Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

I have been wanting to test performance transfer in Seadance 2.5 since launch, now I have, I am really impressed by the results. I wrote a short script and recorded myself giving a rallying speech as an orc warlord, then fed this and an image of the orc into...

Uncanny_Harry's profile picture

Uncanny Harry AI

15,126 subscribers

23,517 Aufrufe • vor 1 Monat •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

67 Kommentare

Profilbild von Gossip Goblin
Gossip Goblinvor 1 Monat

Need you as a voice actor asap

Profilbild von Uncanny Harry AI
Uncanny Harry AIvor 1 Monat

Just say the word brother!

Profilbild von GrandVisionsAI
GrandVisionsAIvor 1 Monat

Impressive, thanks for sharing. I’ve struggled with acting in 2.5, so I’ll try this. You should also check out Wan 3.0. My first generation delivered better acting than multiple 2.5 attempts. I find 2.5’s pacing is off, and I still prefer 2.0 in many ways.

Profilbild von Uncanny Harry AI
Uncanny Harry AIvor 1 Monat

Like this very Last Kingdom!

Profilbild von Tinseltown Pixels
Tinseltown Pixelsvor 1 Monat

Oh wow came out really good

Profilbild von Uncanny Harry AI
Uncanny Harry AIvor 1 Monat

👍

Profilbild von PJ Ace
PJ Acevor 1 Monat

this turned out great! can you try driving a human performance?

Profilbild von Uncanny Harry AI
Uncanny Harry AIvor 1 Monat

Lol i first read that as "can you try a human driving performance?" I thought I know I can look a bit funny in some angles but I am still human! Yeah will be interesting to see if it can do good a convincing transfer onto a human avatar.

Profilbild von Tony
Tonyvor 1 Monat

This is great, awesome performance. I may or may not have a warcraft half sleeve tattoo so I dig it!

Profilbild von Uncanny Harry AI
Uncanny Harry AIvor 1 Monat

✊

Profilbild von StatysTheBaddest
StatysTheBaddestvor 1 Monat

SD2.5 performance transfer came out great. Dialogue very good too!

Profilbild von Uncanny Harry AI
Uncanny Harry AIvor 1 Monat

Thanks 👍

Profilbild von Braveheart619
Braveheart619vor 1 Monat

I wonder what you and @Gossip_Goblin could do with a Viking storyline… Can you give the world the Viking Story that Mel Gibson promised??

Profilbild von Hayden Lee
Hayden Leevor 1 Monat

looks great!

Profilbild von Vaska
Vaskavor 1 Monat

Very impressive. You didn't feed the prompt with your video, right? Just the audio?

Profilbild von Uncanny Harry AI
Uncanny Harry AIvor 1 Monat

No I fed in the still of the orc the video and the text prompt above.

Profilbild von SujiPop
SujiPopvor 1 Monat

It’s so amazing that this used to be the most advanced technology back then, and now you can do this. Performance capture in a total new era now.

Profilbild von redthecreator
redthecreatorvor 1 Monat

this is brilliant brother Great work

Profilbild von Uncanny Harry AI
Uncanny Harry AIvor 1 Monat

🙏

Profilbild von Ellenor Argyropoulos
Ellenor Argyropoulosvor 1 Monat

i love this so much mate , nice one!

Profilbild von Uncanny Harry AI
Uncanny Harry AIvor 1 Monat

Cheers Ellenor, hope you are well 👍

Profilbild von Hero Komi 🎥
Hero Komi 🎥vor 1 Monat

@brandonchinbook This is great for filmmakers!

Profilbild von Along4theride
Along4theridevor 1 Monat

Does the drift in timing happen from a guided place or is the model just steering things

Profilbild von Uncanny Harry AI
Uncanny Harry AIvor 1 Monat

With this one the model, you can tighten things with timecode and writing the dialogue.

Profilbild von DreamAgents
DreamAgentsvor 1 Monat

Incredible!!!

Profilbild von Uncanny Harry AI
Uncanny Harry AIvor 1 Monat

👍

Profilbild von Lola Viscera
Lola Visceravor 1 Monat

is that seedance account legit?

Profilbild von Uncanny Harry AI
Uncanny Harry AIvor 1 Monat

It's followed by @BytePlusGlobal so I would think so... but who can be 100 per cent on anything with the internet!

