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.

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!show more

Curious Refuge

22,576 subscribers

16,487 views • 1 month ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

11 Comments

Alex1 month ago

what type of prompt do you use for something like this?

Genius💡💹🧲 🤖1 month ago

Character consistency plus depth guidance is a pretty powerful combo here

Vini1 month ago

Recreating specific body movements this well is a real technical feat.

biglootpig1 month ago

depth map loses facial performance. not a silver bullet for all use cases

AI Mastery Guide1 month ago

Depth maps for motion instead of the video itself, clever

Taro Bushidō1 month ago

Temporal consistency is the real differentiator here. Per-frame depth without it falls apart in dynamic scenes.

dubcreation25 days ago

I haven't tried this workflow yet, but have you tried feeding an audio reference along with the depth map, to see if the audio drives the lip movements?

madarbro1 month ago

I tested and found that if the OG video is a slow mo then the model struggles to replicate

lbarqueira1 month ago

Thanks. What shall be the prompt to generate the video in Seedance?

Trust⭕️29 days ago

This is wild

Sky Lu (Founder, Sky Studio)25 days ago

why can’t just use video editing? Depth map make it more accurate?

Related Videos

We just tested what might be the most accurate motion transfer workflow we've seen so far. It's a little more involved than a standard workflow, but the results are pretty impressive. Here's the basic workflow: 1. Start with your reference footage. Create character and environment references. 2. Convert the reference footage into a depth map (with Depth-Anything tool on Fal: 3. (Optional) Layer on additional guidance like colorized character masks (with Meta's Segment Anything: and or skeleton poses (with 4. Feed the depth map into Seedance 2.0 Omni as your motion reference along with your character and environment references. 5. Generate your final video. After testing several variations, the depth map workflow consistently produced the cleanest and most accurate motion transfer. If you're trying to recreate specific performances or complex movement, this is one of the closest AI workflows we've seen to achieving production-quality results.

We just tested what might be the most accurate motion transfer workflow we've seen so far. It's a little more involved than a standard workflow, but the results are pretty impressive. Here's the basic workflow: 1. Start with your reference footage. Create character and environment references. 2. Convert the reference footage into a depth map (with Depth-Anything tool on Fal: 3. (Optional) Layer on additional guidance like colorized character masks (with Meta's Segment Anything: and or skeleton poses (with 4. Feed the depth map into Seedance 2.0 Omni as your motion reference along with your character and environment references. 5. Generate your final video. After testing several variations, the depth map workflow consistently produced the cleanest and most accurate motion transfer. If you're trying to recreate specific performances or complex movement, this is one of the closest AI workflows we've seen to achieving production-quality results.

Curious Refuge

30,770 views • 1 month ago

For the facial animations in my game, I use a technique that yields results similar to L.A. Noire. To keep it simple: I first generate a facial animation video using AI like LTX 2. Then, I create a video depth map from that animation and project it onto a face mask. Using vertex displacement, the depth map dynamically deforms the face as the character speaks. The result looks good in standalone VR. I actually created this workflow long time ago:

For the facial animations in my game, I use a technique that yields results similar to L.A. Noire. To keep it simple: I first generate a facial animation video using AI like LTX 2. Then, I create a video depth map from that animation and project it onto a face mask. Using vertex displacement, the depth map dynamically deforms the face as the character speaks. The result looks good in standalone VR. I actually created this workflow long time ago:

Alex

48,296 views • 6 months ago

Kling AI 2.6 motion control is freaking awesome. All you need is one reference video and a character image. It handles facial expressions, body movement, and timing automatically. It even maintains consistent character details across frames. Here’s the full workflow 👇 1/6 #Kling #KlingAI

Kling AI 2.6 motion control is freaking awesome. All you need is one reference video and a character image. It handles facial expressions, body movement, and timing automatically. It even maintains consistent character details across frames. Here’s the full workflow 👇 1/6 #Kling #KlingAI

AshutoshShrivastava

31,682 views • 7 months ago

I just tested Motion Sync on Yapper and I like the cinematic Video made in minutes. Let me show you how you can do it 👇 Step 1: Open Step 2: Click on video and select Motion Sync. Then, ✅️Select base video Pick a video with the movement you want — this will drive the animation. ✅️Add reference image Upload your character or image you want to bring to life. ✅️Generate video Hit generate and watch your idea turn into a smooth motion sync clip. Simple, fast, and actually fun to experiment with.

