Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

OpenAI launched GPT‑Image‑2.5 Sunburst a few days ago. We stress-tested it's object-swap capabilities using the the invideo editor to create this cool match-cut video. Why? The biggest unlock with Sunburst is that when you edit images - NOTHING except the item you're swapping changes in your frame. Most models... before this would do a good job editing images, but the rest of the frame changed ever so slightly. With 2.5 Sunburst, that doesn't happen anymore. Combine that with an agent building your timeline and lining up your edited images for that perfect match cut feel - without you having to manually line-up, cut, and re-insert edited images on the timeline at the exact right spot, is where the biggest unlock is. We created this in a few hours, with our in-house creator directing the idea and an invideo editing agent building and polishing the timeline.show more

Invideo

36,583 subscribers

194,283 views • 11 days ago •via X (Twitter)

Arts Science & Technology

Anya Rossi• Live Now

Private livecam show

32 Comments

Invideo11 days ago

Try GPT-Image- 2.5 Sunburst and invideo Editor here:

Shemakookie11 days ago

This is huge 🔥

MO11 days ago

That's impressive ✌️

Toshi11 days ago

such a cool idea, ill have to try it out!!

JOHN Z⚡11 days ago

This is genuinely impressive. Keeping the frame consistent while changing everything else opens up so many creative possibilities! 🔥

A.W.E.S.O.M.-O 400011 days ago

Match cut timeline breakdown here shows the object swap precision clearly.

Mehwish kiran11 days ago

The object-swap consistency here is seriously impressive

Virginia11 days ago

Generative match cuts are making complex video edits feel almost effortless with AI doing the heavy lifting.

Horace Dodd11 days ago

Looks like a powerful combo!

simeon-sanai11 days ago

This is seriously impressive. The creative possibilities just got much bigger. 🚀

Drew11 days ago

Wow, got to try this asap

Manish Bhati11 days ago

Will try today

ANKIT PATEL 🇮🇳 | AI11 days ago

Definitely try this new sunburst editing style on invideo editor

InsomniaLK11 days ago

That match-cut is smooth. The object-swap fidelity really sounds like a game-changer for editing workflows.

271ey11 days ago

Trying it right now! 🔥

Veo Studio 🎥11 days ago

Keeping the rest of the frame consistent is a big deal for match cuts. Having the invideo agent then build and polish the timeline makes this much more useful than an image swap on its own. Would love to see more of the editing process behind this.

Lost 🎯11 days ago

This is amazing 👀🔥

ToaiDanh11 days ago

wowww, this feature looks really interesting! I’ll probably give it a try soon :)))

Usman11 days ago

How many images are those, that's crazyy !

Mwoosh11 days ago

How many images are those, that's crazyy !

nonameoasis11 days ago

The stability of Sunburst combined with the timeline agent is exactly the unlock we needed for high-end motion design. Keeping the rest of the frame 100% untouched while swapping elements frame-by-frame saves hours of post-production. Incredible update! 🤝✨

Jay Sensei👾11 days ago

We need a dedicated invideo editor tutorial post from @HridayeN-san😅

IndyStry10 days ago

Great example! This is a great use case for this type of shot where every frame has to change, aligning this by hand would take

Ryan Blake11 days ago

This is a huge unlock for AI editing. 🔥 Keeping everything else in the frame untouched makes object swaps actually production-ready, and pairing that precision with an agent that handles the match cuts and timeline automatically is seriously powerful.

Pelaez Design AI11 days ago

So many ideas pouring in!💯

Baran Robin11 days ago

🔥🔥🔥

Zarnab Ai11 days ago

That level of object-swap consistency is seriously impressive.

osama orabi11 days ago

This is seriously impressive. 🔥

DrSadek 🪶11 days ago

Very nice stuff

OBA🕶️11 days ago

Damn 🔥🔥 You guys just keep blowing my mind What a year 2027 has been for the world when it comes to constant technological advancement Interesting times ahead

ŸĘ11 days ago

Jeeezz

Naartjies 🍊11 days ago

Hm

Related Videos

Everyone's testing GPT 5.6. We gave it superpowers ⚡️ Can your agent generate images, turn them into video, and stitch the whole thing together in one chat? Ours can. The new GPT 5.6 image model is a perfect match for the Sogni Creative Agent. 10 images from a single prompt. One follow-up and they're animated and cut into a finished film. Zero editing apps. The newest models, built in: Seedance 4K + Mini, Krea 2 Turbo, HappyHorse 1.1 and more. Works with any AI agent you already use. One command: npx setup-sogni-agent-skill Sogni Creative Agent. Link below 👇

