正在加载视频...

视频加载失败

返回首页

Hollywood isn't dead. It's evolving. And we're leading that evolution. We just shipped Koyal v2.5: The best Agentic AI filmmaking platform. It goes from your script or music to full video with consistent characters, settings & storylines. Large Production houses, music labels & ad agencies use koyal.ai (YC F25)...

meh_agarwal's profile picture

Mehul Agarwal

3,406 subscribers

74,331 次观看 • 4 个月前 •via X (Twitter)

科学技术
LIVE

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Stop begging a model for magic. Start directing. Koyal is an agentic AI filmmaking platform It turns a script - or even raw audio - into a film you can cut, recut, and release It starts where filmmakers start: performance Then agents do what a crew would: scenes, shots, retakes Multilingual script → audio → video Agentic lip-sync with believable motion Characters that stay themselves across scenes Because real directors don’t “prompt” a movie They write. Perform. Reshoot. Koyal brings AI to that century-old workflow 🎙️ Mehul Agarwal, Co-founder & CEO koyal.ai (YC F25) on Fondo.com Start 00:00 Intro to Mehul and Koyal “Agentic AI filmmaking platform” 01:10 Most exciting videos on the platform 01:34 Music video and filming at a UNESCO site with AI 02:55 Origin story from text-to-3D gaming startup to AI filmmaking 03:24 The early days of Stable Diffusion, Midjourney, and the AI image explosion 04:22 Why the gaming industry is a "thankless" place for startups 04:50 "why isn't this a startup?" moment 05:15 meme pages, standup comedy, and scriptwriting 07:08 How Koyal works: the "Pixar process" without a camera 08:30 Launching the first video hackathon at YC 10:47 Where to follow and try Koyal
13:09

Stop begging a model for magic. Start directing. Koyal is an agentic AI filmmaking platform It turns a script - or even raw audio - into a film you can cut, recut, and release It starts where filmmakers start: performance Then agents do what a crew would: scenes, shots, retakes Multilingual script → audio → video Agentic lip-sync with believable motion Characters that stay themselves across scenes Because real directors don’t “prompt” a movie They write. Perform. Reshoot. Koyal brings AI to that century-old workflow 🎙️ Mehul Agarwal, Co-founder & CEO koyal.ai (YC F25) on Fondo.com Start 00:00 Intro to Mehul and Koyal “Agentic AI filmmaking platform” 01:10 Most exciting videos on the platform 01:34 Music video and filming at a UNESCO site with AI 02:55 Origin story from text-to-3D gaming startup to AI filmmaking 03:24 The early days of Stable Diffusion, Midjourney, and the AI image explosion 04:22 Why the gaming industry is a "thankless" place for startups 04:50 "why isn't this a startup?" moment 05:15 meme pages, standup comedy, and scriptwriting 07:08 How Koyal works: the "Pixar process" without a camera 08:30 Launching the first video hackathon at YC 10:47 Where to follow and try Koyal

David J Phillips

25,753 次观看 • 6 个月前

i built a way to make full ai films with seedance 2.5 + higgsfield without shooting a single frame in real life you start with a screenplay, a treatment, or even just an idea and it gives you an actual production plan: scenes, shots, character references, locations, dialogue, b-roll, sound, captions, everything you need to turn it into a finished film this was supposed to stay internal but f*ck it, i’m sharing the whole workflow here’s how it works: the script gets broken down scene by scene, then every scene gets turned into a proper shot list with prompts that account for character continuity, wardrobe, lighting, locations, camera movement, pacing, and what needs to happen before and after that shot those prompts get run through seedance 2.5, using reference assets and longer generations to keep the film feeling like one world instead of a thousand random ai clips stitched together then the footage gets assembled with voice, sound design, music, dialogue, captions, and transitions into an actual watchable film the whole system is built to take you from script to a finished film seedance 2.5 is coming soon on higgsfield, but i’m sharing the full breakdown before it so you can be prepared: the script-to-scene system that turns a screenplay into a real production plan seedance 2.5 prompt setup for cinematic shots and consistent characters the reference-asset workflow for keeping faces, wardrobe, locations, and visual style locked in the editing, voice, sound, and caption workflow that turns generated clips into a finished movie RT + reply “FILM” and (i’ll send it over must follow so i can dm)
0:39