I just tested Motion Sync on Yapper and I like the cinematic Video made in minutes. Let me show you how you can do it 👇 Step 1: Open Step 2: Click on video and select Motion Sync. Then, ✅️Select base video Pick a video with the movement you want — this will drive the animation. ✅️Add reference image Upload your character or image you want to bring to life. ✅️Generate video Hit generate and watch your idea turn into a smooth motion sync clip. Simple, fast, and actually fun to experiment with.

Leonardo

50,931 views • 4 months ago

I wanted to experiment with the image-to-video workflow on Pixmax using Seedance 2.5, and the results genuinely impressed me🔥 I created this short Lay’s commercial from just a couple of reference images, building a playful family story around them. What I really like about the workflow is the control over the environment, product and storytelling while still getting natural-looking motion.

I wanted to experiment with the image-to-video workflow on Pixmax using Seedance 2.5, and the results genuinely impressed me🔥 I created this short Lay’s commercial from just a couple of reference images, building a playful family story around them. What I really like about the workflow is the control over the environment, product and storytelling while still getting natural-looking motion.

Isabella

47,310 views • 16 days ago

How to extend videos using Seedance 2.0 in 3 easy steps 🦄 1. Generate video 1 (e.g. 15 seconds). 2. Use video 1 as a reference when generating video 2. 3. In the prompt for video two, start with "Continue this video". Both videos should have reference images of your characters. Here's a 30 second clip made with two 15 second generations. Workflow in comments below.

How to extend videos using Seedance 2.0 in 3 easy steps 🦄 1. Generate video 1 (e.g. 15 seconds). 2. Use video 1 as a reference when generating video 2. 3. In the prompt for video two, start with "Continue this video". Both videos should have reference images of your characters. Here's a 30 second clip made with two 15 second generations. Workflow in comments below.

Martin LeBlanc

25,133 views • 4 months ago

This is insane!🔥 This is a 720p (2D) video I shot of my kids 15 years ago! I used AI to upscale it, depth-map it, & used the depth map to convert it to 3D SBS, & then converted that to Spatial Video for Apple Vision Pro (MV-HEVC). My son is currently a senior in high school, and my daughter is a sophomore in college. This video has complete spatial depth when viewed in the Apple Vision Pro. Obviously, you can't appreciate that via this post. But it's like I'm there & I can see into this room. Talk about giving you the feels.🥹 This can be done with ANY video. 🤯 I'm working on refining the workflow, as it's a bit cumbersome. I plan to share it, but holy cow! I had to post this.

This is insane!🔥 This is a 720p (2D) video I shot of my kids 15 years ago! I used AI to upscale it, depth-map it, & used the depth map to convert it to 3D SBS, & then converted that to Spatial Video for Apple Vision Pro (MV-HEVC). My son is currently a senior in high school, and my daughter is a sophomore in college. This video has complete spatial depth when viewed in the Apple Vision Pro. Obviously, you can't appreciate that via this post. But it's like I'm there & I can see into this room. Talk about giving you the feels.🥹 This can be done with ANY video. 🤯 I'm working on refining the workflow, as it's a bit cumbersome. I plan to share it, but holy cow! I had to post this.

Blaine Brown

1,468,829 views • 2 years ago

Ok, this is absurd. You can choreograph a complex action scene in Blender with basic shapes, then let Seedance make it real. You need to try this AI filmmaking workflow: 1. Generate a start frame in Midjourney 2. Block out the action in Blender 3. Feed both to Seedance My Blender reference was just rough timing, camera shake, and spatial choreography, and Seedance tracked the speed, motion, and action way better than I expected. This is the difference between describing a shot and directing one.

Ok, this is absurd. You can choreograph a complex action scene in Blender with basic shapes, then let Seedance make it real. You need to try this AI filmmaking workflow: 1. Generate a start frame in Midjourney 2. Block out the action in Blender 3. Feed both to Seedance My Blender reference was just rough timing, camera shake, and spatial choreography, and Seedance tracked the speed, motion, and action way better than I expected. This is the difference between describing a shot and directing one.

