Virtual Community provides an online pipeline that automatically generates... 3D scenes from real geospatial data, performing comprehensive cleaning and enhancement of both geometry and texture — including mesh simplification, texture refinement, object placement, and automatic annotation. 3/nshow more

Photorealistic Object Insertion with Diffusion-Guided Inverse Rendering discuss: The... correct insertion of virtual objects in images of real-world scenes requires a deep understanding of the scene's lighting, geometry and materials, as well as the image formation process. While recent large-scale diffusion models have shown strong generative and inpainting capabilities, we find that current models do not sufficiently "understand" the scene shown in a single picture to generate consistent lighting effects (shadows, bright reflections, etc.) while preserving the identity and details of the composited object. We propose using a personalized large diffusion model as guidance to a physically based inverse rendering process. Our method recovers scene lighting and tone-mapping parameters, allowing the photorealistic composition of arbitrary virtual objects in single frames or videos of indoor or outdoor scenes. Our physically based pipeline further enables automatic materials and tone-mapping refinement.show more

NVIDIA finally released Neuralangelo's source code! The model can... turn videos from any device into detailed 3D structures, fully replicating buildings, sculptures, or other real aworld objects or spaces virtually. Here's how it works: A model utilizes a 2D video with multiple angles of an object or scene. I selects frames from different viewpoints to understand depth, size, and shape. The AI creates an initial 3D representation, similar to a sculptor shaping a subject. The render is optimized to enhance details, like a sculptor refining texture. The outcome is a 3D object or scene suitable for virtual reality, digital twins, or robotics.show more

📢GeomHair: Reconstruction of Hair Strands from Colorless 3D Scans📢... We present a novel method to reconstruct hair strands from colorless 3D scans by extracting orientation cues directly from the mesh surface geometry by finding local characteristic lines and from shaded renderings using a neural 2D line detector. We enhance the reconstruction with a diffusion prior trained on synthetic hair data and adapted to each scan using a tailored text prompt, allowing us to recover both simple and complex hairstyles without relying on color input. To support further research, we also introduce Strands400, the largest publicly available dataset of 3D hair strand reconstructions from real-world scans of 400 different people, featuring complicated hairstyles, such as ponytails and buns. 🌍 📷 Great work by Rachmadio Noval L. Artem Sevastopolsky Egor Zakharov @ness_prisshow more

ImmerseGen: Agent-Guided Immersive World Generation with Alpha-Textured Proxies Contributions:... 1) We propose ImmerseGen, a novel agent-guided 3D environment generation framework. It uses simplified geometric proxies with alpha-textured meshes to produce compact, photorealistic worlds ready for real-time mobile VR rendering. 2) We propose a novel RGBA texturing paradigm. It first synthesizes 8K terrain textures using a geometry-conditioned panorama generator via user-centric mapping, and then directly generates alpha-textured proxy assets, avoiding fidelity loss typically resulting from mesh decimation. 3) To automate scene creation from user prompts, we introduce VLM-based modeling agents equipped with a novel grid-based semantic analysis. This enables 3D spatial reasoning from 2D observations and ensures accurate asset placement. ImmerseGen further enhances immersion with dynamic effects and ambient audio for a multisensory experience. 4) Experiments on multiple scene-generation scenarios and live mobile VR applications show that ImmerseGen outperforms previous methods in visual quality, realism, spatial coherence, and rendering efficiency for immersive real-time VR experiences.show more