Profilbild von Lola Viscera
Lola Visceravor 1 Monat

@BytePlusGlobal love your acting ryan it’s really quite something. these clips are great i so enjoy them. thx for sharing 🔥🔥

Profilbild von Uncanny Harry AI
Uncanny Harry AIvor 1 Monat

@BytePlusGlobal No problem , I’ve done it enough times beyond embarrassment now 😂

Profilbild von Dale Wiliams (The Reel Robot)
Dale Wiliams (The Reel Robot)vor 1 Monat

Well that was excellent

Profilbild von Uncanny Harry AI
Uncanny Harry AIvor 1 Monat

Cheers fella 👍

Profilbild von KevinFleischer
KevinFleischervor 1 Monat

Nice video demonstration. Only thing that's kinda wrong is, orcs needing a motivational speach. Orcs fight and destroy as a reflex, like breathing. Defending and home building is humanizing a race that stands for being anti human.

Profilbild von Stefan Larsen
Stefan Larsenvor 1 Monat

Do a Gollum one, I wanna see something

Profilbild von Changhong Yang
Changhong Yangvor 1 Monat

Good performance

Profilbild von Yang Wong
Yang Wongvor 1 Monat

Ha nice performance Ryan! You should totally voice act all your vids if you don't already. Interesting you got an interpretation. Mine are very much 1-to-1. Must be in the text prompt...

Profilbild von Genmakers
Genmakersvor 1 Monat

Very impressive !

Profilbild von Infinite-Realities
Infinite-Realitiesvor 1 Monat

Impressive. How much did it cost?

Profilbild von Uncanny Harry AI
Uncanny Harry AIvor 1 Monat

The price of about 6 ten second Seadance 2,5 gens.

Profilbild von Infinite-Realities
Infinite-Realitiesvor 1 Monat

Which is how much in $?

Profilbild von Uncanny Harry AI
Uncanny Harry AIvor 1 Monat

Not sure of the credits to $ breakdown.

Profilbild von DreamStarter
DreamStartervor 1 Monat

Very interesting how it interpreted your performance!

Profilbild von Uncanny Harry AI
Uncanny Harry AIvor 1 Monat

Yeah you would have to write a long, complex prompt to achieve that kind of nuance and context in an AI performance.

Profilbild von DreamStarter
DreamStartervor 1 Monat

Yeah but not worth it if you can do it like this.

Profilbild von Stéphane
Stéphanevor 1 Monat

Insanely good. I really have to try it out myself

Profilbild von Uncanny Harry AI
Uncanny Harry AIvor 1 Monat

Do it @ me with your results!

Profilbild von Stéphane
Stéphanevor 1 Monat

I will !

Profilbild von Virash
Virashvor 1 Monat

omg this brings a fantasy character to life, soooo cool

Profilbild von Halim Alrasihi
Halim Alrasihivor 1 Monat

This is really good!! Did you use the normal omni reference or the smart edit?

Profilbild von Uncanny Harry AI
Uncanny Harry AIvor 1 Monat

Normal omni.

Profilbild von Matsuri Yumeai／夢逢真月里
Matsuri Yumeai／夢逢真月里vor 1 Monat

I also use Lumina regularly and I’m really interested in the potential of Seedance 2.5. Seeing the quality of this performance transfer, I made some new discoveries myself. It was very helpful — thank you for sharing!

Profilbild von The Ruggeds
The Ruggedsvor 1 Monat

Nicely done!

Profilbild von Uncanny Harry AI
Uncanny Harry AIvor 1 Monat

👍

Profilbild von ☠️Bonesmegga👽
☠️Bonesmegga👽vor 1 Monat

Looks good!

Profilbild von Uncanny Harry AI
Uncanny Harry AIvor 1 Monat

👍

Profilbild von Loop'n'Mix
Loop'n'Mixvor 1 Monat

Acting is on point! 🔥👌

Profilbild von Uncanny Harry AI
Uncanny Harry AIvor 1 Monat

Eastenders in middle earth more like!

Profilbild von Loop'n'Mix
Loop'n'Mixvor 1 Monat

😂

Profilbild von NΞXUS
NΞXUSvor 1 Monat

Honestly it's very Good, how did you come up such good dialogue, I always tried to wrote good one but they always end up being very vilain like dialogue. 😂🤣

Profilbild von Uncanny Harry AI
Uncanny Harry AIvor 1 Monat

I’ve been writing scripts for 30 years. I’d recommend books like into the woods by John Yorke, the screenplay problem solver by Sid Field also the script notes podcast. Also read scripts by your favourite filmmakers and see how they wrote the dialogue on the page 👍

Profilbild von NΞXUS
NΞXUSvor 1 Monat

Gonna save this, by next next week they will be on my desk

Profilbild von Uncanny Harry AI
Uncanny Harry AIvor 1 Monat

Some of my collection 👍

Profilbild von CoffeeVectors
CoffeeVectorsvor 1 Monat

Looking good!!

