Wan Animate 2 is in ComfyUI with native support... he driving video goes straight into the transformer. No motion extractor in the middle, so nothing gets flattened before generation starts — subtle expression, finger position, all of it survives. Better motion. Stronger identity. And the camera is yours: viewpoint is text-driven, decoupled from whatever the driving clip was shot on. Wan Animate 2 Lite runs at real-time latency. Click the link below for the workflows and the blog👇show more

🚨 Wan Motion is now live on fal !... An optimized version of Wan 2.2 Animate. 🎬 Transfer motion from any driving video to a single reference image 🎭 Built-in motion retargeting, adapts to different body proportions ✨ Optional Flux 2 Edit identity enhancement for sharper character preservation 💸 Just $0.06/s for 720p, the cheapest motion transfer API availableshow more

SAM 3D Body is open-source, so it can be... run locally or on Comfy Cloud. Extract motion from a recording → bring it into Blender → control the camera → use the result with Seedance 2.5 More control over body motion and camera movement. To try this workflows, links below 👇show more

Real Human support for Seedance 2.0 is now available... in ComfyUI. Unlock real human video generation with Seedance 2.0 now in ComfyUI. This unlocks real-person video generation with consistent identity and authentic facial expressions — after a one-time verification.show more

How to animate a photo with Grok imagine :... 1-import the photo in Grok imagine 2-Click on Animate That's it ! And the result is sublime. See video 👍 Original photo below⏬show more

The Grok Imagine updates keep accelerating. Reference-to-Video + Video... Extend just landed! Live in ComfyUI on Day 0. The generation speed alone makes it worth trying. Reference-to-Video: add up to 7 reference images to generate consistent characters and scenes Video Extend: seamlessly extend any video with smooth, natural motion Workflows and more details about the Grok updates below ⬇️show more

The next frontier in AI video isn't better motion... - it's better perspective. What used to require a full production setup, camera rig, location scout, multi-shot choreography - now starts with a single image inside Comfy. Creator seungho__yeo ( IG ) used Hyper POV + Seedance 2 to build a complete cinematic space traversal from one still frame: → Aggressive first-person orbit through the full environment → Fly-through movement that inhabits the space, not just records it → Motion blur and single-take continuity that holds the cinematic feel end to end → No cuts. No rig. One image as the source of truth. This is what perspective design looks like at the new baseline.show more

Turn one idea into a complete storyboard, then animate... it in Seedance 2.0 using a reference image. This ComfyUI workflow uses LLMs to build storyboard scenes and prepare them for Seedance, making the jump from concept to animation much easier. Link below 👇show more

In this setup, a Blender blockout provides the motion... and composition while a reference image guides the environment, subject, and textures with MiniMax H3. With open weights, you can previs the final look locally for free or run it on Comfy Cloud. To try this workflow, link below 👇show more

Okay, this is the kind of AI video that... makes you watch the clip twice. Wan 3.0 on Magnific surprised me with how well it handles dialogue, camera movement, and character consistency in the same generation.show more

Wan 3.0 is live on Magnific. One generation now... takes 20 references at once: 10 images, 5 audio, 5 videos. Not one style ref. Twenty. What that actually changes: Length : 2 to 30 seconds in a single pass. No stitching, no extending clip by clip and praying the character survives the cut. Native audio : voice, ambience and SFX generated with the video, not laid on top afterwards. Multiple ratios available , and adaptive the model composes for the frame instead of cropping into it. 10 image refs : a character, a product, a location and a lighting look can all hold in the same shot. ⚡ 40% off until September 30. More details in comments 👇 What's the first thing you'd throw 20 references at?show more

You can create split-stack videos like this in one... click with the link below.👇 In the simple version, all you have to do is upload an image and it handles everything for you. But if you want more control, you can jump into graph mode and tweak each parameter to get more detailed, custom results.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

A guy from China is reshaping glowing particles into... a jellyfish, a statue, a dragon, and a samurai just by moving his hands in front of a camera No controller, no mouse, no keyboard Just a camera reading his hand position and a particle system recalculating thousands of points in real time, morphing one shape straight into the next Clench both fists at the end, and everything collapses into nothing This is running live at 60fps, not pre-rendered The entire scene sits inside a wireframe box tracking every motion as raw geometry reshapes into whatever his hands tell it to becomeshow more

Using Blender camera animation with Seedance 2.0 gives you... a lot more control over your shots. By keyframing the camera in Blender, you can precisely define movement, rotation, and framing, then bring that motion into Seedance. It's a great workflow for previs-style blockouts or any shot where intentional camera movement matters. To try this workflow, link below 👇show more

Unreal 5.6 Motion tools let you send shockwaves through... the environment in the style of Quantum Break, all procedural & no sim. In real-time and now officially supported for packaged game projects. We set this up inside Unreal Motion 5.6, link is below.show more

Create a storyboard, feed it into Seedance 2.0, and... let an LLM analyze the storyboard to generate better prompts. A practical way to turn visual planning into more controlled and consistent video generation. To try this workflow, link 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

This ComfyUI workflow lets you draw lines and annotations... to guide motion, define where actions should happen, and influence movement throughout a scene. An integrated LLM translates those annotations into prompt instructions, making it easier to direct motion visually instead of relying entirely on text prompts. The workflow works best with clear, intentional paths, while more complex routes with frequent direction changes can be harder to follow consistently. To try this workflow, link below 👇show more