i built a way to make full ai films with seedance 2.5 + higgsfield without shooting a single frame in real life you start with a screenplay, a treatment, or even just an idea and it gives you an actual production plan: scenes, shots, character references, locations, dialogue, b-roll, sound, captions, everything you need to turn it into a finished film this was supposed to stay internal but f*ck it, i’m sharing the whole workflow here’s how it works: the script gets broken down scene by scene, then every scene gets turned into a proper shot list with prompts that account for character continuity, wardrobe, lighting, locations, camera movement, pacing, and what needs to happen before and after that shot those prompts get run through seedance 2.5, using reference assets and longer generations to keep the film feeling like one world instead of a thousand random ai clips stitched together then the footage gets assembled with voice, sound design, music, dialogue, captions, and transitions into an actual watchable film the whole system is built to take you from script to a finished film seedance 2.5 is coming soon on higgsfield, but i’m sharing the full breakdown before it so you can be prepared: the script-to-scene system that turns a screenplay into a real production plan seedance 2.5 prompt setup for cinematic shots and consistent characters the reference-asset workflow for keeping faces, wardrobe, locations, and visual style locked in the editing, voice, sound, and caption workflow that turns generated clips into a finished movie RT + reply “FILM” and (i’ll send it over must follow so i can dm)

Sulfur

47,302 次观看 • 7 天前

Grok Imagine gives you complete control over your videos, letting you direct the camera's movement, control your character's actions, script their dialogue, and manage how objects in the scene interact. Your characters can smash objects, swing a bat, or walk out of a room. To build seamless videos, start by extracting the last frame from your current clip and using it as the starting frame for the next one.
0:29

Grok Imagine gives you complete control over your videos, letting you direct the camera's movement, control your character's actions, script their dialogue, and manage how objects in the scene interact. Your characters can smash objects, swing a bat, or walk out of a room. To build seamless videos, start by extracting the last frame from your current clip and using it as the starting frame for the next one.

tetsuo

26,461 次观看 • 10 个月前

i built a way to generate realistic AI influencer vlogs without ever touching a camera. this was supposed to stay internal but f*ck it, i'm leaking the entire production system. pick any topic. or paste in a script. a few minutes later you've got a finished influencer-style vlog with: > a consistent AI character > cinematic shots > natural dialogue > realistic iPhone footage > b-roll here's how it works: the workflow first breaks your script into a complete scene-by-scene storyboard with timestamps, camera directions, dialogue, environments, pacing, and shot planning so every clip has a purpose instead of feeling randomly generated. each scene gets its own reference image prompt for Higgsfield that locks the character's identity, clothing, camera angle, lighting, and environment to keep the person looking the same across the entire vlog. those reference images are then animated in Seedance 2.5 using scene-specific prompts that control movement, lip sync, ambient audio, dialogue, camera motion, and timing so every clip feels like it was filmed on an iPhone instead of generated by AI. finally everything gets assembled in CapCut with b-roll, subtitles, transitions, music, pacing, and final polish into a complete vlog that's ready to upload. you're not filming,hiring actors or recording voiceovers. the whole thing goes from idea → finished AI influencer vlog. the document i'm sharing includes: > the complete scene breakdown framework > every Higgsfield image prompt > every Seedance 2.5 animation prompt > dialogue for every scene > b-roll prompts > editing workflow inside capcut > structural notes that make the vlog feel real instead of AI RT + reply "AI VLOG", i'll DM you the entire production blueprint.(must be following so i can DM.)
2:30