Everyone's testing GPT 5.6. We gave it superpowers ⚡️ Can your agent generate images, turn them into video, and stitch the whole thing together in one chat? Ours can. The new GPT 5.6 image model is a perfect match for the Sogni Creative Agent. 10 images from a single prompt. One follow-up and they're animated and cut into a finished film. Zero editing apps. The newest models, built in: Seedance 4K + Mini, Krea 2 Turbo, HappyHorse 1.1 and more. Works with any AI agent you already use. One command: npx setup-sogni-agent-skill Sogni Creative Agent. Link below 👇

Sogni.ai

353,235 views • 2 months ago

Created entirely using invideo Money Shot, using 6 product images + a prompt. AI Ads that are 'somewhat close to the actual product' no longer cut it. Say hello to one-click ads with 100% product and text consistency. RT + Comment the name of the product in the video, lucky few win the highest generative invideo plan for FREE + $1200 in credits. Keep your DMs open to hear from us.

Created entirely using invideo Money Shot, using 6 product images + a prompt. AI Ads that are 'somewhat close to the actual product' no longer cut it. Say hello to one-click ads with 100% product and text consistency. RT + Comment the name of the product in the video, lucky few win the highest generative invideo plan for FREE + $1200 in credits. Keep your DMs open to hear from us.

Invideo

1,188,681 views • 9 months ago

A screen recording is the best context you can give an AI agent. It's also the worst. A few seconds of video is thousands of images. Feed that to an agent and you instantly blow up its memory. So I built a tool that fixes it. How it works: Hit record and just do your thing. Click around, type, and talk out loud about what you're doing. While you record, it quietly captures the stuff that actually matters: your voice transcription, every click and the exact thing you clicked, what you typed, and the shortcuts you press. When you stop, it doesn't hand the agent the whole video. It writes a short, readable summary: a timeline of what you said and did. The agent reads that tiny summary first. Then, only when it needs to actually see a moment, it pulls that one exact frame from the video, like flipping to a single page instead of reading the whole book. The result: the agent understands everything you did! Full context. Less tokens.

A screen recording is the best context you can give an AI agent. It's also the worst. A few seconds of video is thousands of images. Feed that to an agent and you instantly blow up its memory. So I built a tool that fixes it. How it works: Hit record and just do your thing. Click around, type, and talk out loud about what you're doing. While you record, it quietly captures the stuff that actually matters: your voice transcription, every click and the exact thing you clicked, what you typed, and the shortcuts you press. When you stop, it doesn't hand the agent the whole video. It writes a short, readable summary: a timeline of what you said and did. The agent reads that tiny summary first. Then, only when it needs to actually see a moment, it pulls that one exact frame from the video, like flipping to a single page instead of reading the whole book. The result: the agent understands everything you did! Full context. Less tokens.

Milind S

12,409 views • 2 months ago

Gemini Omni Flash is now live on invideo. Combining Gemini Omni’s capabilities inside Invideo Agent One means editing and creating films, series, ads, any kind of video is going to feel a lot more intuitive and make you feel a lot more in control. The hybrid filmmaking possibilities and VFX capabilities that the Omni-Agent One combination unlock are super exciting.

Gemini Omni Flash is now live on invideo. Combining Gemini Omni’s capabilities inside Invideo Agent One means editing and creating films, series, ads, any kind of video is going to feel a lot more intuitive and make you feel a lot more in control. The hybrid filmmaking possibilities and VFX capabilities that the Omni-Agent One combination unlock are super exciting.

Invideo

19,754 views • 2 months ago

Launching 'Stock' on Agent Two. Day 7 of 12 Days of Agent Two. As invideo grows into frontier intelligence for creative work, everything you've used invideo for in the past also comes with it. A lot of our existing users and customers build with stock and real-life footage too - and that work belongs in the Agent too. Which is why - Agent Two now has the ability to pull from 16 million premium clips, images and music tracks — Shutterstock, iStock, every premium provider. Cleared for commercial use. The upgrade: you don't search a library manually. You tell the Agent what your video needs and it pulls the footage in itself, music bed included. Everything you could do on invideo, you can still do. Just with a lot more intelligence in the room. Agent Two is frontier intelligence for creative work. 4x faster, at half the price.

