🔥 Diving deeper into Hailuo AI (MiniMax) ✨ #MiniMaxH3

Anissa

14,609 görüntüleme • 10 gün önce

🎥 Comparing AI video models: Image to video • Gen-3 • Kling AI 1.5 • Hailuo MiniMax • Luma Dream Machine I used a Midjourney image in each model 4 times with no text prompt. This type of image is difficult for the AI to separate the subject in the front from the people behind her - they tend to move the group as if they are a single unit. But the results were interesting, as you can see! I chose my favorite results, below.
0:10

🎥 Comparing AI video models: Image to video • Gen-3 • Kling AI 1.5 • Hailuo MiniMax • Luma Dream Machine I used a Midjourney image in each model 4 times with no text prompt. This type of image is difficult for the AI to separate the subject in the front from the people behind her - they tend to move the group as if they are a single unit. But the results were interesting, as you can see! I chose my favorite results, below.

Heather Cooper

41,354 görüntüleme • 1 yıl önce

Yesterday someone suggested I create a fight between Alucard and Drolta Tzuentes using Kling AI 2.6. I usually work with Text to Video, but in this case I had to use Image to Video. The base image is a fusion of two images created in Niji and combined with GPT Image 1.5. Then I added the right prompt to give the fight speed and dynamism. The result isn’t perfect, but it’s pretty cool.
0:10

Yesterday someone suggested I create a fight between Alucard and Drolta Tzuentes using Kling AI 2.6. I usually work with Text to Video, but in this case I had to use Image to Video. The base image is a fusion of two images created in Niji and combined with GPT Image 1.5. Then I added the right prompt to give the fight speed and dynamism. The result isn’t perfect, but it’s pretty cool.

OscarAI

18,533 görüntüleme • 7 ay önce

🎬Comparing AI video models with no prompt: • Gen-3 • Kling AI 1.5 • Hailuo MiniMax • Luma Dream Machine I used a Midjourney image in each model 3 times with no text prompt. I chose my favorite results, below. Sometimes I test certain images with no prompt to see how creative the models can be. Take a look at the results, but don't just focus on how much movement there is - pay attention to what is actually moving. The fog/mist adds to the dramatic effect:
0:10

🎬Comparing AI video models with no prompt: • Gen-3 • Kling AI 1.5 • Hailuo MiniMax • Luma Dream Machine I used a Midjourney image in each model 3 times with no text prompt. I chose my favorite results, below. Sometimes I test certain images with no prompt to see how creative the models can be. Take a look at the results, but don't just focus on how much movement there is - pay attention to what is actually moving. The fog/mist adds to the dramatic effect:

Heather Cooper

29,138 görüntüleme • 1 yıl önce

Google dropped a new AI paper called LUMIERE. It's remarkably flexible, supporting video inpainting, image-to-video, AND stylized video generation tasks. Say hello to “space-time diffusion” for video generation! Now what the heck does that mean exactly?! 🌐⏳ → TL;DR it utilizes a “Space-Time UNet” architecture that generates the full duration of the video in one pass, rather than generating distant keyframes and interpolating between them like prior works. Because the computation is done in this “compressed space-time representation” to generate the full clip at once, it's far more temporally consistent. → Another benefit of generating the full video at once is that you can “direct” the video generation, making it easier to hand off to other models/tasks without having to stitch together partial solutions. You can condition generations on additional inputs, meaning you get the full stack of AI video capabilities – from video inpainting to image-to-video and beyond. → New SOTA for AI video generation? User study results in the paper suggest human evaluators preferred Lumiere over Runway Gen-2, Pika Labs, and Stable Video Diffusion in terms of quality, text alignment AND motion. But as always, we need to get hands-on with this tech when Google *actually* decides to ship it. → Could this end up inside YouTube? Y’all know i’m obsessed with blending reality and imagination – so it’s the video inpainting tech I'm most excited about. I really hope this model finds its way into YouTube's Generative AI efforts, and based on their prior announcements and the list of acknowledgments in the paper I think it might! 🤞🏽 Links: 🔗Paper: 🔗Project:
0:13