i built a way to generate realistic AI influencer vlogs without ever touching a camera. this was supposed to stay internal but f*ck it, i'm leaking the entire production system. pick any topic. or paste in a script. a few minutes later you've got a finished influencer-style vlog with: > a consistent AI character > cinematic shots > natural dialogue > realistic iPhone footage > b-roll here's how it works: the workflow first breaks your script into a complete scene-by-scene storyboard with timestamps, camera directions, dialogue, environments, pacing, and shot planning so every clip has a purpose instead of feeling randomly generated. each scene gets its own reference image prompt for Higgsfield that locks the character's identity, clothing, camera angle, lighting, and environment to keep the person looking the same across the entire vlog. those reference images are then animated in Seedance 2.5 using scene-specific prompts that control movement, lip sync, ambient audio, dialogue, camera motion, and timing so every clip feels like it was filmed on an iPhone instead of generated by AI. finally everything gets assembled in CapCut with b-roll, subtitles, transitions, music, pacing, and final polish into a complete vlog that's ready to upload. you're not filming,hiring actors or recording voiceovers. the whole thing goes from idea → finished AI influencer vlog. the document i'm sharing includes: > the complete scene breakdown framework > every Higgsfield image prompt > every Seedance 2.5 animation prompt > dialogue for every scene > b-roll prompts > editing workflow inside capcut > structural notes that make the vlog feel real instead of AI RT + reply "AI VLOG", i'll DM you the entire production blueprint.(must be following so i can DM.)

Sulfur

69,649 次观看 • 4 天前

Get any camera move you want, using just your phone. Frame the shot, hit record, and move your camera exactly how you want it - a simple pan, a push-in and swirl, whatever. Load that clip into Agent One and tell it what you want in the shot. Your recorded video drives the camera move, Agent One runs it through Seedance, and you sit back and watch. Pro tip - match your phone frame to your first generated frame. The closer it lines up, the better it lands. Watch the video to see exactly how we did it.
0:49

Get any camera move you want, using just your phone. Frame the shot, hit record, and move your camera exactly how you want it - a simple pan, a push-in and swirl, whatever. Load that clip into Agent One and tell it what you want in the shot. Your recorded video drives the camera move, Agent One runs it through Seedance, and you sit back and watch. Pro tip - match your phone frame to your first generated frame. The closer it lines up, the better it lands. Watch the video to see exactly how we did it.

Invideo

30,624 次观看 • 1 个月前

✨ 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 次观看 • 1 年前

i built a way to generate full ai vlogs for youtube using seedance 2.5, without ever picking up a camera this was supposed to stay internal but f*ck it, i'm leaking the whole thing you give it a script or even just a topic and it comes back with a finished vlog, voiceover, b-roll, captions, ready to upload here's how it works: a custom claude skill breaks your script into scenes and writes timestamped storyboard prompts for each one, matched to pacing so nothing feels random. those prompts get fed into seedance 2.5, using its 30 second continuous generation and reference asset support to keep the visuals consistent across scenes instead of looking like ten unrelated clips stitched together. then it pulls in an ai voiceover that matches the tone of the script, stitches every scene together, and burns in captions automatically you're not filming, not voicing, not editing, not exporting from three different apps the whole thing runs start to finish and outputs a finished 16:9 vlog ready to post, and it costs a fraction of what an editor or camera setup would run you i'm sharing the full breakdown, which includes: the claude skill that handles scene breakdown and storyboard prompts the seedance 2.5 setup that keeps visuals consistent scene to scene the voiceover setup that keeps it from sounding robotic the exact workflow from script to finished vlog RT + reply "PROMPTS" and i'll send it over (must follow so i can dm)
0:57

i built a way to generate full ai vlogs for youtube using seedance 2.5, without ever picking up a camera this was supposed to stay internal but f*ck it, i'm leaking the whole thing you give it a script or even just a topic and it comes back with a finished vlog, voiceover, b-roll, captions, ready to upload here's how it works: a custom claude skill breaks your script into scenes and writes timestamped storyboard prompts for each one, matched to pacing so nothing feels random. those prompts get fed into seedance 2.5, using its 30 second continuous generation and reference asset support to keep the visuals consistent across scenes instead of looking like ten unrelated clips stitched together. then it pulls in an ai voiceover that matches the tone of the script, stitches every scene together, and burns in captions automatically you're not filming, not voicing, not editing, not exporting from three different apps the whole thing runs start to finish and outputs a finished 16:9 vlog ready to post, and it costs a fraction of what an editor or camera setup would run you i'm sharing the full breakdown, which includes: the claude skill that handles scene breakdown and storyboard prompts the seedance 2.5 setup that keeps visuals consistent scene to scene the voiceover setup that keeps it from sounding robotic the exact workflow from script to finished vlog RT + reply "PROMPTS" and i'll send it over (must follow so i can dm)