As a graphics engine coder I think when you... look at a flickering bug like this one in the video below it’s not immediately obvious what is going on. The key here is observation - to study this flickering/bugged render carefully - what do we see? Firstly for me it was very obvious that nearly all of the scene shadows were flashing on and off - but (but!) there was a secondary issue where some buildings and parts of the sky were also flashing purple. Hmmmm. Interesting. I initially thought then this might be two separate bugs - but because the sky purple element could only based on full screen post fx and not 3D rendering I looked at this first with a few GPU captures to step through all our post processing to find the rendering stage which made these pixels turn purple: When I did this I found the colour 3D texture LUT grading that makes our different biomes have unique colour palettes was going very wrong - colours near 0 or 1 were wrapping and making the purple elements that we see in the said sky and base parts. The only way this could happen was if the texture was corrupt (which it was not) or if the 3D texture sampling was wrapping and not clamped as intended. That was the Eureka moment - because if the post fx had the wrong texture sampler then the disappearing shadows which also require an exact texture sampler for comparing depth might be also wrong because of the same kind of texture sampling issue! So with this idea that the engine was using the wrong texture samplers, but only in very high draw call scenes like the big base here I the looked at some engine limits and found the bug very quickly - a circular dx12 descriptor buffer for samplers running out over multiple frames, reusing the wrong data for new scenes inflight. Hence the flickering, as the GPU randomly got wrong samplers for some post textures or shadow depth. Easy to fix with triple limits for future expansion and also adding an assert/debug spam in case this limit is ever reached again - QA testers would see this message and report if they ever saw a flicker with this style of bug. My bug and my bad from 2017 porting NMS to DX12 without foreseeing how massively complex bases and our game would grow.show more

DroneSplat: 3D Gaussian Splatting for Robust 3D Reconstruction from... In-the-Wild Drone Imagery Abstract: Drones have become essential tools for reconstructing wild scenes due to their outstanding maneuverability. Recent advances in radiance field methods have achieved remarkable rendering quality, providing a new avenue for 3D reconstruction from drone imagery. However, dynamic distractors in wild environments challenge the static scene assumption in radiance fields, while limited view constraints hinder the accurate capture of underlying scene geometry. To address these challenges, we introduce DroneSplat, a novel framework designed for robust 3D reconstruction from in-the-wild drone imagery. Our method adaptively adjusts masking thresholds by integrating local-global segmentation heuristics with statistical approaches, enabling precise identification and elimination of dynamic distractors in static scenes. We enhance 3D Gaussian Splatting with multi-view stereo predictions and a voxel-guided optimization strategy, supporting high-quality rendering under limited view constraints. For comprehensive evaluation, we provide a drone-captured 3D reconstruction dataset encompassing both dynamic and static scenes. Extensive experiments demonstrate that DroneSplat outperforms both 3DGS and NeRF baselines in handling in-the-wild drone imagery.show more

📢 Our lab has been exploring 3D world models... for years — and we’re thrilled to share **PhysTwin**: a milestone that reconstructs object appearance, geometry, and dynamics from just a few seconds of interaction! Led by the amazing Hanxiao Jiang 👉 PhysTwin combines **Gaussian splatting** with **inverse dynamics optimization** based on simple **spring-mass** systems. ⚙️ The result? Real-time, action-conditioned 3D video prediction under novel interactions (i.e., 3D world models). 🔑 A few key takeaways: 1. Having the right structure (e.g., particles/masses) helps navigate the trade-off between sample efficiency, generalization, and broad applicability. 2. Visual foundation models (VFMs) have matured to the point where they can provide rich supervision for world modeling (e.g., tracking, shape completion). 3. Beyond VFMs, many crucial components have come together in recent years: Gaussian splats for rendering, NVIDIA Warp for high-performance simulation, and scene/asset generation from a wide range of labs and companies. The future of 3D world models is looking bright! ✨ 4. The resulting digital twin supports a wide range of downstream applications—especially in data generation and policy evaluation, thanks to its realistic rendering and simulation capabilities. 🎥 All code and data to reproduce the results, along with interactive demos, are available on the website. Check the following visualizations of: (1) observations, (2) reconstructed state/actions, (3) interactive digital twins, and (4) the overlays between real-world robot teleoperation and our model’s open-loop predictions.show more