Google dropped a new AI paper called LUMIERE. It's remarkably flexible, supporting video inpainting, image-to-video, AND stylized video generation tasks. Say hello to “space-time diffusion” for video generation! Now what the heck does that mean exactly?! 🌐⏳ → TL;DR it utilizes a “Space-Time UNet” architecture that generates the full duration of the video in one pass, rather than generating distant keyframes and interpolating between them like prior works. Because the computation is done in this “compressed space-time representation” to generate the full clip at once, it's far more temporally consistent. → Another benefit of generating the full video at once is that you can “direct” the video generation, making it easier to hand off to other models/tasks without having to stitch together partial solutions. You can condition generations on additional inputs, meaning you get the full stack of AI video capabilities – from video inpainting to image-to-video and beyond. → New SOTA for AI video generation? User study results in the paper suggest human evaluators preferred Lumiere over Runway Gen-2, Pika Labs, and Stable Video Diffusion in terms of quality, text alignment AND motion. But as always, we need to get hands-on with this tech when Google *actually* decides to ship it. → Could this end up inside YouTube? Y’all know i’m obsessed with blending reality and imagination – so it’s the video inpainting tech I'm most excited about. I really hope this model finds its way into YouTube's Generative AI efforts, and based on their prior announcements and the list of acknowledgments in the paper I think it might! 🤞🏽 Links: 🔗Paper: 🔗Project:

Bilawal Sidhu

44,822 görüntüleme • 2 yıl önce

Comparing AI video results: • Gen-3 • Kling AI 1.5 • Hailuo MiniMax • Luma Dream Machine I used a FLUX1.1 [pro] image as the input. Each model ran the same prompt 3 times, and I chose the best results: "Smooth side tracking shot of a woman jogging at twilight with the city skyline in the background, sharp focus on the woman as she pumps her arms with each stride as she jogs, depth of field, advertising commercial" Running, jogging, and walking are difficult for AI video models, and none of them produced a smooth result, but this is the worst they will be.
0:10

Comparing AI video results: • Gen-3 • Kling AI 1.5 • Hailuo MiniMax • Luma Dream Machine I used a FLUX1.1 [pro] image as the input. Each model ran the same prompt 3 times, and I chose the best results: "Smooth side tracking shot of a woman jogging at twilight with the city skyline in the background, sharp focus on the woman as she pumps her arms with each stride as she jogs, depth of field, advertising commercial" Running, jogging, and walking are difficult for AI video models, and none of them produced a smooth result, but this is the worst they will be.

Heather Cooper

57,672 görüntüleme • 1 yıl önce

I didn’t expect Grok’s video model to improve this much. Today, when I was generating a video with Seedance 2.0, I found the results weren’t very good. So I tried using the exact same source material and prompt in Grok instead. To my surprise, Grok actually produced better results than Seedance 2.0. I’ve put the prompt and source material in the comments, so if you’re interested, you can give it a try too. The left side shows the video generated by Grok, and the right side shows the video generated by Seedance 2.0.
0:10

I didn’t expect Grok’s video model to improve this much. Today, when I was generating a video with Seedance 2.0, I found the results weren’t very good. So I tried using the exact same source material and prompt in Grok instead. To my surprise, Grok actually produced better results than Seedance 2.0. I’ve put the prompt and source material in the comments, so if you’re interested, you can give it a try too. The left side shows the video generated by Grok, and the right side shows the video generated by Seedance 2.0.

underwood

34,518 görüntüleme • 4 ay önce

7M views on instagram IN A MONTH i have this account where i found the format that works best, all organic, no ads at all a video of my face with some question-text, some trending song and with a duration of 7-8 seconds it's always the same format, i haven't even followed anyone else but NASA (since i'm going up lol) i mostly post them as trials and then if they get more than 50k views, i share them to everyone copy the format and see if it works for you too let's grow your MRR, let's see what really works will keep you updated
0:16

7M views on instagram IN A MONTH i have this account where i found the format that works best, all organic, no ads at all a video of my face with some question-text, some trending song and with a duration of 7-8 seconds it's always the same format, i haven't even followed anyone else but NASA (since i'm going up lol) i mostly post them as trials and then if they get more than 50k views, i share them to everyone copy the format and see if it works for you too let's grow your MRR, let's see what really works will keep you updated

Guillem

13,399 görüntüleme • 1 ay önce

So remember that time machine I told you about? I managed to sneek out another video from my visit to the future.. this time I captured video of a 3d artist creating assets for a short commercial. They sculpted the bird in the video with nothing but two controllers which they used to manipulate generative matter in 3d. The AI model changed in realtime and adopted their style of work, both based on the work they did on the scene, and on reference images they gave the system. Seeing the 3d model transform in realtime as they were working on it was incredible. When it started moving and reacted to their instructions, I knew it was time to return to the present :D #art #ai
0:16

So remember that time machine I told you about? I managed to sneek out another video from my visit to the future.. this time I captured video of a 3d artist creating assets for a short commercial. They sculpted the bird in the video with nothing but two controllers which they used to manipulate generative matter in 3d. The AI model changed in realtime and adopted their style of work, both based on the work they did on the scene, and on reference images they gave the system. Seeing the 3d model transform in realtime as they were working on it was incredible. When it started moving and reacted to their instructions, I knew it was time to return to the present :D #art #ai

Martin Nebelong

22,044 görüntüleme • 2 yıl önce

Today marks two years from the first stump job I ever completed. This is a video from the night before (August 6th, 2024.) Rental trailer and machine locked and loaded. Didn’t really know how to use the machine. You can hear the nervousness in my voice.😂 Since then I’ve done $505,375 worth of stumps. You have to start somewhere!
0:14

Today marks two years from the first stump job I ever completed. This is a video from the night before (August 6th, 2024.) Rental trailer and machine locked and loaded. Didn’t really know how to use the machine. You can hear the nervousness in my voice.😂 Since then I’ve done $505,375 worth of stumps. You have to start somewhere!