Sulfur

237,034 次观看 • 9 天前

🚨BREAKING: The AI studio behind an estimated $110M in global sales just made their cinematic model available to the public. it's called PAI from Utopai Studios. and it works completely different from Sora, Runway, or Kling. you don't type a prompt and hope for the best. you actually direct. What it actually does: → 4K output, 16 shots per sequence → Characters stay consistent across episodes → Post-render editing in plain English → Original character models from references → Scene-level storyboard control → IP protection baked into every frame i got early access and tested it. for long-form AI video, nothing else is even in the same conversation right now. Thanks Utopai Studios for the early access.
0:51

🚨BREAKING: The AI studio behind an estimated $110M in global sales just made their cinematic model available to the public. it's called PAI from Utopai Studios. and it works completely different from Sora, Runway, or Kling. you don't type a prompt and hope for the best. you actually direct. What it actually does: → 4K output, 16 shots per sequence → Characters stay consistent across episodes → Post-render editing in plain English → Original character models from references → Scene-level storyboard control → IP protection baked into every frame i got early access and tested it. for long-form AI video, nothing else is even in the same conversation right now. Thanks Utopai Studios for the early access.

Farhan

102,302 次观看 • 3 个月前

Today, we’re launching a new way to create with AI. With OpenArt Worlds, you can generate a fully navigable 3D environment from a single prompt or image, step inside it, and capture shots exactly the way you envision them. No more starting over. No more inconsistent scenes. You build the world once - and create inside it. • Move through your scene freely • Find your angles • Add characters and elements • Capture production-ready shots
0:53

Today, we’re launching a new way to create with AI. With OpenArt Worlds, you can generate a fully navigable 3D environment from a single prompt or image, step inside it, and capture shots exactly the way you envision them. No more starting over. No more inconsistent scenes. You build the world once - and create inside it. • Move through your scene freely • Find your angles • Add characters and elements • Capture production-ready shots

OpenArt

7,301,887 次观看 • 4 个月前

AI video has a control problem. Most AI tools generate in 2D. Filmmakers think, stage, and direct in 3D. Today we're introducing Flow Studio 3D Editor + Canvas. Build and direct your scene in 3D. Then use Canvas to render and refine the final look with leading AI models. Stay in 2D when speed matters. Move into 3D when you need precision. AI can build the scene. You still call the shots. Start directing:
2:06

AI video has a control problem. Most AI tools generate in 2D. Filmmakers think, stage, and direct in 3D. Today we're introducing Flow Studio 3D Editor + Canvas. Build and direct your scene in 3D. Then use Canvas to render and refine the final look with leading AI models. Stay in 2D when speed matters. Move into 3D when you need precision. AI can build the scene. You still call the shots. Start directing:

Autodesk Flow Studio

34,070 次观看 • 8 天前

We're making a 90-min feature film. Real actors, real sets, real crew, and AI filling in only what the budget can't cover. The one thing we don't have yet is a script. If you've written one, polished it, pitched it, and watched it go nowhere, we want to read it. If we love it, we buy it, and you're in on the whole thing. We want to build it with people who care about it, as much as we do. The whole production runs in public - every workflow, every breakthrough, every failure. The script you stopped pitching might be the one that finally gets made. Don't let it sit in a drawer. Send it over.
0:53

We're making a 90-min feature film. Real actors, real sets, real crew, and AI filling in only what the budget can't cover. The one thing we don't have yet is a script. If you've written one, polished it, pitched it, and watched it go nowhere, we want to read it. If we love it, we buy it, and you're in on the whole thing. We want to build it with people who care about it, as much as we do. The whole production runs in public - every workflow, every breakthrough, every failure. The script you stopped pitching might be the one that finally gets made. Don't let it sit in a drawer. Send it over.