Reid Hannaford

527,421 views • 2 months ago

Seedance 2.0 vs Gemini Omni, tested under the same conditions 👀 I was working on a new storyboard. After generating it with Seedance 2.0, I gave the exact same prompt + storyboard reference + character reference to Gemini Omni as well. Result: Gemini Omni surprised me with style quality and got closer than I expected in prompt adherence. But Seedance still feels ahead for storyboard execution, motion energy, camera language and environmental interaction. Gemini looks good. Seedance feels directed. You can see them in the video and the storyboard sheet is shown at the end. Which one do you think is more useful for this kind of work?

Seedance 2.0 vs Gemini Omni, tested under the same conditions 👀 I was working on a new storyboard. After generating it with Seedance 2.0, I gave the exact same prompt + storyboard reference + character reference to Gemini Omni as well. Result: Gemini Omni surprised me with style quality and got closer than I expected in prompt adherence. But Seedance still feels ahead for storyboard execution, motion energy, camera language and environmental interaction. Gemini looks good. Seedance feels directed. You can see them in the video and the storyboard sheet is shown at the end. Which one do you think is more useful for this kind of work?

Kōda

36,082 views • 3 months 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.

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 • 7 months ago

Google Gemini Omni is here Generate, animate and edit any video with one model → Edit with your words: a character, a camera angle, the action → Motion that behaves like the real world → From reference to a cinematic scene Now on Magnific, via Magnific MCP and Spaces

Google Gemini Omni is here Generate, animate and edit any video with one model → Edit with your words: a character, a camera angle, the action → Motion that behaves like the real world → From reference to a cinematic scene Now on Magnific, via Magnific MCP and Spaces

Magnific

88,179 views • 2 months ago

Introducing Character Motion Control for Video Diffusion Models Creators currently lack control over how characters move and act in the videos they generate with AI. Today, we’re changing that. With Character Motion Control, you can act it out and bring your exact vision to life. How it works: 1️⃣ Describe the scene with a prompt 2️⃣ Upload an acting video to guide character movement 🎥 Generate a video where character motion is driven by the acting video. Register for Early Access via the link in the comments.

Introducing Character Motion Control for Video Diffusion Models Creators currently lack control over how characters move and act in the videos they generate with AI. Today, we’re changing that. With Character Motion Control, you can act it out and bring your exact vision to life. How it works: 1️⃣ Describe the scene with a prompt 2️⃣ Upload an acting video to guide character movement 🎥 Generate a video where character motion is driven by the acting video. Register for Early Access via the link in the comments.

Kinetix

97,996 views • 1 year ago

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.

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 views • 4 months ago

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 Seedance with this prompt "A cinematic close up of an orc warlord giving a rallying speech to his army of orcs. Transfer the performance, movement and audio from Video 1 onto the the character Image 1. Do not add any music" I didn't prompt the dialogue or performance in text. The first video you see is a a final cut of the video, the second is the final cut of the video with my video performance. As you can see it's not an exact like-for-like transfer of the performance and voice but more a interpretation by Seedance. It's made my amateur performance better IMHO, more fitting with the creator but retain the essence, nuance and context. So you don't have to feed in a long prompt to get good performance out of your AI actors you can just show them what you want with a video! I used Seedance Enterprise on bytedances lumina platform Lumina link in the comments!

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 Seedance with this prompt "A cinematic close up of an orc warlord giving a rallying speech to his army of orcs. Transfer the performance, movement and audio from Video 1 onto the the character Image 1. Do not add any music" I didn't prompt the dialogue or performance in text. The first video you see is a a final cut of the video, the second is the final cut of the video with my video performance. As you can see it's not an exact like-for-like transfer of the performance and voice but more a interpretation by Seedance. It's made my amateur performance better IMHO, more fitting with the creator but retain the essence, nuance and context. So you don't have to feed in a long prompt to get good performance out of your AI actors you can just show them what you want with a video! I used Seedance Enterprise on bytedances lumina platform Lumina link in the comments!