Profilbild von Uncanny Harry AI
Uncanny Harry AIvor 1 Monat

Cheers mate 👍

Profilbild von Radiate Studio
Radiate Studiovor 1 Monat

Giving the model an actual performance instead of just a still clearly made a huge difference. This is such a smart way to do it

Profilbild von Uncanny Harry AI
Uncanny Harry AIvor 1 Monat

Yeah we have so many ways to enhance our prompts with references now.

Profilbild von Alysse 🔥
Alysse 🔥vor 1 Monat

Recording yourself as the orc reference is genius — how'd the performance transfer hold up?

Ähnliche Videos

Another Hailuo AI (MiniMax) H3 test, this time looking at audio reference and performance (A little NSFW language on end of this one!). I recorded the dialogue as an audio track and fed that in as a reference with a image reference of the man. In the text prompts I gave some direction to the actor (Like the look to camera at the end). I think the model did a brilliant job of matching the performance to the words and emotion that were in the audio ref. Unlike Seedance 2.0 I didn't have to feed in black video or write the words in the prompt to get the words correct. It seemed to use the exact audio from the reference I provided, which is what you want when using voice actors. Things are getting real... fast
0:29

Another Hailuo AI (MiniMax) H3 test, this time looking at audio reference and performance (A little NSFW language on end of this one!). I recorded the dialogue as an audio track and fed that in as a reference with a image reference of the man. In the text prompts I gave some direction to the actor (Like the look to camera at the end). I think the model did a brilliant job of matching the performance to the words and emotion that were in the audio ref. Unlike Seedance 2.0 I didn't have to feed in black video or write the words in the prompt to get the words correct. It seemed to use the exact audio from the reference I provided, which is what you want when using voice actors. Things are getting real... fast

Uncanny Harry AI

14,036 Aufrufe • vor 2 Monaten

This might be the best synthetic performance I have got from a video model. We can generate 30-second shots and create near seamless extensions (with a bit of post blending) for far longer sequences, powered by Seedance Enterprise 2.5. I set out to test this out by making the scene below all-in-one shot. I wrote the script, built the character references in Seedream and then broke the script down to two 30 second prompts. The prompts were really detailed with pauses, gestures and emotional shifts and the model delivered on all of them. I was really impressed with the performance and voices which were generated in the model. Previously, AI film scenes had to be composed of short cuts, now we have options on pacing, and nuance... we can let our scenes breathe. All this done with only around 3 rolls per take, we have left the slot machine age of AI video Gen behind and are now in the age of control. Next for me will be testing real actors performance as a reference to drive the generation. Seedance 2.5 API is about to launch on BytePlus , and Lumina will also roll out Seedance 2.5 soon.
0:59

This might be the best synthetic performance I have got from a video model. We can generate 30-second shots and create near seamless extensions (with a bit of post blending) for far longer sequences, powered by Seedance Enterprise 2.5. I set out to test this out by making the scene below all-in-one shot. I wrote the script, built the character references in Seedream and then broke the script down to two 30 second prompts. The prompts were really detailed with pauses, gestures and emotional shifts and the model delivered on all of them. I was really impressed with the performance and voices which were generated in the model. Previously, AI film scenes had to be composed of short cuts, now we have options on pacing, and nuance... we can let our scenes breathe. All this done with only around 3 rolls per take, we have left the slot machine age of AI video Gen behind and are now in the age of control. Next for me will be testing real actors performance as a reference to drive the generation. Seedance 2.5 API is about to launch on BytePlus , and Lumina will also roll out Seedance 2.5 soon.