Invideo

68,626 次观看 • 1 个月前

Sharing this Godot quick tip for the new people trying to figure out how to mess with the game while it's running! ✨ (Thanks to Daniel Queiroz Porto and and Ian Williams for pointing this out) 1. Go to the Project Settings 2. Click "Advanced Settings" 3. In "Window" highlight "Always on Top" and create a new editor override for it by choosing "editor" from the list and clicking "Add" 4. Enable the new override you just added 5. Now when you run the scene (Ctrl+R) the window will always stay on top! 6. Press the Camera icon on top of the viewport to sync your editor camera to the game camera 7. Click on the "Remote" tab of the Scene panel. All of the changes you make to these objects will sync with your game in real time! Bonus Tip: You can make it switch to the "Remote" tab by default when you run the game if you go to Editor Settings (Ctrl+Comma) -> Network -> Debugger and click "Auto Switch to Remote Scene Tree"! #godottips
0:42

Sharing this Godot quick tip for the new people trying to figure out how to mess with the game while it's running! ✨ (Thanks to Daniel Queiroz Porto and and Ian Williams for pointing this out) 1. Go to the Project Settings 2. Click "Advanced Settings" 3. In "Window" highlight "Always on Top" and create a new editor override for it by choosing "editor" from the list and clicking "Add" 4. Enable the new override you just added 5. Now when you run the scene (Ctrl+R) the window will always stay on top! 6. Press the Camera icon on top of the viewport to sync your editor camera to the game camera 7. Click on the "Remote" tab of the Scene panel. All of the changes you make to these objects will sync with your game in real time! Bonus Tip: You can make it switch to the "Remote" tab by default when you run the game if you go to Editor Settings (Ctrl+Comma) -> Network -> Debugger and click "Auto Switch to Remote Scene Tree"! #godottips

passivestar

96,110 次观看 • 2 年前

Today we're launching iMessage video ads in Claude. Faceless video is the best-performing ad format right now — and Claude can now generate a full one end to end, in one prompt. Here's how it works: 1. Install: npx gooseworks install --all 2. Run: /goose-video make an iMessage ad for [your product] Claude writes the script, generates the photos in the thread, animates the conversation, and closes on your brand. SFX, music, end card, all of it. The trick: it's just HTML. No video generation models, so it's fast and cheap — and it works because it doesn't look like an ad. It's that easy. But this is just the start. We have created a library with 100+ open-source skills for growth that some of the fastest growing startups in the world are using every day to run ads, content, competitor research, gtm, seo and more. Comment Goose and I'll DM you the full open-source skill library.
0:28

Today we're launching iMessage video ads in Claude. Faceless video is the best-performing ad format right now — and Claude can now generate a full one end to end, in one prompt. Here's how it works: 1. Install: npx gooseworks install --all 2. Run: /goose-video make an iMessage ad for [your product] Claude writes the script, generates the photos in the thread, animates the conversation, and closes on your brand. SFX, music, end card, all of it. The trick: it's just HTML. No video generation models, so it's fast and cheap — and it works because it doesn't look like an ad. It's that easy. But this is just the start. We have created a library with 100+ open-source skills for growth that some of the fastest growing startups in the world are using every day to run ads, content, competitor research, gtm, seo and more. Comment Goose and I'll DM you the full open-source skill library.

Soham Mehta

49,849 次观看 • 1 个月前

Runway Characters are now available in the Runway iOS app. Have a conversation on the go. Or point your camera at the world and talk to a character that can actually see what you see. Try it today at the link below.
0:58

Runway Characters are now available in the Runway iOS app. Have a conversation on the go. Or point your camera at the world and talk to a character that can actually see what you see. Try it today at the link below.

Runway

17,551 次观看 • 4 个月前

The AI video content being made with the Google Gemini is blowing our minds¹ 🤯 With our latest #PixelDrop, you can now upload images directly from your camera roll, enter a prompt to describe a scene, and let Gemini bring it all to life:²
1:23

The AI video content being made with the Google Gemini is blowing our minds¹ 🤯 With our latest #PixelDrop, you can now upload images directly from your camera roll, enter a prompt to describe a scene, and let Gemini bring it all to life:²