Uncanny Harry AI

23,258 views • 1 month ago

GPT Image 2 - Character Reference Sheet Prompt You can create a character reference sheet in any style you want for use in your Seedance 2.0 videos. All you need to do is either provide a reference image or describe your character. You can also input random values to generate completely random characters. This reference sheet provides a clear, structured, and highly readable visual breakdown of the character, helping the model maintain strong identity consistency across different outputs. The layout ensures the model focuses on essential visual information rather than stylistic noise, while the inclusion of expressions, head angles, and performance cues improves the model’s ability to generate believable acting and varied poses without losing character integrity. All clips in the demonstration video were generated using the reference sheet image and the same Seedance 2.0 prompt. You can find the prompts in the replies. 👇 GPT Image 2 and Seedance 2.0 are both available on mitte.ai

GPT Image 2 - Character Reference Sheet Prompt You can create a character reference sheet in any style you want for use in your Seedance 2.0 videos. All you need to do is either provide a reference image or describe your character. You can also input random values to generate completely random characters. This reference sheet provides a clear, structured, and highly readable visual breakdown of the character, helping the model maintain strong identity consistency across different outputs. The layout ensures the model focuses on essential visual information rather than stylistic noise, while the inclusion of expressions, head angles, and performance cues improves the model’s ability to generate believable acting and varied poses without losing character integrity. All clips in the demonstration video were generated using the reference sheet image and the same Seedance 2.0 prompt. You can find the prompts in the replies. 👇 GPT Image 2 and Seedance 2.0 are both available on mitte.ai

Kōda

164,464 views • 4 months ago

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.

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

17,412 views • 3 months ago

Did you know you can create captivating motion sync videos on Yapper Follow the steps below and push your creativity boundaries Step 1: Go to on your browser step 2: Click on videos and select Motion Sync Step 3: Select Base Video The video's movement will be used to animate the reference image. Step 4: Add Reference Image Upload an image of a character to be animated by the base video. Step 5: Describe Your Vision Write a prompt that guides the background of the output video. Step 6: Generate Select your model and the output video will be generated in real-time

Did you know you can create captivating motion sync videos on Yapper Follow the steps below and push your creativity boundaries Step 1: Go to on your browser step 2: Click on videos and select Motion Sync Step 3: Select Base Video The video's movement will be used to animate the reference image. Step 4: Add Reference Image Upload an image of a character to be animated by the base video. Step 5: Describe Your Vision Write a prompt that guides the background of the output video. Step 6: Generate Select your model and the output video will be generated in real-time

Kuria | AI

46,344 views • 4 months ago

ACTORS ARE COOKED WITH GEN AI.... NO! ACTORS WILL COOK WITH GEN AI! Kling Just rolled out Kling 3.0 with Omni and motion control models. The new motion control gives you really detailed performance capture so you can transfer a genuine nuanced human performance onto your AI characters. You can also blend that performance in with AI generated events , using Kling's start and end frame workflow. So your character can interact with the AI generated environment, or fly or transform into something else. Actors now it the time to get involved. Kling AI P.S Sorry for my G.C.S.E level acting, for reference only 😂

ACTORS ARE COOKED WITH GEN AI.... NO! ACTORS WILL COOK WITH GEN AI! Kling Just rolled out Kling 3.0 with Omni and motion control models. The new motion control gives you really detailed performance capture so you can transfer a genuine nuanced human performance onto your AI characters. You can also blend that performance in with AI generated events , using Kling's start and end frame workflow. So your character can interact with the AI generated environment, or fly or transform into something else. Actors now it the time to get involved. Kling AI P.S Sorry for my G.C.S.E level acting, for reference only 😂

Uncanny Harry AI

25,521 views • 6 months ago

Pls pls pls read 1 comic this morning for free and lmk what you thought of the story Reply with a in depth review or even video review and with your ETH wallet as I want to gift a few of you your first VeeFriends nft if you do so..If you’re VF curious … this is the time to jump in

Pls pls pls read 1 comic this morning for free and lmk what you thought of the story Reply with a in depth review or even video review and with your ETH wallet as I want to gift a few of you your first VeeFriends nft if you do so..If you’re VF curious … this is the time to jump in

Gary Vaynerchuk

46,169 views • 1 month 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

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