Opus 4.6 vs GPT-5.4 (4/9) prompt: Build a production-quality... 3D flight-tracking web app using React + Vite + Three.js (react-three-fiber + drei) that visualizes live OpenSky aircraft data on a rotatable 3D Earth, with real-time plane motion, smooth interpolation, altitude-accurate positioning, and polished lighting/post-processing. Both models did really well on this one and honestly I’m impressed with both. GPT-5.4 had the nicer post-processing out of the box. I really liked the subtle light shimmer on the airplanes when rotating the planet, and the camera work when clicking a plane felt better overall. Opus 4.6 though had a few details I liked more. It automatically went and found a much nicer Earth texture on GitHub, while with GPT-5.4 I had to reprompt it to go look for a better one. I also preferred Opus’s plane model overall, it just looked more polished, whereas GPT-5.4’s plane asset looked a bit funny. One thing I noticed with GPT-5.4 is that when you click into the plane, the camera sometimes clips through the planet, which breaks the effect a bit. Opus handled that part more cleanly. Overall this felt like a strong result from both, just with different strengths. GPT-5.4 felt better on presentation and post-processing, while Opus had better asset choices and a more premium-looking Earth/plane combo.show more

Human3R: Everyone Everywhere All at Once Note: I recorded... the video from the interactive demo on their project page (linked in the comment below). Abstract (excerpt): Human3R jointly recovers global multi-person SMPL-X bodies ("everyone"), dense 3D scenes ("everywhere"), and camera trajectories in a single forward pass ("all-at-once"). Our method builds upon the 4D online reconstruction model CUT3R and uses parameter-efficient visual prompt tuning to preserve CUT3R's rich spatiotemporal priors while enabling direct readout of multiple SMPL-X bodies. Human3R is a unified model that eliminates heavy dependencies and iterative refinement. After being trained on the relatively small-scale synthetic dataset BEDLAM for just one day on one GPU, it achieves superior performance with remarkable efficiency: it reconstructs multiple humans in a one-shot manner, along with 3D scenes, in one stage, at real-time speed (15 FPS) with a low memory footprint (8 GB).show more

Natively integrated—and #PoweredbyPyth🔮 Native is a liquidity solution that... combines bridges, assets, and pricing into one offering on prominent L1/L2s, including . Learn more about our integration below: ℹ️ About Native Sourcing and supplying liquidity is expected to become prohibitively expensive and challenging as more networks emerge. Liquidity fragmentation persists because pricing remains inventory-based. Native was designed in response to this complexity and offers an elegant solution for routing any asset on one chain into a new target asset on any target chain. Native achieves this through a cross-chain liquidity mesh of cross-chain liquidity networks, bridges, DEXs, and PMMs. More specifically, Native can aggregate the best prices from its network of AMMs, aggregators, and partnered PMMs, so that users will always have competitive prices. 🔮 Native is #PoweredByPyth Native taps into Pyth’s real-time feeds to fetch prices on-chain and off-chain. for example, Native leverages Pyth Price Feeds to power ZetaSwap and support its token pricing operations. How Native Leverages Pyth Price Feeds Native runs its own in-house price-oracle service which will fetch pricing from a variety of sources, including Pyth, to update token prices in Native's backend server. These prices are then fetched and displayed to users live via the NativeX widget. Native also seeks to provide its proprietary trading data and become a part of the Pyth data provider community - more details to come.show more

A 14-year-old student ordered a Raspberry Pi Zero W... for $15, a small LCD screen for $12 and printed a case on a 3D printer for $3. $30 total and a package from AliExpress. He built a Pwnagotchi - a device that looks like a toy with a little face on the screen and automatically intercepts WiFi handshake packets nearby. Just sits on the desk, smiles and collects data. Then he used the intercepted data to break into the internal network where the GTA VI pre-alpha build was stored. The one Rockstar keeps locked away from everyone. The debug console appeared on screen. Jason's inventory. Simulation Variables - atmospheric controls, AI traffic behavior, coastal cliff region generative tests. Things only the developers were supposed to see. Rockstar spent 10 years and keeps a team of 2,000 engineers to protect that build. The student spent $30 and built the device in an evening.show more

