Testing SCAIL-2, an open source model for motion transfer.... I wanted to see how it can handle driving videos with fast, dynamic movement. The part that really impressed me was how the model retained details from the input character's outfit (especially the straps on the shorts). I attached the input character below for you to compare against. The model also has a replacement mode that swaps the character into the driving video's scene, but here I used animation mode, which keeps the reference image's scene instead.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

Seedance 2.0 has a fix for character drift almost... nobody uses. Every new text description is a fresh interpretation of appearance. That's where the drift comes from: a slightly different face, a slightly different outfit, proportions that shift from scene to scene. The @ Image tag solves this directly — attach a photo once, and it becomes the fixed source of truth for face, outfit, and proportions across the entire multi-shot sequence. The @ Video tag works the same way for motion and camera — tag a reference instead of describing it, and the model copies that exact style instead of an approximation. You're not making the model remember. You're just stopping yourself from reminding it differently every single time.show more

Video Model Comparison: Image2Video Same input image + text... prompt on each model: • Pika 2.0 • OpenAI Sora • Runway Gen-3 • Kling AI 1.6 • Luma Dream Machine • Hailuo MiniMax I used the same prompt that I used to generate this image in Midjourney and chose the best results for each model tested. The prompt didn't include specific camera motion, so it was interesting to see each model's interpretation:show more

Here it is! I wanted to make a short... animation to show off the rig and model, so here's Sarahtrap from I'm Not The Purple Guy comic! Character by @TennMiddle Model, Rigging, and Animation by me! #Sarahtrapshow more

I wanted to see how well Kling 4.0 could... handle a cinematic Wuxian action sequence, especially with all the fast movements and camera changes involved. What impressed me most was how naturally the action flowed. The character movements felt coordinated, the camera followed the action smoothly, and the overall scene had that cinematic martial arts film feeling I was going for. This is the kind of control I’ve been wanting from AI video generation. Instead of just producing beautiful frames, Kling AI 4.0 is making complex action storytelling feel much more achievable. Here’s how it turned out 👇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

New Model! Egyptian Girl I made the model according... to an art on Pinterest I learned a lot about how to make better hair. #lowpoly #blender #character #3DModel #animationshow more

GPT-6 Astra + MiniMax H3 A workflow I've been... experimenting with: First, used GPT-6 Astra with Blender to create the base video as a simple 3D previs. Then took that video into MiniMax H3 and used a character reference + prompt to replace the placeholder object, populate the environment and transform the whole scene into a polished 2D anime sequence. The useful part is that Blender already solves the camera path, timing, scale, blocking and environment geometry. So instead of asking the video model to figure out everything from scratch, you give it a moving blueprint and let it focus on the character, animation and final look. You can find the MiniMax H3 prompt below. Used a premade model from sketchfab for this experiment: "Day 5. Final:The Western Saloon" ( by Olyona Kuznetsova is licensed under Creative Commons Attribution.show more

Seedance 2.0 has the most accurate character swap available... in my opinion. It's managed to maintain complete scene continuity. I can't see anything else that has changed in the entire scene. It's also maintained accurate camera motion and character movement and just swapped out the character as instructed. The best way to see accuracy is to showcase both clips. All you have to do is upload the video you want to replace the character in as an OMNI Reference and an image of the character to replace them with and type in the following prompt and adjust as needed: Keep the scene the same but just swap the women with the grey shirt with a completely different person, it's the black female in Image1 wearing a dark blue knitted sweater. #CapCutSeedance2 CapCutshow more

Kling 3 is a remarkable model. This was a... one-shot generation from an input image and text prompts - the model retained character, scene, and voice consistency across cuts 🤯 IMO this is a step-function change in capabilities. If you haven't tried it yet, head over to fal!show more