Uncanny Harry AI

61,125 Aufrufe • vor 1 Monat

Here's how to do a bit of VFX work using Seedance 2: If you generate with Seedance 2 you often get a great shot but unfortunately with one or more minor artefacts. Instead of discarding the generation, you can actually edit the video using Seedance 2. In my case it i had to remove a character and I did this using simply as the prompt and using the original video as reference: "Remove boy from video". I then regenerated the missing detail (the boy) using an isolated version of the boy that I removed. And then animated using Seedance 2: "the boy runs sideways and stops. white background. he stays in the center of the screen." In the tutorial below, I'll show how I got rid of an artefact in a shot I liked, and used good old compositing to combine a two videos. As always I'll share the link to the Space below.
5:36

Here's how to do a bit of VFX work using Seedance 2: If you generate with Seedance 2 you often get a great shot but unfortunately with one or more minor artefacts. Instead of discarding the generation, you can actually edit the video using Seedance 2. In my case it i had to remove a character and I did this using simply as the prompt and using the original video as reference: "Remove boy from video". I then regenerated the missing detail (the boy) using an isolated version of the boy that I removed. And then animated using Seedance 2: "the boy runs sideways and stops. white background. he stays in the center of the screen." In the tutorial below, I'll show how I got rid of an artefact in a shot I liked, and used good old compositing to combine a two videos. As always I'll share the link to the Space below.

Martin LeBlanc

18,312 Aufrufe • vor 4 Monaten

I've been playing more with this depth map motion transfer workflow, and if you're trying to recreate really specific body movements from a reference video, this works surprisingly well. Here's the workflow: 1. Grab your reference video, then create your character and environment references. 2. Run the video through Depth Anything on fal to generate a depth map: 3. Drop that depth map into Seedance Omni as your motion reference along with your character and environment references. You don't even need the original video. I also tested this against using the original video as the motion reference in Seedance, and there's definitely a noticeable difference. One thing I found, though, is that this works much better for body movement than facial performance since the depth map can't really capture subtle facial motion. I'm running more tests to see if there's a good way to control both body movement and facial performance. If you have any workflows I should try, do share in the comments!
0:52

I've been playing more with this depth map motion transfer workflow, and if you're trying to recreate really specific body movements from a reference video, this works surprisingly well. Here's the workflow: 1. Grab your reference video, then create your character and environment references. 2. Run the video through Depth Anything on fal to generate a depth map: 3. Drop that depth map into Seedance Omni as your motion reference along with your character and environment references. You don't even need the original video. I also tested this against using the original video as the motion reference in Seedance, and there's definitely a noticeable difference. One thing I found, though, is that this works much better for body movement than facial performance since the depth map can't really capture subtle facial motion. I'm running more tests to see if there's a good way to control both body movement and facial performance. If you have any workflows I should try, do share in the comments!

Curious Refuge

16,487 Aufrufe • vor 1 Monat

Sharing some work in progress on my latest AI short. Here is a rough cut of a dialogue scene where I use Kling 2.6 motion control to capture and transfer my performance to the AI generated characters of both Terry and Carol. No sound design, Carol's voice is just mine pitched up 😝 and I am clearly not a trained actor but I think this gives you a good idea of where we are in terms being able to capture performance and create engaging dialogue scenes with AI tools. I'd usually post the video with an inset of me performing but I did this late last night in my Rick and Morty Oodie with hair like a crazy money, ain't nobody need to see that!
0:33

Sharing some work in progress on my latest AI short. Here is a rough cut of a dialogue scene where I use Kling 2.6 motion control to capture and transfer my performance to the AI generated characters of both Terry and Carol. No sound design, Carol's voice is just mine pitched up 😝 and I am clearly not a trained actor but I think this gives you a good idea of where we are in terms being able to capture performance and create engaging dialogue scenes with AI tools. I'd usually post the video with an inset of me performing but I did this late last night in my Rick and Morty Oodie with hair like a crazy money, ain't nobody need to see that!

Uncanny Harry AI

65,195 Aufrufe • vor 8 Monaten

I'm still convinced that you can get a better acting performance with AI by generating dialogue first and generating the video to sync with the audio. As audio generation is so much cheaper you're also able to validate the performance for a few cents before using credits for the video. Midjourney 8.2 -> SeeDream 5.0 -> SeedAudio 1.0 -> SeeDance 2.0
0:26

I'm still convinced that you can get a better acting performance with AI by generating dialogue first and generating the video to sync with the audio. As audio generation is so much cheaper you're also able to validate the performance for a few cents before using credits for the video. Midjourney 8.2 -> SeeDream 5.0 -> SeedAudio 1.0 -> SeeDance 2.0

