After extracting the depth video, the effect obtained by... video referencing is very good. 1. Prepare the reference video 2. Extract the depth video 3. Prepare the character reference images 4. Input the extracted depth video and character reference images into seedance2, and you will get perfect results Complete workflow is below:show more

1. Reference Video -> Convert to Depth Map 2.... Depth Map -> Seedance 2.0 (Reference Video) 3. Add Reference Image 4. Set Duration / Resolution / Aspect 5. Pass Audio from Reference Video -> Final 6. Hit Runshow more

🤯 Found another great use case for Depth today!... I tried recreating this fashion transformation video with my own character, but the original character kept showing up. 🌟 So I switched the reference video to Depth, and it worked way better! Same motion and timing, but now I can use my own character and completely new outfits! Quick workflow in the comments Full Depth workflow in the quoted post 👇show more

Guys, Depth Map Control now live on Mini Apps... The workflow is quite easy: reference video -> depth map video -> reference image + depthvideo -> a video that follows motion and space more precisely. RT + Follow + Reply = 150 Credits in DMs (72H ONLY)show more

Depth video workflows have been getting a lot of... attention lately, so I tested one myself. Combined with Seedance 2.0, it produced more natural motion-transfer results than using Kling Motion Control directly. Why use a depth video? 1. It removes the original character and scene details, reducing copyright and sensitive-content risks. 2. It preserves the original motion, timing, and spatial structure. This separates motion extraction from visual generation, allowing you to recreate the movement with better models and any reference character. We’ve also launched a free online tool that converts regular videos into depth videos—no local setup required: In the example below, we converted a dance video from Douyin into a depth video, then regenerated it with a reference character using Seedance 2.0. The original choreography and timing are preserved, while the lighting adapts naturally to the new character and scene.show more

🤯 Depth can now recreate complex climbing and parkour... motion this cleanly! Turned a fast climbing clip into a Depth motion reference, then swapped in a 20-year-old twin-tail student with a backpack while keeping the same concrete structure. Wall contact, weight shifts, jumps, climbing paths, and full-body movement all stay surprisingly clean and consistent! 🌟 Workflow: 1. Pick a reference clip under 15 seconds 2. Convert it to Depth with Depth Anything V2 3. Generate a new character + scene 4. Feed everything into Seedance with the prompt below 🌟 Depth video conversion: You can build a local Depth converter with Codex — prompt in the comments. Dance, martial arts, climbing, parkour, and other complex movements can all be transferred cleanly with Depth! Workflow + Prompt below 👇show more

New fal workflow: video restyling with Video Depth Anything... and Seedance 2.0 - Restyle the first frame into your target look - Extract consistent depth across the source video - Use that depth to guide Seedance 2.0 through the full sequence - Preserve the original motion and composition while transforming the visual style A simple workflow for turning existing footage into stylized video.show more

Let's create a music video with these characters. Used... the Midjourney images directly into Seedance 2.0 and added the track I created in Suno as a blackout video reference. You can find the prompt below.show more

THE DEPTH MAP TRICK THAT FIXED DANCE ACCURACY IN... SEEDANCE 2.0 Feed the model a video of someone dancing and it tries to interpret everything- the person, the clothes, the lighting, the room, and somewhere in there, the movement. Feed it a depth map and there's nothing left to interpret but the motion. Most creators trying to transfer a dance to a character reference the source footage directly, then wonder why the choreography drifts. The problem isn't the model - it's that you handed it ten variables when you only wanted one. Here's the workflow 1. Lock the character reference in GPT Image 2 first -face, build, costume, so identity holds independently of whatever motion gets applied to it 2. Convert the source dance footage into a depth map instead of using the raw video -this strips out the original performer's appearance, clothing, and environment entirely 3. Feed the depth map as the motion reference and the character sheet as the identity reference- two separate inputs doing two separate jobs, not one input trying to do both 5. Let the depth map carry only spatial movement -the model receives body position and momentum with no competing information about who's moving or what they look like 6. Keep the character and motion inputs isolated throughout - the moment you mix appearance data into the motion reference, the model starts negotiating between two identities Why this works • Raw footage passes the model everything at once- performer, wardrobe, room, lighting -and the choreography competes with all of it for attention • A depth map is pure spatial information, so the only thing left to transfer is movement • Separating identity from motion means the character can stay locked while the dance stays accurate - normally you're trading one for the other • The accuracy gain isn't the model getting better, it's the model getting fewer decisions to make Use cases: ⁃ Dance and choreography transfer onto original characters ⁃ Motion capture-style workflows without motion capture ⁃ Any sequence where a specific movement needs to survive intact ⁃ Character showcase content built on existing performance footage The character sheet answers who's dancing. The depth map answers how - and keeping those two questions separate is the whole trick.show more