Tyler Mumford - The Stump Guy

14,349 görüntüleme • 2 gün önce

I managed to add lip sync with audio but somehow I can't change the audio in this model so it's stuck at Neil Degrassi Tyson 😂 But okay we have a proof of concept, from AI pic -> AI video -> AI lipsync'd I wanted to add an AI voice, anyone know how to make the audio work on this model? Chenxi Whitehouse
0:10

I managed to add lip sync with audio but somehow I can't change the audio in this model so it's stuck at Neil Degrassi Tyson 😂 But okay we have a proof of concept, from AI pic -> AI video -> AI lipsync'd I wanted to add an AI voice, anyone know how to make the audio work on this model? Chenxi Whitehouse

@levelsio

98,610 görüntüleme • 2 yıl önce

i still remember when jungkook went to qatar to perform at the fifa world cup by himself and how his hyungs supported him from their home, now all of them are coheadlining at the world cup together. we really came a long way.
0:11

i still remember when jungkook went to qatar to perform at the fifa world cup by himself and how his hyungs supported him from their home, now all of them are coheadlining at the world cup together. we really came a long way.

vani⁷

43,111 görüntüleme • 2 ay önce

so, i might have been wrong.... i've been looking into AI UGC a little bit more and it's actually kind of insane the video you see below took $2 to make and the only visible problem (might) be the audio i know ecom brands using ai ugc for there organic and paid doing over $1M/mo i'm still bullish on real human clipping and ai content but considering how much ai ugc has improved over the last few months... it's going to be interesting to see how the content marketing world changes this year
0:17

so, i might have been wrong.... i've been looking into AI UGC a little bit more and it's actually kind of insane the video you see below took $2 to make and the only visible problem (might) be the audio i know ecom brands using ai ugc for there organic and paid doing over $1M/mo i'm still bullish on real human clipping and ai content but considering how much ai ugc has improved over the last few months... it's going to be interesting to see how the content marketing world changes this year

Alex

24,711 görüntüleme • 3 ay önce

⏳ I saw fofr using Flux Kontext to restore old photos So I tried to restore the oldest photo in the world with people on it from 1838 186 years ago in Paris It works remarkably well and seems to stay quite close to the original Then I turned it into a video with Kling AI 2.1 and added background sounds with ElevenLabs Video-to-SFX model Actually feels like you can travel back in time a bit now I've always hated black and white photos with a passion because it makes history look very far away when it's not, much of the world looked very much the same as it does today, especially in historical places like Paris
0:10

⏳ I saw fofr using Flux Kontext to restore old photos So I tried to restore the oldest photo in the world with people on it from 1838 186 years ago in Paris It works remarkably well and seems to stay quite close to the original Then I turned it into a video with Kling AI 2.1 and added background sounds with ElevenLabs Video-to-SFX model Actually feels like you can travel back in time a bit now I've always hated black and white photos with a passion because it makes history look very far away when it's not, much of the world looked very much the same as it does today, especially in historical places like Paris

@levelsio

429,190 görüntüleme • 1 yıl önce

Most AI video generators can animate a product. Keeping it accurate is another story. I tested Pollo AI Commerce Studio with a Versace perfume listing and was impressed by how well it preserved the original product. The bottle looked consistent from scene to scene, with accurate colors, recognizable branding, and details that stayed true to the original image throughout the video. The final result felt more like a luxury fragrance commercial than an AI-generated video. With over 100 templates and no prompts required, creating high-quality product videos feels surprisingly effortless.
0:10

Most AI video generators can animate a product. Keeping it accurate is another story. I tested Pollo AI Commerce Studio with a Versace perfume listing and was impressed by how well it preserved the original product. The bottle looked consistent from scene to scene, with accurate colors, recognizable branding, and details that stayed true to the original image throughout the video. The final result felt more like a luxury fragrance commercial than an AI-generated video. With over 100 templates and no prompts required, creating high-quality product videos feels surprisingly effortless.