TomLikesRobots🤖

38,110 Aufrufe • vor 2 Monaten

For “The Final Callback,” I used Seedream 5.0 Pro via Lumina to shape the theatre and characters, SeedAudio for the dialogue and emotional soundscape, and Seedance Enterprise 2.5 to bring the full 30-second cinematic drama to life. The biggest surprise during my test wasn't just the cinematic quality—it was how much less trial-and-error the workflow required. For emotional scenes like these, I would normally regenerate multiple versions before getting a usable performance. With Seedance 2.5, I was able to achieve production-ready results in around 1-2 attempts, which significantly reduced generation costs while saving a lot of production time. That efficiency let me spend more time refining the story instead of constantly rerolling shots. The realism is what really completes the experience: Maya's restrained performance, natural dialogue delivery, subtle pauses, realistic character movement, and smooth cinematic camera motion make the scene feel much closer to a real film than an AI-generated clip. Seedance 2.5 API is about to launch on BytePlus, and now you can try it directly on Lumina.
0:25

For “The Final Callback,” I used Seedream 5.0 Pro via Lumina to shape the theatre and characters, SeedAudio for the dialogue and emotional soundscape, and Seedance Enterprise 2.5 to bring the full 30-second cinematic drama to life. The biggest surprise during my test wasn't just the cinematic quality—it was how much less trial-and-error the workflow required. For emotional scenes like these, I would normally regenerate multiple versions before getting a usable performance. With Seedance 2.5, I was able to achieve production-ready results in around 1-2 attempts, which significantly reduced generation costs while saving a lot of production time. That efficiency let me spend more time refining the story instead of constantly rerolling shots. The realism is what really completes the experience: Maya's restrained performance, natural dialogue delivery, subtle pauses, realistic character movement, and smooth cinematic camera motion make the scene feel much closer to a real film than an AI-generated clip. Seedance 2.5 API is about to launch on BytePlus, and now you can try it directly on Lumina.

Marry claire

25,293 Aufrufe • vor 1 Monat

Seedance 2.0 is allowing us to enter a new era of music video creation. Here is how I created HONEY. It was a quick test to see how well this workflow holds up. 🐝 1 - Write your song and generate the music with Suno 5.5. 2 - Use an image generator of your choice. For HONEY I combined both Grok Imagine for aesthetics and Nano Banana Pro for refined editing. 3 - In Capcut I import my audio and just save out a blank video video containing the audio. This step is important because this video file containing audio will now be used with Seedance 2.0 as a video reference with Omni. This allows the AI to apply automatic and realistic lipsync and movement to the music, it's extremely powerful! 4 - Once I have a both my image and video with audio as reference, I use Seedance 2.0 Omni and upload my starting image and then the video reference with the audio. 5 - From here I'm simply prompting like normal, specifying what's happening in my scene with detailed instructions, mentioning multi shots and camera angle changes and then specifying that the person is singing along to the song. I type out the lyrics that are present to have better lipsync accuracy. 6 - Once I have generated a video and like the result, I do video to video, so i upload that video that just got generated and type "The scene continues" and prompt new actions to take place. This allows you to expand on a narrative. These new shots can be used as B-ROLL and since I uploaded my video as reference I have full consistency of everything it saw in the video. This is also extremely powerful. 7 - This is actually the most difficult part. Edit in Capcut. This is where you need to understand pacing and shot selection from all the scenes you generated to bring it all together. You must be strategic with the editing. Goodluck! I'll probably record a video tutorial at some point as it's easier to see what is being done.
0:46

Seedance 2.0 is allowing us to enter a new era of music video creation. Here is how I created HONEY. It was a quick test to see how well this workflow holds up. 🐝 1 - Write your song and generate the music with Suno 5.5. 2 - Use an image generator of your choice. For HONEY I combined both Grok Imagine for aesthetics and Nano Banana Pro for refined editing. 3 - In Capcut I import my audio and just save out a blank video video containing the audio. This step is important because this video file containing audio will now be used with Seedance 2.0 as a video reference with Omni. This allows the AI to apply automatic and realistic lipsync and movement to the music, it's extremely powerful! 4 - Once I have a both my image and video with audio as reference, I use Seedance 2.0 Omni and upload my starting image and then the video reference with the audio. 5 - From here I'm simply prompting like normal, specifying what's happening in my scene with detailed instructions, mentioning multi shots and camera angle changes and then specifying that the person is singing along to the song. I type out the lyrics that are present to have better lipsync accuracy. 6 - Once I have generated a video and like the result, I do video to video, so i upload that video that just got generated and type "The scene continues" and prompt new actions to take place. This allows you to expand on a narrative. These new shots can be used as B-ROLL and since I uploaded my video as reference I have full consistency of everything it saw in the video. This is also extremely powerful. 7 - This is actually the most difficult part. Edit in Capcut. This is where you need to understand pacing and shot selection from all the scenes you generated to bring it all together. You must be strategic with the editing. Goodluck! I'll probably record a video tutorial at some point as it's easier to see what is being done.