Launching 'Stock' on Agent Two. Day 7 of 12 Days of Agent Two. As invideo grows into frontier intelligence for creative work, everything you've used invideo for in the past also comes with it. A lot of our existing users and customers build with stock and real-life footage too - and that work belongs in the Agent too. Which is why - Agent Two now has the ability to pull from 16 million premium clips, images and music tracks — Shutterstock, iStock, every premium provider. Cleared for commercial use. The upgrade: you don't search a library manually. You tell the Agent what your video needs and it pulls the footage in itself, music bed included. Everything you could do on invideo, you can still do. Just with a lot more intelligence in the room. Agent Two is frontier intelligence for creative work. 4x faster, at half the price.

Invideo

1,542,301 views • 1 month ago

New course: Build AI agents that generate images and videos -- an under-explored frontier. A key to performance is having the agent evaluate its own output, and iterate to improve quality. This short course is built together with Google Cloud Tech and taught by Katie Nguyen and Wafae Bakkali. You'll learn three evaluation techniques and combine them in an agent: image-text similarity scoring to check the output matches the prompt, an LLM judge that scores against custom criteria like brand consistency, and structured rubrics that break a prompt into verifiable yes/no questions like "is the subject in the frame?" and "does the camera motion match?" Skills you'll gain: - Learn image and video prompt engineering - Build an image agent that turns brand guidelines into UI mockups - Build a video agent that plans multi-scene explainers and animates reference frames with synchronized audio Join and build agents that create images and video!

Andrew Ng

141,600 views • 4 months ago

The secret to character consistency with Google Flow: 👤 Create a saveable character using the Character tab (this is where you dial in the details!). 📸 Generate reference images to lock in the details. 🎬 Use those images in your prompt to build out your scene! Try it out and show us what you're building. 👇

The secret to character consistency with Google Flow: 👤 Create a saveable character using the Character tab (this is where you dial in the details!). 📸 Generate reference images to lock in the details. 🎬 Use those images in your prompt to build out your scene! Try it out and show us what you're building. 👇

Google Flow

22,041 views • 1 month ago

CSS Tip! ✨ You can create these parallax effects and image cross-fades with scroll-driven animations 🤙 img { animation: fade; animation-timeline: view(); mix-blend-mode: plus-lighter } img:last-of-type { animation-direction: reverse; } @keyframes fade { to { opacity: 0; }} This one's fun! 😁 The trick with the cross-fading image is to make use of one animation that runs at the same time on two images inside a container. You use the same animation, animation-timeline, and animation-range. But, you use animation-direction: reverse on one of the images so they go in the opposite direction 🫶 The use of mix-blend-mode: plus-lighter; produces a better cross-fade result 💯 A viewTimeline (view()) works because you know that both images are the same height. The range you can use is img { animation-timeline: view(); animation-range: cover 45% cover 55%; } That means when the image has covered 45% of the scrollport (In this case, the window), start the animation. And finish when it has covered 55% 🎬 How about the slight parallax? This is a trick with calc(). You know the top of the small image and the big image line up. And you can do this by absolutely placing the caption outside of the small image. The trick is to translate the small image by a distance so it lines up with the bottom of the big image. You can do that like this :root { --catch-up: calc( var(--big-height) - var(--small-height) ); } @keyframes move { to { translate: 0 var(--catch-up); }} Then drive that animation with a scroll-driven animation using the container of both images as the driver 🤙 /* section contains both images */ section { view-timeline: --container; } .img-fader { animation: catch-up both linear; animation-timeline: --container; animation-range: 50vh calc(100vh + (var(--big-height) * 0.25)); } That's it! Scroll-driven image cross-fading and parallax effects without any JavaScript. This demo will work in all browsers as there is some JavaScript in place where the API isn't supported 🤙 To do that, it uses GSAP ScrollTrigger 🏆 As always, any questions, requests, etc. hit me up! 🤙 CodePen.IO link below 👇

