Loading video...

Video Failed to Load

Go Home

This is so much fun—it actually worked! You’ll need three reference images: one for the character, one for the stage, and one for the pose. I’ve put together all the reference materials and the English prompt here 👇

underwoodxie96's profile picture

underwood

42,573 subscribers

441,849 views • 1 day ago •via X (Twitter)

Science & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

One prompt. Multiple gaming scenes 🎮 The Nano Banana agent can generate several images at once, using a reference image to keep the same person consistent across scenes. This example spans different gaming eras, but the same approach works for any theme or style. Images and videos, all in one place. Agent + prompt 👇
0:24

One prompt. Multiple gaming scenes 🎮 The Nano Banana agent can generate several images at once, using a reference image to keep the same person consistent across scenes. This example spans different gaming eras, but the same approach works for any theme or style. Images and videos, all in one place. Agent + prompt 👇

GLIF

10,882 views • 6 months ago

the director and character designers of ‘kpop demon hunters’ revealed that txt was one of the main groups used as reference for saja boys and yeonjun was the reference and inspiration for the member, romance.
0:22

the director and character designers of ‘kpop demon hunters’ revealed that txt was one of the main groups used as reference for saja boys and yeonjun was the reference and inspiration for the member, romance.

💬

685,606 views • 1 year ago

There is literally a song about Donald Trump called “The Chosen One.” I’ve never seen so much blatant idolatry for one man on the world stage. It’s impossible not to wonder if this is all setting the stage for something much bigger…
0:23

There is literally a song about Donald Trump called “The Chosen One.” I’ve never seen so much blatant idolatry for one man on the world stage. It’s impossible not to wonder if this is all setting the stage for something much bigger…

Donnie Discerned

40,520 views • 1 year ago

made this short tribute to Wong Kar Wai’s Fallen Angels with MiniMax H3 only used one prompt and two character reference images the native 2K output made a noticeable difference here, especially in the details and motion and the cost is much lower than Seedance 2 more experiments soon MiniMax Design (H3) #MiniMaxH3
0:29

made this short tribute to Wong Kar Wai’s Fallen Angels with MiniMax H3 only used one prompt and two character reference images the native 2K output made a noticeable difference here, especially in the details and motion and the cost is much lower than Seedance 2 more experiments soon MiniMax Design (H3) #MiniMaxH3

Latte

20,925 views • 1 month 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.
0:56

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 • 2 months ago

Midjourney v8.2 + GPT Image 2 + Seedance 2.5 This video was created using one character reference and one environment reference. You can find the Midjourney, the character sheet and the Seedance 2.5 prompts below. Created with Seedance 2.5 on Astorie AI
0:30

Midjourney v8.2 + GPT Image 2 + Seedance 2.5 This video was created using one character reference and one environment reference. You can find the Midjourney, the character sheet and the Seedance 2.5 prompts below. Created with Seedance 2.5 on Astorie AI

Kōda

64,876 views • 23 days ago

Didn’t get the reference so he sang the song for me… never let me fumble this one
0:30

Didn’t get the reference so he sang the song for me… never let me fumble this one

Ren ❤️‍🔥

18,389 views • 5 months ago

This man is not only one of the best in the business, but is also one of the kindest human beings I’ve ever met. Thank you for all of the opportunities-you made every segment so much fun and it was a blessing to be on with you, Neil Cavuto! You’ll be incredibly missed!
2:20

This man is not only one of the best in the business, but is also one of the kindest human beings I’ve ever met. Thank you for all of the opportunities-you made every segment so much fun and it was a blessing to be on with you, Neil Cavuto! You’ll be incredibly missed!

Abby Hornacek

18,252 views • 1 year ago

Okay, so the power up transformation is much faster this time, and I love the ONE FOR ALL, ALL FOR ONE, WE ARE PRECURE! part so much!! It's so... perfect!! Minna de Tomorrow is one of the GOATs of all time! #precure
1:28

Okay, so the power up transformation is much faster this time, and I love the ONE FOR ALL, ALL FOR ONE, WE ARE PRECURE! part so much!! It's so... perfect!! Minna de Tomorrow is one of the GOATs of all time! #precure

Hibiki♡

18,998 views • 3 months ago

I wanted to do a couple pose and what better place to go for a reference than the The Pose Archives | Pose Reference ⚔️
1:03

I wanted to do a couple pose and what better place to go for a reference than the The Pose Archives | Pose Reference ⚔️

HAELE 3D - Anatomy Drawing Reference Tools

66,591 views • 9 months ago

Is it insane to call this one of the best scenes in the series? The character acting is so fluid (kinda looks like rotoscope) and the camera staying in this one angle for like 4 minutes does so much for the atmosphere How is this anime real man
1:11

Is it insane to call this one of the best scenes in the series? The character acting is so fluid (kinda looks like rotoscope) and the camera staying in this one angle for like 4 minutes does so much for the atmosphere How is this anime real man

Yasso | ياسو

70,206 views • 7 months ago

Introducing Ideogram Character -- the first character consistency model that works with just one reference image. Now available to all users for free! Create consistent character images in any style, expression, scene, and lighting. Who wants video next? 🥺
1:00