Travis Davids

19,236 Aufrufe • vor 5 Monaten

behind story of the performance with kai’s long hair ⭐️ 🐧 my dream image of having long hair…i wanted it to look pretty like a character so to have long hair, your jawline has to be very sharp so the day before the performance with my long hair, i drank liquor with a high alcohol percentage and i just gulped it and… 🐧 apparently if you want to quickly get rid (of any puffiness), you can drink liquor that has a high percentage of alcohol so i was like “really?” and i drank the liquor the day before the performance and i went through a hard time the next day…as soon as i woke up 🐧 since it’s alcohol, the water retention goes down and it does look sharper BUT! don’t do it at any cost. 🐧 it wasn’t easy, i did it for that one day but i don’t want to do it again
1:13

behind story of the performance with kai’s long hair ⭐️ 🐧 my dream image of having long hair…i wanted it to look pretty like a character so to have long hair, your jawline has to be very sharp so the day before the performance with my long hair, i drank liquor with a high alcohol percentage and i just gulped it and… 🐧 apparently if you want to quickly get rid (of any puffiness), you can drink liquor that has a high percentage of alcohol so i was like “really?” and i drank the liquor the day before the performance and i went through a hard time the next day…as soon as i woke up 🐧 since it’s alcohol, the water retention goes down and it does look sharper BUT! don’t do it at any cost. 🐧 it wasn’t easy, i did it for that one day but i don’t want to do it again

💬

168,960 Aufrufe • vor 1 Jahr

I used Seedance Enterprise 2.5 to create this AI rap music video. One thing I noticed during testing was that I spent less time regenerating shots. I got the result on the second attempt. I was getting usable results more consistently, which made the workflow feel faster and more cost-effective. The authenticity struck me profoundly, Seedance 2.5 captures micro‑expressions and subtle eye shifts that feel unscripted — the kind of nuance that usually gets lost in AI, but here makes every frame read as a real performance. The 30-second generation made the creative process feel much more natural. The motion, lighting, and camera movement felt more natural, making it easier to focus on storytelling instead of fixing every scene. I can also see how pairing it with SeedAudio would make the overall AI music video workflow even more seamless. Support for multimodal references and localized editing helped keep the visuals consistent while making refinements much easier. Overall, Seedance 2.5 feels less like a shot generator and more like a creative tool for cinematic storytelling and music videos. Seedance 2.5 API is about to launch on BytePlus, and Lumina will also roll out Seedance 2.5 soon
0:30

I used Seedance Enterprise 2.5 to create this AI rap music video. One thing I noticed during testing was that I spent less time regenerating shots. I got the result on the second attempt. I was getting usable results more consistently, which made the workflow feel faster and more cost-effective. The authenticity struck me profoundly, Seedance 2.5 captures micro‑expressions and subtle eye shifts that feel unscripted — the kind of nuance that usually gets lost in AI, but here makes every frame read as a real performance. The 30-second generation made the creative process feel much more natural. The motion, lighting, and camera movement felt more natural, making it easier to focus on storytelling instead of fixing every scene. I can also see how pairing it with SeedAudio would make the overall AI music video workflow even more seamless. Support for multimodal references and localized editing helped keep the visuals consistent while making refinements much easier. Overall, Seedance 2.5 feels less like a shot generator and more like a creative tool for cinematic storytelling and music videos. Seedance 2.5 API is about to launch on BytePlus, and Lumina will also roll out Seedance 2.5 soon