Made by Google

44,608 次观看 • 1 年前

Security Camera App: DVR Recorded Video Playback Watch this video to see how easy it is to remotely playback recorded video surveillance footage on a Viewtron DVR with the mobile app for iPhone and Android. You can do this at the location of your security camera system using a WIFI connection or remotely over the Internet from anywhere in the world. It's easy to check in on your property using a Viewtron camera system when you are traveling. You can learn more about the Viewtron mobile app here.
2:48

Security Camera App: DVR Recorded Video Playback Watch this video to see how easy it is to remotely playback recorded video surveillance footage on a Viewtron DVR with the mobile app for iPhone and Android. You can do this at the location of your security camera system using a WIFI connection or remotely over the Internet from anywhere in the world. It's easy to check in on your property using a Viewtron camera system when you are traveling. You can learn more about the Viewtron mobile app here.

CCTV Camera Pros

30,806 次观看 • 1 年前

Rick Rubin: "Make what you love, not what you think people will like" "If you want to live in a creative way, which will benefit everything in your life, be a better person in your family, do a better job starting a new business, it's all the same. I don't really know anything about music. It's more a way of looking at the world and wanting it to be the best it could possibly be. And doing whatever it takes to be the best it could possibly be." Rubin shares how his career happened: "From the beginning, I never thought any of the things I'm doing were possible or realistic. I just did things out of the love of them, thinking I would have real jobs. That my passion would be my hobby, and I'd have a job to support my hobby. And it just magically turned out different than that without me knowing it was possible." On why some things connect and others don't: "The stars line up at certain times for certain things to happen. Sometimes you can make something great, and it doesn't connect for whatever reason. Sometimes you make two things you think are the two best things you've ever made. One of them connects with the world. One of them doesn't. And it might not have anything to do with what's in the art. It might be that it came out the same day as something else. Or there was a bigger story at the time. There's so much to it that we don't understand." He continues: "All we can do is make something good and put it out and hope for the best. That's all there is. We never know why things work. Even if you make a piece of art and it works, you may not know why." On talent versus work ethic: "There are a lot of talented people who never make it because they don't have the work ethic. It's not just talent, talent's a piece. And you could argue for some people, the work ethic trumps the talent." Rubin explains what real collaboration is: "Having worked with a lot of bands, I see there's often this friction where people are trying to get their idea in. That's not a collaboration. A real collaboration is when everyone who's there is working together towards whatever is the best thing for the whole. Whether it's your idea or someone else's idea, it doesn't matter. If you're invested in the collaboration, you want the best idea to win. You don't want your idea to win." On what makes art great: "What makes it great is the personal. With all of its imperfections. With all of its quirkiness. That's what makes it great. How you see the world that's different from how everyone else sees the world. That's why you're an artist. That's your purpose in sharing your work with the world." He warns against being derivative: "There are these derivative voices where they're finding what they think other people want to hear, and they start saying it because they've heard other people say similar things that are now successful. Even if they have some short-term success doing that, it's not revolutionary. It doesn't change the world. It doesn't last. The people who you first see and you might not like that you come to like because you don't understand them at first, those are the ones that change the world. Those are the ones you dedicate your fandom to for life." Rubin shares his philosophy on taste: "You can't second-guess your own taste for what someone else is going to like. We're not smart enough to know what someone else is going to like. To make something thinking, 'Well, I don't really like it, but I think this group of people will like it,' it's a bad way to play the game of music or art. You have to do what's personal to you. Take it as far as you can go. Really push the boundaries. And people will resonate with it if they're supposed to resonate with it." He describes creativity as catching waves: "We're really talking about magic. The universe conspiring on our behalf if we let it. Being in this flow of catching these waves that anyone can catch. If you're trying to catch it, you're open to it, you see it coming, you take off on every chance you get. And sometimes the ride happens. It's remarkable how it happens. It doesn't come from preconception. It's not an idea. It's through the doing." Rubin explains how ideas exist in the universe: "Have you ever had that experience where you have an idea for something, you don't do it, and then six months later you see someone else has done it? It's not because they took your idea. It's that it's time for that, and you can act on it or not. The best artists are the ones who have the best antenna for this material that's available. It's coming through. The best comedians see the best jokes. They see them coming. We all live in the same world; the way you see it, you have the best joke because you see it best." He closes with how to stay open: "If we listen to what's going on around us, you can overhear a conversation in a coffee shop, and it is the setup for an idea you're working on. You hear a phrase you don't commonly use. My experience is: when you are open and looking for these clues in the world, they're happening all the time. And they're happening often right when you need them."
8:29