OpenAI's AgentKit will be so insane, build every step... of agents on one platform. These visual agent builders make the whole process of iterating and launching agents far more efficient. It sits on top of the Responses API and unifies the tools that were previously scattered across SDKs and custom orchestration. It lets developers create agent workflows visually, connect data sources securely, and measure performance automatically without coding every layer by hand. The core of AgentKit is the Agent Builder, a drag-and-drop canvas where each node represents an action, guardrail, or decision branch. Developers can link these nodes into multi-agent workflows, preview results instantly, and version each setup. It supports inline evaluation so that developers can see how changes affect output before deploying. The Connector Registry is a single admin panel that manages how data and tools connect across the OpenAI ecosystem. It centralizes integrations like Google Drive, SharePoint, Dropbox, and Microsoft Teams. Large organizations can govern access and flow of data between agents securely under one global console. ChatKit provides a ready-to-use chat interface for embedding agents inside apps or websites. It manages streaming, message threads, and model reasoning displays automatically. Developers can skin the interface to match their product without writing custom front-end code. Under the hood, all these blocks use the same execution core that runs agent reasoning through OpenAI’s APIs. Workflows in Agent Builder compile down to structured instructions for the Responses API, which handles model calls, tool use, and context passing. Connector Registry handles authentication and routing for external tools, while Evals and RFT provide feedback loops that improve agents over time. This integration means developers no longer need to handle orchestration logic, model evaluation pipelines, or safety layers separately. Everything runs natively within OpenAI’s control plane with managed security, automatic versioning, and built-in testing. In short, AgentKit standardizes the entire life cycle of an AI agent—from visual design to deployment and performance tuning—inside a single unified system.show more

WeatherEdit: Controllable Weather Editing with 4D Gaussian Field Contributions:... 1. Based on our analysis of weather editing characteristics, we introduce WeatherEdit, a comprehensive and efficient framework for realistic and controllable weather generation. Compared with existing methods that focus on either background editing or static weather effects, a progressive 2D-to-4D transformation process in WeatherEdit enhances adaptability across a wider range of scenarios. 2. We introduce an all-in-one adapter to enable a diffusion model for multi-weather (snowy, rainy, and fog) synthesis, along with a Temporal-View attention to ensure consistent editing across multi-frame and multi-view. 3. We design a 4D Gaussian field for weather particle modeling, enabling plausible simulation of raindrops, snowflakes, and fog with controllable severity. 4. We demonstrate WeatherEdit’s effectiveness in generating realistic, consistent, and controllable weather effects in 3D driving scenes, showcasing its applicability to real-world scenarios.show more

This guy built a visual scanner that reads 468... points on his face and 42 points on his hands from a regular webcam and turns them into a cloud of thousands of particles right between his palms. Inside, MediaPipe and TouchDesigner are linked: the first captures hands and face from the webcam with high accuracy, the second turns those coordinates into a live plane and feeds it into a POP system that instantly generates a swarm of particles in the shape of a head. No studio, no render farmer, no VR headset. Just a laptop, a webcam, and 1 TouchDesigner session. And traditional VJ studios keep teams of 5 people on a setup with lighting, custom hardware, and commercial plugins, while his expenses are only a TouchDesigner subscription and a regular USB camera. One laptop runs MediaPipe and TouchDesigner simultaneously, holds the camera stream at 60 FPS without drops, and in parallel processes 468 face points + 21 points on each hand. The camera captures frame after frame, MediaPipe in real time sends TouchDesigner the finger coordinates and face geometry, and the POP operator inside the engine translates those numbers into thousands of particle points with colors from bright pink to gold. This setup immediately defines the role of the tool and the limits of its autonomy. It knows where the fingertips are at every moment of the frame. It knows how to read the face geometry at any angle to the camera. It knows how to draw a swarm of particles between them with the right color and contour. → MediaPipe pulls 468 points from the face and 21 points from each hand, 60 times per second → TouchDesigner receives those coordinates, builds a virtual rectangle between the fingertips, and feeds it into the POP system → POP generates thousands of particle points in the shape of a head, coloring them in a gradient from bright pink to gold → The HUD layer adds green corners and a blue neon frame, styling the image like an AR interface → All layers assemble into 1 real-time frame that projects back onto the video in the camera window → The final image is recorded to a file or broadcast to a projector for a live installation And only when the guy spreads his hands wider does the plane between the palms stretch; brings them together, it narrows. Otherwise the system runs on its own. And when he moves from his home room to a concert hall, the same laptop with the same webcam launches the same TouchDesigner session in just 5 minutes, without reconfiguration, without a new team, and without a single line of new code. In his work setup there is no studio of his own and no team for assembly. On the desk sits a laptop with a webcam, on top run MediaPipe and TouchDesigner with POP operators, and the same setup through a USB camera moves to any concert without a new configuration. Out of everything I have seen this year, this is the cleanest Creative Coding setup on 1 laptop: 0 render farms, 0 studio lighting, and between them 3 libraries, thousands of particle points, and 1 webcam.show more