Introducing Ideogram Character -- the first character consistency model that works with just one reference image. Now available to all users for free! Create consistent character images in any style, expression, scene, and lighting. Who wants video next? 🥺

Ideogram

1,713,989 views • 1 year ago

FIRST TEST Seedance 2.0! From my initial tests, this is one of the more impressive AI video models I’ve tried so far. Dynamic motion feels fluid, prompt adherence is solid, and the efficiency really stood out, very little iteration needed. Everything you see here was generated using just one reference image + one prompt. I also tested a 3×3 image grid with no prompt at all, and the results stayed surprisingly consistent. Another highlight: sound design is already included, and it actually works really well. Tested via BytePlus 👉 More detail and access link to try Seedance 2.0 is in the comments.
1:34

FIRST TEST Seedance 2.0! From my initial tests, this is one of the more impressive AI video models I’ve tried so far. Dynamic motion feels fluid, prompt adherence is solid, and the efficiency really stood out, very little iteration needed. Everything you see here was generated using just one reference image + one prompt. I also tested a 3×3 image grid with no prompt at all, and the results stayed surprisingly consistent. Another highlight: sound design is already included, and it actually works really well. Tested via BytePlus 👉 More detail and access link to try Seedance 2.0 is in the comments.

Dinda Prasetyo

45,450 views • 6 months ago

❤️💛💙💚🧡 The Savannah Bananas Baseball Team from Georgia put together a video of the team dancing and singing to the 1D Movie Video ‘Best Song Ever’ on pitch!! They commented on their instagram saying “this one is for all directioners patiently waiting for the reunion tour” This is so much fun. I hope all of One Direction see it! 😂 🎥thesavbananas
1:17

❤️💛💙💚🧡 The Savannah Bananas Baseball Team from Georgia put together a video of the team dancing and singing to the 1D Movie Video ‘Best Song Ever’ on pitch!! They commented on their instagram saying “this one is for all directioners patiently waiting for the reunion tour” This is so much fun. I hope all of One Direction see it! 😂 🎥thesavbananas

For the Love of OT5 - Update Account

58,573 views • 2 years ago

The best feet pose drawing reference is the one you make for yourself with HAELE 3D ⭐️Now at a 40% Discount on Steam
0:59

The best feet pose drawing reference is the one you make for yourself with HAELE 3D ⭐️Now at a 40% Discount on Steam

HAELE 3D - Anatomy Drawing Reference Tools

131,907 views • 4 months ago

Fable 5 is back. So I gave it one of my favorite frontend tests: one prompt + one reference image. The task: rebuild a 3D globe dashboard.🌎 The result was almost too good. It did not just make a working page. The texture, lighting, spacing, depth, glass panels, and overall layout were all close to the reference. Some parts felt nearly pixel-level.
0:29

Fable 5 is back. So I gave it one of my favorite frontend tests: one prompt + one reference image. The task: rebuild a 3D globe dashboard.🌎 The result was almost too good. It did not just make a working page. The texture, lighting, spacing, depth, glass panels, and overall layout were all close to the reference. Some parts felt nearly pixel-level.

Kai

116,405 views • 2 months ago

Seedance 2.5 is now LIVE on OpenGradient! This entire film was generated from a single prompt. One take, no edits. → Up to 30-second clips from one prompt → 10,000 character prompts for full scene-by-scene direction → Up to 30 reference uploads for character and environment consistency → Native audio and sound design built in Even the judges agree: it's a 2.5. Try it now →
0:28

Seedance 2.5 is now LIVE on OpenGradient! This entire film was generated from a single prompt. One take, no edits. → Up to 30-second clips from one prompt → 10,000 character prompts for full scene-by-scene direction → Up to 30 reference uploads for character and environment consistency → Native audio and sound design built in Even the judges agree: it's a 2.5. Try it now →

OpenGradient (∇, ∇)

11,705 views • 23 days ago

Seedance 2.0 vs. Kling 3.0: Who delivers the most realistic emotional expressions? I put both models through the same test using one character, one reference image, and the exact same prompt. Each generated four emotions: anger, sadness, happiness, and disgust. Which AI video model handled the emotions better ?
0:28

Seedance 2.0 vs. Kling 3.0: Who delivers the most realistic emotional expressions? I put both models through the same test using one character, one reference image, and the exact same prompt. Each generated four emotions: anger, sadness, happiness, and disgust. Which AI video model handled the emotions better ?

FATHELA ESQ

38,646 views • 2 months ago

One of my friends was curious about my workflow for my renders, so I went ahead and threw this video together to show them. Original video is 12 minutes and 21 seconds. Pose reference photo from: Marvii The Collie Norspil made by: Vivi
3:11

One of my friends was curious about my workflow for my renders, so I went ahead and threw this video together to show them. Original video is 12 minutes and 21 seconds. Pose reference photo from: Marvii The Collie Norspil made by: Vivi

🧡🖤Aleks Vilong 🧡🖤 🔜Denfur

13,139 views • 5 months ago