Zara

31,783 Aufrufe • vor 1 Monat

Full Breakdown: How I Created a Viral Ad This will be a very long post as I will provide you with the exact way I achieved the original ad, as well as a prompt that get's you straight to the result in case you want to speed-run it. How I created the original: I made the ad collaborating with an agent. You can do this on the Runway platform, via the ChatGPT Runway Plugin or using Runway MCP. I asked the Agent the following: "Can you make a 30 second seedance 2.5 optimised prompt where the story is someone on vacation (beach/zipline/kayaking/hotairballoon/etc.) gets texted by his boss for one final change ASAP. They then look slightly concerned followed by the camera zooming out to reveal a vast landscape. Make sure to end on a super wide shot so that taglines can be added." It ran some thoughts by me, and as I genuinely didn't expect this to blow up, I just blindly let it do its thing and told the agent to start the video generation. The result is the one that you saw a few days ago. Keep in mind that results may vary, as many agents create personalized profiles of you based on their previous conversations. Once you have a prompt/result you like, you can go back to the agent and ask something like the following to get more variations: "What are other funny situations we can do that use the exact same structure?" ------------------------------ You can also skip all that, as I am sharing the exact prompt I used below. I used Seedance 2.5 set to 30 sec duration for my ads. 720p gives you that $9 ad, however you can also run it at 1080p for a more final production spec asset. You can also give the prompt to an LLM and ask it to make new narrative scenarios, using the exact same prompt structure. 🧵 Prompt is in the thread below! 🧵 Thank you for all the love on the ad. I've already seen a bunch of spin-offs, and can't wait to see even more.
0:30

Full Breakdown: How I Created a Viral Ad This will be a very long post as I will provide you with the exact way I achieved the original ad, as well as a prompt that get's you straight to the result in case you want to speed-run it. How I created the original: I made the ad collaborating with an agent. You can do this on the Runway platform, via the ChatGPT Runway Plugin or using Runway MCP. I asked the Agent the following: "Can you make a 30 second seedance 2.5 optimised prompt where the story is someone on vacation (beach/zipline/kayaking/hotairballoon/etc.) gets texted by his boss for one final change ASAP. They then look slightly concerned followed by the camera zooming out to reveal a vast landscape. Make sure to end on a super wide shot so that taglines can be added." It ran some thoughts by me, and as I genuinely didn't expect this to blow up, I just blindly let it do its thing and told the agent to start the video generation. The result is the one that you saw a few days ago. Keep in mind that results may vary, as many agents create personalized profiles of you based on their previous conversations. Once you have a prompt/result you like, you can go back to the agent and ask something like the following to get more variations: "What are other funny situations we can do that use the exact same structure?" ------------------------------ You can also skip all that, as I am sharing the exact prompt I used below. I used Seedance 2.5 set to 30 sec duration for my ads. 720p gives you that $9 ad, however you can also run it at 1080p for a more final production spec asset. You can also give the prompt to an LLM and ask it to make new narrative scenarios, using the exact same prompt structure. 🧵 Prompt is in the thread below! 🧵 Thank you for all the love on the ad. I've already seen a bunch of spin-offs, and can't wait to see even more.

Nicolas Neubert

64,760 Aufrufe • vor 17 Tagen

Seedance 2.0 is insane. Blender previs is having a moment in AI filmmaking for a reason. I wanted to see how far I could push the workflow beyond a simple camera move in an ambush scene. The workflow: 1. Make a start image in Midjourney 2. Block it out in Blender, animate the camera 3. Feed both to Seedance The more I test this pipeline, the more convinced I am that hybrid pipelines are the future. The conversation is moving fast but previs is one of the clearest unlocks so far. Seedance still isn't perfect at matching the reference but it's close. You can experiment with staging, timing, and camera movement before you ever touch the video model. Solve the scene before you generate the shot.
0:44

Seedance 2.0 is insane. Blender previs is having a moment in AI filmmaking for a reason. I wanted to see how far I could push the workflow beyond a simple camera move in an ambush scene. The workflow: 1. Make a start image in Midjourney 2. Block it out in Blender, animate the camera 3. Feed both to Seedance The more I test this pipeline, the more convinced I am that hybrid pipelines are the future. The conversation is moving fast but previs is one of the clearest unlocks so far. Seedance still isn't perfect at matching the reference but it's close. You can experiment with staging, timing, and camera movement before you ever touch the video model. Solve the scene before you generate the shot.