CSS Tip! ✨ You can create these parallax effects and image cross-fades with scroll-driven animations 🤙 img { animation: fade; animation-timeline: view(); mix-blend-mode: plus-lighter } img:last-of-type { animation-direction: reverse; } @keyframes fade { to { opacity: 0; }} This one's fun! 😁 The trick with the cross-fading image is to make use of one animation that runs at the same time on two images inside a container. You use the same animation, animation-timeline, and animation-range. But, you use animation-direction: reverse on one of the images so they go in the opposite direction 🫶 The use of mix-blend-mode: plus-lighter; produces a better cross-fade result 💯 A viewTimeline (view()) works because you know that both images are the same height. The range you can use is img { animation-timeline: view(); animation-range: cover 45% cover 55%; } That means when the image has covered 45% of the scrollport (In this case, the window), start the animation. And finish when it has covered 55% 🎬 How about the slight parallax? This is a trick with calc(). You know the top of the small image and the big image line up. And you can do this by absolutely placing the caption outside of the small image. The trick is to translate the small image by a distance so it lines up with the bottom of the big image. You can do that like this :root { --catch-up: calc( var(--big-height) - var(--small-height) ); } @keyframes move { to { translate: 0 var(--catch-up); }} Then drive that animation with a scroll-driven animation using the container of both images as the driver 🤙 /* section contains both images / section { view-timeline: --container; } .img-fader { animation: catch-up both linear; animation-timeline: --container; animation-range: 50vh calc(100vh + (var(--big-height) 0.25)); } That's it! Scroll-driven image cross-fading and parallax effects without any JavaScript. This demo will work in all browsers as there is some JavaScript in place where the API isn't supported 🤙 To do that, it uses GSAP ScrollTrigger 🏆 As always, any questions, requests, etc. hit me up! 🤙 CodePen.IO link below 👇

jhey ʕ•ᴥ•ʔ

242,205 views • 2 years ago

this guy built an AI video pipeline that turns one prompt into a finished short. he barely opens editing software. give Claude a simple idea. in the demo: a puppy rescue story. Claude runs the entire production from there: → generates the images with Nano Banana 2 → turns them into motion with Kinovi / Seedance 2.0 → stitches the clips together with FFmpeg → uploads the finished video no manually generating every frame. no dragging clips around a timeline for an hour. no stitching together the edit by hand. here’s the actual shift, and it’s bigger than “AI made a video”: Claude isn’t just one tool in the chain anymore. it’s coordinating the whole chain deciding what goes where, which tool handles which step, and executing it end to end. idea → images → video clips → edit → final render. one prompt in, finished short out. most people are still using AI one tool at a time generate an image here, cut it there, stitch it somewhere else, doing the coordination themselves. the bigger unlock isn’t a better individual tool. it’s connecting the tools so nothing needs a human in between steps. give it an idea. let the system make the video.

this guy built an AI video pipeline that turns one prompt into a finished short. he barely opens editing software. give Claude a simple idea. in the demo: a puppy rescue story. Claude runs the entire production from there: → generates the images with Nano Banana 2 → turns them into motion with Kinovi / Seedance 2.0 → stitches the clips together with FFmpeg → uploads the finished video no manually generating every frame. no dragging clips around a timeline for an hour. no stitching together the edit by hand. here’s the actual shift, and it’s bigger than “AI made a video”: Claude isn’t just one tool in the chain anymore. it’s coordinating the whole chain deciding what goes where, which tool handles which step, and executing it end to end. idea → images → video clips → edit → final render. one prompt in, finished short out. most people are still using AI one tool at a time generate an image here, cut it there, stitch it somewhere else, doing the coordination themselves. the bigger unlock isn’t a better individual tool. it’s connecting the tools so nothing needs a human in between steps. give it an idea. let the system make the video.

RUX

11,269 views • 1 month ago

This is the kind of AI workflow that makes more sense to me: Don’t try to make the perfect video in one step. Build it. Start with the idea in GPT Image 2.5 and turn it into a visual storyboard. GPT Image 2.5 is coming to CapCut, where it will be available through Design Studio and AI Image. Then take the storyboard into CapCut PC’s multi-track timeline and use AI Video with Seedance 2.5 to generate the first full film. Once you have something to work with, use AI Edit to shape it. Generate the foundation. Edit the details. Keep the story. Keep the creative control. Idea → Storyboard → Full Film → Your Version. That feels like a much more sustainable way to make with AI. #GPTImage25 #CapCutPC #AIVideo #Seedance25