Testing out runway’s first frame as a relighting tool.... I relit the frame with Magnific. The Magnific relight isn’t perfect and can change the character a bit but it seems like the runway part stays pretty true to the input.show more

i built an open world minigame that's controlled with... hand movements only here's a step-by-step tutorial: > started with my mediapipe + threejs template (see QT) > added a 3D model made by quaternius > sent a few prompts to gemini 3... --- prompt #1: repurpose the attached script, but now I want to import a gltf model (assets/model.gltf) and use that in the scene instead of the cube when the user moves their hand, a waypoint indicator should move around the scene, and the 3D model should smoothly move there when the user makes a fist, the model should jump the 3D model contains bundled animations in it. use the "idle", "run", and "jump" animations --- prompt #2: make this a procedural open world adventure. generate very simple procedural voxel terrain when the model gets near the edges of the screen, the camera should move, allowing the model to keep going in that direction --- prompt #3: add some floating glowing gems around the map that the user can collect --- i made some manual tweaks for styling and game feel, but that's the gist of it thanks for reading if you got all the way here full code is available at my link in bioshow more

Finally, now that I’ve finished, I can announce that... I’ve created a model for Aqua Star – a complete remake based on the previous generic model, which was a combination of others. This time, the entire model has been rebuilt from scratch, right down to the new rig.show more

Introducing: Nvidia Pro Mode! Basically GPT-5 Pro, but for... the new Nvidia open source model :) Pro Mode chains together up to 50 instances of the new Nemotron 9B model, enabling it to produce a better answer than one instance alone could create! Open source, link here:show more

Here's a good example of how you can use... Seedance 2 to edit videos. In the opening shot of the Thriller movie clip I posted last night, I had a generation that was perfect, with the exception of a man entering the scene at the end, and running past the woman. Didn't want that! So, I uploaded the video into Seedance 2's Omnireference on Dreamina AI and used the following prompt, which worked like a charm! The "EDIT THE VIDEO - remove the man in the white shirt who enters the scene at 00:07 seconds. The woman in the yellow dress is the only character we should see in this scene. Maintain all other details." Before (left) and After (right).show more

🚨 Wait… I think I just discovered something HUGE... about AI-generated 3D models. I found Hyper3D’s new Agentic Mode that can BUILD, EDIT & ANIMATE 3D models!! And there’s one thing that really surprised me. Unlike regular 3D generation, Agentic Mode can automatically filter and organize more informative input. You can give it different views, individual parts, or even a single reference image of separate components… And it can figure out how they fit together and generate a complete 3D model — with surprisingly accurate structure and details. That’s something I haven’t seen regular 3D generation handle this well. Check out this 3D windmill animation 👇 Hyper3D Agentic Mode lets you control 3D models with PARAMETERS !! Instead of rebuilding the sofa from scratch, you can change things like: → Parametric Control → Animation Pressets → Enhance Materials So you can generate the model once... and keep editing its geometry without starting from scratchshow more

Guys, I translated the model into English, but unfortunately,... for some reason, the parameters were hidden when I added it - I'm so sorry! Here’s how to translate the model into English and reveal the customization parameters.show more

Here it is! An incredibly fast model that’s unrivaled,... especially when it comes to motion graphics. AND YES! This video was also made using this model! I’ll be posting a fal guide very soon to help you create the best videos with this model.show more

gemini omniflash is actually f*cking cracked. you can animate/edit... any video with a text prompt. character swaps, object transforms, full environment changes without regenerating/rotoscoping. everyone using AI to to animate and edit videos right now hits the same wall. the clip comes out 90% right and you regenerate from scratch hoping the 10% fixes itself. it never does. the fix is using your video as the input. omniflash edits what's already there instead of rolling the dice again. here's what's in the system: > the two-layer premiere trick: generate the same shot twice (one with background removed), stack them, cut at one frame, instant scene change > character swap with a single reference image (plus the one line you need or the model keeps the original's features) > object transforms that leave the rest of the frame untouched: stone into glowing sphere, candles into flowers > style transfer from an image reference instead of text, way more accurate > why stacking edits in one prompt breaks everything and the exact step order that doesn't > the audio limitation nobody mentions and how to work around it i packaged every prompt, the edit sequence, and the premiere layering setup. RT + reply "OMNI" and i'll send it over.show more