Reid Hannaford

227,284 Aufrufe • vor 3 Monaten

Here's a badly made video of what I did for my final year project lads! Badly made for now, I'll make a detailed video in the first week of May, and a blog by the 3rd week of May. I have my exams and internship completion processes that I have to do, then I have to move from Pune to Mumbai, and then Mumbai to Surat. Crazy stuff, but I'll make sure that I have the time for this! There's so much that I have to share with you guys about this and my competency as an embedded software engineer! I just hope that some of you get inspired by my work and end up choosing the core engineering industries like I have! If you like what you see here, do share and retweet as much as possible. Thank you lads!
3:53

Here's a badly made video of what I did for my final year project lads! Badly made for now, I'll make a detailed video in the first week of May, and a blog by the 3rd week of May. I have my exams and internship completion processes that I have to do, then I have to move from Pune to Mumbai, and then Mumbai to Surat. Crazy stuff, but I'll make sure that I have the time for this! There's so much that I have to share with you guys about this and my competency as an embedded software engineer! I just hope that some of you get inspired by my work and end up choosing the core engineering industries like I have! If you like what you see here, do share and retweet as much as possible. Thank you lads!

kshitij vaze

25,189 Aufrufe • vor 1 Jahr

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

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

@levelsio

565,543 Aufrufe • vor 2 Monaten

I’m excited to share this performance video of “You Could Start A Cult” with you today: It’s the first of many performances that I shot with Vevo as a part of their Extended Play series that will be coming out over the next few weeks. Performing live is my favourite thing to do. To bring the songs I’ve spent so much time with, seen through from start to finish is an amazing feeling. Shooting these performances with Vevo was a really special experience. I was able to go back to the place where I made the music, an area of California I adore and have spent a lot of time in over my career. Watch it now on my Vevo channel and stay tuned for another performance video coming your way next week!
0:44

I’m excited to share this performance video of “You Could Start A Cult” with you today: It’s the first of many performances that I shot with Vevo as a part of their Extended Play series that will be coming out over the next few weeks. Performing live is my favourite thing to do. To bring the songs I’ve spent so much time with, seen through from start to finish is an amazing feeling. Shooting these performances with Vevo was a really special experience. I was able to go back to the place where I made the music, an area of California I adore and have spent a lot of time in over my career. Watch it now on my Vevo channel and stay tuned for another performance video coming your way next week!

Niall Horan

953,668 Aufrufe • vor 3 Jahren

I screened this latest AI short in Paris for the Prompt Club alongside a great showcase for French AI filmmaking talent. I think we have reached a tipping point where the quality of the models is no longer an obstacle to telling the story. Sure, there are problems with detail at distance, dynamic movement, and more than one character speaking or doing complex movement at the same time but nothing a director with awareness of the models can’t overcome. Kling motion control is a massive unlock, in this short I am playing all the characters so it’s quite broad because I am not an actor, but I have seen it used with professional actors and it captures real nuanced human performance, with everything that brings. I will be employing professional actors for my films in the future. This was made predominantly with Kling 2.5, and 2.6 motion with some seedance shots on the wider 2-shots. We are there, now go make your thing!
3:50

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

Uncanny Harry AI

10,292 Aufrufe • vor 8 Monaten

Dreamina Seedance 2.0 is by far the best video model I've tried, and Dreamina makes it even better. You can try it in the link below. It's not just about the quality of the output, but about how much control you have over your video's look. Watch my video here. I'm attaching reference images and asking the model to generate a video using them. I can reference each image using the @ symbol to instruct the model which image to use. You can even upload a clip and use its camera movement, styles from an image, and audio vibe from a track. By the way, you can take an existing video and replace, remove, or add elements to it while the model preserves everything else. This is the closest we've gotten to "editing videos like photos".
3:26

Dreamina Seedance 2.0 is by far the best video model I've tried, and Dreamina makes it even better. You can try it in the link below. It's not just about the quality of the output, but about how much control you have over your video's look. Watch my video here. I'm attaching reference images and asking the model to generate a video using them. I can reference each image using the @ symbol to instruct the model which image to use. You can even upload a clip and use its camera movement, styles from an image, and audio vibe from a track. By the way, you can take an existing video and replace, remove, or add elements to it while the model preserves everything else. This is the closest we've gotten to "editing videos like photos".

Santiago

46,575 Aufrufe • vor 6 Monaten

This video captures a performance of the famous song "I am the Very Model of a Modern Major-General" from the comic opera The Pirates of Penzance by Gilbert & Sullivan. This is an excerpt from a performance at the Stratford Festival in Canada in 1985.
4:32

This video captures a performance of the famous song "I am the Very Model of a Modern Major-General" from the comic opera The Pirates of Penzance by Gilbert & Sullivan. This is an excerpt from a performance at the Stratford Festival in Canada in 1985.

🎶𝗖𝗹𝗮𝘀𝘀𝗶𝗰𝗮𝗹 𝗠𝗲𝗹𝗼𝗱𝗶𝗲𝘀 ✨

14,393 Aufrufe • vor 3 Monaten