Rick Rubin: "Make what you love, not what you think people will like" "If you want to live in a creative way, which will benefit everything in your life, be a better person in your family, do a better job starting a new business, it's all the same. I don't really know anything about music. It's more a way of looking at the world and wanting it to be the best it could possibly be. And doing whatever it takes to be the best it could possibly be." Rubin shares how his career happened: "From the beginning, I never thought any of the things I'm doing were possible or realistic. I just did things out of the love of them, thinking I would have real jobs. That my passion would be my hobby, and I'd have a job to support my hobby. And it just magically turned out different than that without me knowing it was possible." On why some things connect and others don't: "The stars line up at certain times for certain things to happen. Sometimes you can make something great, and it doesn't connect for whatever reason. Sometimes you make two things you think are the two best things you've ever made. One of them connects with the world. One of them doesn't. And it might not have anything to do with what's in the art. It might be that it came out the same day as something else. Or there was a bigger story at the time. There's so much to it that we don't understand." He continues: "All we can do is make something good and put it out and hope for the best. That's all there is. We never know why things work. Even if you make a piece of art and it works, you may not know why." On talent versus work ethic: "There are a lot of talented people who never make it because they don't have the work ethic. It's not just talent, talent's a piece. And you could argue for some people, the work ethic trumps the talent." Rubin explains what real collaboration is: "Having worked with a lot of bands, I see there's often this friction where people are trying to get their idea in. That's not a collaboration. A real collaboration is when everyone who's there is working together towards whatever is the best thing for the whole. Whether it's your idea or someone else's idea, it doesn't matter. If you're invested in the collaboration, you want the best idea to win. You don't want your idea to win." On what makes art great: "What makes it great is the personal. With all of its imperfections. With all of its quirkiness. That's what makes it great. How you see the world that's different from how everyone else sees the world. That's why you're an artist. That's your purpose in sharing your work with the world." He warns against being derivative: "There are these derivative voices where they're finding what they think other people want to hear, and they start saying it because they've heard other people say similar things that are now successful. Even if they have some short-term success doing that, it's not revolutionary. It doesn't change the world. It doesn't last. The people who you first see and you might not like that you come to like because you don't understand them at first, those are the ones that change the world. Those are the ones you dedicate your fandom to for life." Rubin shares his philosophy on taste: "You can't second-guess your own taste for what someone else is going to like. We're not smart enough to know what someone else is going to like. To make something thinking, 'Well, I don't really like it, but I think this group of people will like it,' it's a bad way to play the game of music or art. You have to do what's personal to you. Take it as far as you can go. Really push the boundaries. And people will resonate with it if they're supposed to resonate with it." He describes creativity as catching waves: "We're really talking about magic. The universe conspiring on our behalf if we let it. Being in this flow of catching these waves that anyone can catch. If you're trying to catch it, you're open to it, you see it coming, you take off on every chance you get. And sometimes the ride happens. It's remarkable how it happens. It doesn't come from preconception. It's not an idea. It's through the doing." Rubin explains how ideas exist in the universe: "Have you ever had that experience where you have an idea for something, you don't do it, and then six months later you see someone else has done it? It's not because they took your idea. It's that it's time for that, and you can act on it or not. The best artists are the ones who have the best antenna for this material that's available. It's coming through. The best comedians see the best jokes. They see them coming. We all live in the same world; the way you see it, you have the best joke because you see it best." He closes with how to stay open: "If we listen to what's going on around us, you can overhear a conversation in a coffee shop, and it is the setup for an idea you're working on. You hear a phrase you don't commonly use. My experience is: when you are open and looking for these clues in the world, they're happening all the time. And they're happening often right when you need them."