This is the kind of AI workflow that makes more sense to me: Don’t try to make the perfect video in one step. Build it. Start with the idea in GPT Image 2.5 and turn it into a visual storyboard. GPT Image 2.5 is coming to CapCut, where it will be available through Design Studio and AI Image. Then take the storyboard into CapCut PC’s multi-track timeline and use AI Video with Seedance 2.5 to generate the first full film. Once you have something to work with, use AI Edit to shape it. Generate the foundation. Edit the details. Keep the story. Keep the creative control. Idea → Storyboard → Full Film → Your Version. That feels like a much more sustainable way to make with AI. #GPTImage25 #CapCutPC #AIVideo #Seedance25

Iris Quinn

68,211 views • 10 days ago

I was so frustrated with the experience using nano-banana that I built a self-correcting image agent. The agent generates images and evaluates them against the original request until the goal is met. Like in this video, it was able to achieve the goal in 6 loops.

I was so frustrated with the experience using nano-banana that I built a self-correcting image agent. The agent generates images and evaluates them against the original request until the goal is met. Like in this video, it was able to achieve the goal in 6 loops.

Pietro Schirano

101,693 views • 1 year ago

This is how you build the next generation of AI applications. You need an idea, a good model architecture, and a great harness. That's what MUZIM did. It's an app that runs local multimodal and vision models offline to parse and index your images, videos, and documents frame by frame. • Super fast on-device processing • On-device video & image understanding • You can also bring your API keys for heavy reasoning • Your data stays where it is / nothing goes to the cloud You can do a couple of things with this: 1. Vibe searching for whatever you remember in photos or raw video clips. The app will jump straight to the exact frame and timestamp of the video. This is search as it should be. 2. Use local-running agents to perform tasks on your files. I show a couple of examples in my video. You can check it out here: Thanks to the MUZIM by OpenSoul team for showing me the tool and partnering with me on this post.

This is how you build the next generation of AI applications. You need an idea, a good model architecture, and a great harness. That's what MUZIM did. It's an app that runs local multimodal and vision models offline to parse and index your images, videos, and documents frame by frame. • Super fast on-device processing • On-device video & image understanding • You can also bring your API keys for heavy reasoning • Your data stays where it is / nothing goes to the cloud You can do a couple of things with this: 1. Vibe searching for whatever you remember in photos or raw video clips. The app will jump straight to the exact frame and timestamp of the video. This is search as it should be. 2. Use local-running agents to perform tasks on your files. I show a couple of examples in my video. You can check it out here: Thanks to the MUZIM by OpenSoul team for showing me the tool and partnering with me on this post.

Santiago

65,953 views • 1 month ago

i built a free tool* using the chatgpt api to add a mask to an image so it only modifies the area you select the idea is that in chatgpt it changes the full img, but this focuses the edit not sure it's 100% working tho as some images change a lot still *bring your own key

i built a free tool* using the chatgpt api to add a mask to an image so it only modifies the area you select the idea is that in chatgpt it changes the full img, but this focuses the edit not sure it's 100% working tho as some images change a lot still *bring your own key

Ian Nuttall

22,119 views • 1 year ago

The AI I am training for you will not just understand the images of an epoch, but also the “feel” of an epoch. I have 100s and 1000s of hours of contextual video that I also connect with real time context. Few understand why this is vital today and the future. This is 1973…

The AI I am training for you will not just understand the images of an epoch, but also the “feel” of an epoch. I have 100s and 1000s of hours of contextual video that I also connect with real time context. Few understand why this is vital today and the future. This is 1973…

Brian Roemmele

42,306 views • 1 year ago

This is how we do science on the International Space Station. In this demonstration, we have one person operating the ultrasound and the other person operating the controls. A remote guider and a team of doctors make sure that we’re getting the right images and also analyzing the images immediately in case we need to follow up. Scientists and physicians are concerned that microgravity changes the normal flow of blood and could predispose astronauts to blood clots.

This is how we do science on the International Space Station. In this demonstration, we have one person operating the ultrasound and the other person operating the controls. A remote guider and a team of doctors make sure that we’re getting the right images and also analyzing the images immediately in case we need to follow up. Scientists and physicians are concerned that microgravity changes the normal flow of blood and could predispose astronauts to blood clots.