Calira

28,965 görüntüleme • 1 ay önce

It’s my big day! (No, not my birthday; this is way more important to me.) Two years since I chose myself and the generations after me. I’m on the precipice of my new career in polysomnography, and I’m celebrating this win, these wins actually , being alcohol free and now completely sober has really contributed to all my other accomplishments as of late . See y’all when I hit five on all these and I’m so serious 😌. (I would post the whole video but it’s so lengthy I may redo it for a different platform when I find the time to)
0:00

It’s my big day! (No, not my birthday; this is way more important to me.) Two years since I chose myself and the generations after me. I’m on the precipice of my new career in polysomnography, and I’m celebrating this win, these wins actually , being alcohol free and now completely sober has really contributed to all my other accomplishments as of late . See y’all when I hit five on all these and I’m so serious 😌. (I would post the whole video but it’s so lengthy I may redo it for a different platform when I find the time to)

Bri 💋

21,878 görüntüleme • 1 yıl önce

Yongha 🫧 - 260405 😸: Donating the chin-ups we used to use in the practice room. Are you doing a good job, guys? Can I send you a chin-up video? How do I get rid of the sound? LOL It's such a long time ago. I'm fat now. Do I look like a chicken? I was skinny back then, but I'm going to eat and exercise from now on. #WEi #YOOYONGHA #위아이 #유용하 #ヨンハ
0:11

Yongha 🫧 - 260405 😸: Donating the chin-ups we used to use in the practice room. Are you doing a good job, guys? Can I send you a chin-up video? How do I get rid of the sound? LOL It's such a long time ago. I'm fat now. Do I look like a chicken? I was skinny back then, but I'm going to eat and exercise from now on. #WEi #YOOYONGHA #위아이 #유용하 #ヨンハ

𝑴𝒊𝒔𝒔 𝒀𝒐𝒐 (유샌디) ₍ᐢ.ˬ.ᐡ₎♡ᵎᵎᵎ

15,795 görüntüleme • 4 ay önce

The whole process of putting together the "I hate cowboys" record and the "go down singin'" record was a long two years of figuring out how do something I've never done before. All the songs were written on guitar and a depth I haven't really hit before. This is the final piece of that puzzle. "The fireside sessions" are both those albums together, all acoustic, featuring the songwriters from both those records. This time in my career ends with both album covers together with me and my dad standing next to each other. It's the first time I've ever been able to see a picture of us as two grown men. I'm moving on to another album early next year, but I hope y'all love these versions of the songs, as they were written. The bluebird last night was a special way to celebrate the ending of these last two years, and the start of something new👏🏼
0:16

The whole process of putting together the "I hate cowboys" record and the "go down singin'" record was a long two years of figuring out how do something I've never done before. All the songs were written on guitar and a depth I haven't really hit before. This is the final piece of that puzzle. "The fireside sessions" are both those albums together, all acoustic, featuring the songwriters from both those records. This time in my career ends with both album covers together with me and my dad standing next to each other. It's the first time I've ever been able to see a picture of us as two grown men. I'm moving on to another album early next year, but I hope y'all love these versions of the songs, as they were written. The bluebird last night was a special way to celebrate the ending of these last two years, and the start of something new👏🏼

Chase Rice

24,346 görüntüleme • 1 yıl önce

✨ Made a new mini feature on Photo AI: [ Grab from 3d model ] So the problem is we're at that stage in time (typical for AI) where image-to-3d models are not good enough but are fun to play with, but we know they'll be good enough in 1-2 years With [ Make 3d model ] you already can turn any Photo AI pic into a 3d model but it still looks hyper clunky and deformed, but it works! One cool idea I had to make that more useful and made now: Let people make a 3d model then change the view of the it with the 3d viewer, then press [ o ] and it grabs a frame of the 3d That image you can then [ Remix ] (img2img), and it becomes a real photo again and that in turn you can then turn into a video again with [ Make video ] So that essentially gives you a fully freeform camera position control to take photos with One thing I need to fix is the background/skybox, I kinda need to take the original photo and remove the person and just get the background for the 3d model viewer, in this case it should be white, but it's a start!
0:51

✨ Made a new mini feature on Photo AI: [ Grab from 3d model ] So the problem is we're at that stage in time (typical for AI) where image-to-3d models are not good enough but are fun to play with, but we know they'll be good enough in 1-2 years With [ Make 3d model ] you already can turn any Photo AI pic into a 3d model but it still looks hyper clunky and deformed, but it works! One cool idea I had to make that more useful and made now: Let people make a 3d model then change the view of the it with the 3d viewer, then press [ o ] and it grabs a frame of the 3d That image you can then [ Remix ] (img2img), and it becomes a real photo again and that in turn you can then turn into a video again with [ Make video ] So that essentially gives you a fully freeform camera position control to take photos with One thing I need to fix is the background/skybox, I kinda need to take the original photo and remove the person and just get the background for the 3d model viewer, in this case it should be white, but it's a start!

@levelsio

119,210 görüntüleme • 1 yıl önce