Jaynit

109,182 次观看 • 4 个月前

Hedra Prompt Builder is LIVE. You never have to think about prompting again. Pick your subject + style + camera + location → HIT BUILD → and it instantly generates a full scene for you. Welcome to easy mode. To celebrate the launch, we’re giving 1,000 credits to the first 500 followers who want to try it. Reply “Hedra Prompt Builder” and I’ll DM you the code. Clock’s ticking. Go.
0:29

Hedra Prompt Builder is LIVE. You never have to think about prompting again. Pick your subject + style + camera + location → HIT BUILD → and it instantly generates a full scene for you. Welcome to easy mode. To celebrate the launch, we’re giving 1,000 credits to the first 500 followers who want to try it. Reply “Hedra Prompt Builder” and I’ll DM you the code. Clock’s ticking. Go.

Hedra

348,047 次观看 • 8 个月前

We generated this scene with just one trial on Seedance Enterprise 2.5. We had run this same shot on other models and it took us around 8 attempts before anything came back usable. Generations are billed one at a time so 8 tries to 1 is the entire cost story. 30 seconds, single shot, no stitching, what used to be a day of rerolling is now a single pass, which means the budget goes into testing new concepts instead of rescuing one. Watch the water as the creature moves through it, and watch the camera fall behind during the escape. The realistic physics, smooth camera motion, and shot consistency all came directly from the model.None of that was added in post. We used Seedream 5.0 for the visual ideation and Seedance 2.5 for the video. Both are running on lumina at 4K, up to 50 references to hold a character or product steady across a shot, and region editing to fix one part of a frame without regenerating the whole thing. Seedance 2.5 API is about to launch on BytePlus, and now you can try it directly on Lumina.
0:30

We generated this scene with just one trial on Seedance Enterprise 2.5. We had run this same shot on other models and it took us around 8 attempts before anything came back usable. Generations are billed one at a time so 8 tries to 1 is the entire cost story. 30 seconds, single shot, no stitching, what used to be a day of rerolling is now a single pass, which means the budget goes into testing new concepts instead of rescuing one. Watch the water as the creature moves through it, and watch the camera fall behind during the escape. The realistic physics, smooth camera motion, and shot consistency all came directly from the model.None of that was added in post. We used Seedream 5.0 for the visual ideation and Seedance 2.5 for the video. Both are running on lumina at 4K, up to 50 references to hold a character or product steady across a shot, and region editing to fix one part of a frame without regenerating the whole thing. Seedance 2.5 API is about to launch on BytePlus, and now you can try it directly on Lumina.

Future Stacked

86,132 次观看 • 7 天前

Insane! A brand-new AI video tool vid.fun just dropped, and it makes videos in a new way. With zero editing skills, you can go from idea to polished video in minutes by using AI agents 🤯🚀 Here’s how it works: • Start with your idea: drop a prompt, links, or even PDFs into the reasoning box (powered by o3-mini), and it will pull research and inspiration for you. • The AI agents handle the flow from over 1,000 style suggestions (or your custom LoRA!) to storyboarding. • choose from the best video models: Minimax, luma Veo2, and others • I chose Minimax for this onea, esily tweak keyframes, then watch Minimax turn them into video clips. • Add camera movements with Minimax Director mode. • Finally, Vid dot fun stitches it all together, adds an Udio soundtrack (also editable), and you’re done. No editor, no manual cuts just fast, smart 30-second video creation from start to finish.
0:30

Insane! A brand-new AI video tool vid.fun just dropped, and it makes videos in a new way. With zero editing skills, you can go from idea to polished video in minutes by using AI agents 🤯🚀 Here’s how it works: • Start with your idea: drop a prompt, links, or even PDFs into the reasoning box (powered by o3-mini), and it will pull research and inspiration for you. • The AI agents handle the flow from over 1,000 style suggestions (or your custom LoRA!) to storyboarding. • choose from the best video models: Minimax, luma Veo2, and others • I chose Minimax for this onea, esily tweak keyframes, then watch Minimax turn them into video clips. • Add camera movements with Minimax Director mode. • Finally, Vid dot fun stitches it all together, adds an Udio soundtrack (also editable), and you’re done. No editor, no manual cuts just fast, smart 30-second video creation from start to finish.

Amira Zairi

16,576 次观看 • 1 年前