Anil Menon

94,711 views • 12 days ago

I was invited to test OpenArt Director. I made this nearly 1-minute cinematic video through conversation, starting with only an initial idea, two character images, and one background image. This is what vibe directing feels like. A few details impressed me: Director first generates the voiceover, then uses it as reference audio for Seedance 2.0. That makes the character voices feel much more natural and better synced. After the character images, it also helps create storyboard frames and camera reference images. That massively improves the final generation quality. It feels less like writing a prompt, and more like building a shot with an AI production team.

I was invited to test OpenArt Director. I made this nearly 1-minute cinematic video through conversation, starting with only an initial idea, two character images, and one background image. This is what vibe directing feels like. A few details impressed me: Director first generates the voiceover, then uses it as reference audio for Seedance 2.0. That makes the character voices feel much more natural and better synced. After the character images, it also helps create storyboard frames and camera reference images. That massively improves the final generation quality. It feels less like writing a prompt, and more like building a shot with an AI production team.

underwood

16,581 views • 3 months ago

I think the biggest change here is where the filmmaking process starts. Instead of opening a video generator with a blank prompt, start by building the visual language of the story first. GPT Image 2.5 is coming to CapCut, where it will be available through Design Studio and AI Image. Use it to turn an idea into a visual storyboard. Then bring that storyboard into CapCut PC’s multi-track timeline and use AI Video with Seedance 2.5 to generate the first full version. Once the video exists, AI Edit lets you keep working on it. Change a scene. Adjust the pacing. Improve the audio. Refine the details. The first generation gives you the film. The editing gives you control over what the film becomes. #GPTImage25 #CapCutPC #AIVideo #Seedance25

I think the biggest change here is where the filmmaking process starts. Instead of opening a video generator with a blank prompt, start by building the visual language of the story first. GPT Image 2.5 is coming to CapCut, where it will be available through Design Studio and AI Image. Use it to turn an idea into a visual storyboard. Then bring that storyboard into CapCut PC’s multi-track timeline and use AI Video with Seedance 2.5 to generate the first full version. Once the video exists, AI Edit lets you keep working on it. Change a scene. Adjust the pacing. Improve the audio. Refine the details. The first generation gives you the film. The editing gives you control over what the film becomes. #GPTImage25 #CapCutPC #AIVideo #Seedance25

AI Panda

95,573 views • 11 days ago

Launching Notebooks on Agent Two: Day 5 of 12 Days of Agent Two. With notebooks, you have complete control over the work you do with individual models. invideo's got ALL the state-of-the-art models across images, video, sound, music, creative tools. So essentially you can work with the Agent in free-flow, switch to the notebook for hands-on granular work on particular gens (both creating and editing gens), and switch back to the Agent as and when you like with no loss of context or output. This is the full range of how you can do creative work. And that's why Agent Two is the frontier intelligence agent out there. 4x faster, at half the price.

Launching Notebooks on Agent Two: Day 5 of 12 Days of Agent Two. With notebooks, you have complete control over the work you do with individual models. invideo's got ALL the state-of-the-art models across images, video, sound, music, creative tools. So essentially you can work with the Agent in free-flow, switch to the notebook for hands-on granular work on particular gens (both creating and editing gens), and switch back to the Agent as and when you like with no loss of context or output. This is the full range of how you can do creative work. And that's why Agent Two is the frontier intelligence agent out there. 4x faster, at half the price.

Invideo

1,091,714 views • 1 month ago

Seedance 2 is on Freepik (now Magnific) 🔥 Some observations: - Preparation is key. Make reference images for characters, props, environment before generating videos. - Use the reference images and refer to them in the prompt. - Go for multishot. You can basically do rough editing of the video at prompt level. - Generate multiple videos for each prompt and then chop it up in your video editor. Often these videos can be combined in many ways using the best shots from each. - Generate SFX, but avoid music. Add that manually later. Link to the Spaces workflow below.

Seedance 2 is on Freepik (now Magnific) 🔥 Some observations: - Preparation is key. Make reference images for characters, props, environment before generating videos. - Use the reference images and refer to them in the prompt. - Go for multishot. You can basically do rough editing of the video at prompt level. - Generate multiple videos for each prompt and then chop it up in your video editor. Often these videos can be combined in many ways using the best shots from each. - Generate SFX, but avoid music. Add that manually later. Link to the Spaces workflow below.

Martin LeBlanc

17,538 views • 5 months ago