THE DEPTH MAP TRICK THAT FIXED DANCE ACCURACY IN... SEEDANCE 2.0 Feed the model a video of someone dancing and it tries to interpret everything- the person, the clothes, the lighting, the room, and somewhere in there, the movement. Feed it a depth map and there's nothing left to interpret but the motion. Most creators trying to transfer a dance to a character reference the source footage directly, then wonder why the choreography drifts. The problem isn't the model - it's that you handed it ten variables when you only wanted one. Here's the workflow 1. Lock the character reference in GPT Image 2 first -face, build, costume, so identity holds independently of whatever motion gets applied to it 2. Convert the source dance footage into a depth map instead of using the raw video -this strips out the original performer's appearance, clothing, and environment entirely 3. Feed the depth map as the motion reference and the character sheet as the identity reference- two separate inputs doing two separate jobs, not one input trying to do both 5. Let the depth map carry only spatial movement -the model receives body position and momentum with no competing information about who's moving or what they look like 6. Keep the character and motion inputs isolated throughout - the moment you mix appearance data into the motion reference, the model starts negotiating between two identities Why this works • Raw footage passes the model everything at once- performer, wardrobe, room, lighting -and the choreography competes with all of it for attention • A depth map is pure spatial information, so the only thing left to transfer is movement • Separating identity from motion means the character can stay locked while the dance stays accurate - normally you're trading one for the other • The accuracy gain isn't the model getting better, it's the model getting fewer decisions to make Use cases: ⁃ Dance and choreography transfer onto original characters ⁃ Motion capture-style workflows without motion capture ⁃ Any sequence where a specific movement needs to survive intact ⁃ Character showcase content built on existing performance footage The character sheet answers who's dancing. The depth map answers how - and keeping those two questions separate is the whole trick.show more

Midjourney + GPT Image 2 + Seedance 2.0 -... Prompt Share Zero Trace 1. Generate the character. - Midjourney v8.1: hacker girl --ar 2:3 --profile w9b13s1 --stylize 1000 2. Create a character sheet. 3. Create a storyboard using the character sheet as the character identity reference. 4. Create the final video using both the character sheet and storyboard as references. You can find the prompts below.show more

Turn a simple idea into a storyboard, then generate... the video with Seedance 2.0. This ComfyUI workflow uses LLMs to structure prompts into storyboard-ready scenes that define how the video should play out. The storyboard can be paired with reference images and sent directly into Seedance for video generation. To try this workflow, link below 👇show more

MiniMax H3 Character Board Animation (Bottom Video) & Character... Intro Animation (Top Video) First, we create our character board in GPT Image 2 or Seedream 5 using our character reference image. Then, we use that board as a reference in MiniMax H3 to turn it into an animated character board. Also, you can create another character animation with this board. You can find the prompts below.show more

Nano Banana 2 now takes video as input 🍌... - Drop a video, get context-aware images out - Thumbnails & infographics generated from your footage - Character and style consistency across frames - Edit outputs with a reference image + prompt Feature available on Runware nowshow more

🔥 AI video creation is finally evolving beyond basic... motion prompts. Try out Depth Map Control right here: Historically, the hardest part of the process has been maintaining scene consistency: • camera movement • object placement • spatial relationships Thanks to PixVerse Depth Map Control, you can now grab depth data from a reference video and merge it with a fresh image to explore highly directed video generation. The final outcome? Much smoother camera tracking. Highly cohesive visual scenes. It is a powerful workflow that hands creators actual authority over how their AI visuals shift and flow over time. 🎬show more

Recreating a video's style normally takes hours of editing... and iteration. With Wizstar_official Video Reference feature, I simply uploaded a reference video and let AI do the work. The results were surprisingly close to the original feel. 👇show more

AI video is becoming less about generating a clip... and more about controlling the entire scene. 🎬 MiniMax H3 is now available on Magnific, with a multimodal workflow that brings text, images, video and audio together. → Up to 9 image + 3 video + 3 audio references → 2K video up to 15 seconds → Native synced voice, music & sound effects → Motion transfer → Instruction-based video editing → Camera, character and voice control The interesting part is how much you can build from references. A moodboard, product, character, environment or motion reference can all become part of the same generation. And the sound is generated alongside the video, instead of being added afterward. MiniMax H3 on Magnific makes the whole process feel much closer to directing a scene than simply prompting a video.show more

Seedance 2.0 - Advanced Workflow Series 🧵 7. Storyboard... to Video Provide basic storyboards along with a character sheet and environment images. Seedance will create a complete sequence by connecting the shots, with cuts between the different panels. Workflow + Prompts 👇show more

KAIYA: The Wolf Blade GPT Images 2 + Seedance... 2 is an insane combo. Created the entire character sheet with GPT Images… Then turned it into a cinematic video using Seedance. this will change how we create AI videos... Prompts below: ↓show more

Starting from only a few reference images… Magnific Spaces... turned them into a complete cinematic video sequence. The final result keeps the same mood, style, and visual identity surprisingly well across the entire clip. Magnific (formerly Freepik) #Magnificshow more

Create the viral “girlfriend opens the door” video with... GPT Image 2 + local MiniMax H3. 1️⃣ Use GenVizu Canvas Mode to generate the character and scene reference images. 2️⃣ Use my ComfyUI node to turn a simple prompt into a structured 6-part H3 prompt. 3️⃣ Wait & Enjoy! ✨show more