A Letter to Our Community: The Road Ahead for... Robotics To our Community and Partners, As we step into 2026, our mission at Axis is clearer than ever: Constructing the definitive End-to-End Scaling Layer for Robotics. Our goal is to accelerate the transfer of diverse human intelligence into Robotics General Intelligence (RGI). By owning the critical path of intelligence creation, we are turning the physical limitations of robotics into a scalable, software-driven future. Here is our strategic outlook and roadmap for the year ahead. The Core Thesis: Simulation is the Only Way Out The path to RGI is currently blocked by Data Scarcity, Generalization Fragility, and Hardware Fragmentation. At Axis, we believe Simulation is the only way out. Our Simulation Data Platform and Data Augmentation Engine transform raw data into "Synthetic Gold". Backed by academic milestones like Roboverse, Skill Blending, and GraspVLA, we have proven that pure simulation can achieve the generalization required for the real world. We don’t just collect data; we architect it. The Engine: Why Crypto? We believe RGI should come from all, not a few. Crypto is not just a feature; it is the primitive that powers our entire ecosystem flywheel: - Incentive Mechanism: Democratizing contribution and rewarding the trainers and developers. - Assetization: Turning proprietary data and refined models into liquid, ownable assets. - Verifiable Workflow: We are opening the "Black Box" of AI. By bringing total transparency to the Task Generation → Data Collection → Model Training pipeline, we ensure every byte of intelligence is verifiable, traceable, and secure. 2026 Strategic Deliverables This year, we are committed to delivering three foundational pillars: - The World's Largest Training Dataset for Robots: A robot training set—diverse, high-quality interaction data at an unprecedented scale. - A Robotics Foundation Model: A universal robotic brain trained on our pure simulation and synthetic data, capable of robust cross-embodiment transfer and open-world adaptability. - Evolvable Robot Hardware: Robots deployed with Axis models that autonomously evolve through continuous interaction, turning every deployment into a self-improving node within our RGI network. The Ultimate Vision We are building more than models; we are architecting the Distributed Machine Economy. A future where every dataset, model, and robotic embodiment is a verifiable asset in a global, autonomous network. Thank you for building the future of intelligence with us✌️📷show more

Proud to announce my role as an official Ambassador... for Atlas Ora. Excited to contribute to a decentralized travel platform that is bringing the short-term rental economy fully on-chain. Atlas Ora is building an open network where hosts and guests connect directly without intermediaries taking a cut. Each booking runs through smart contracts, with payments handled transparently on-chain. No hidden fees, no delayed payouts only verified listings and secure transactions that both sides can trust. The model gives ownership back to the community. Hosts keep more of what they earn, guests pay a fair rate, and reputation is built through verifiable on-chain data rather than centralized reviews. Beyond short-term rentals, the platform opens possibilities for tokenized incentives, loyalty programs, and real economic participation in the travel ecosystem. Atlas represents a shift from platform-owned markets to user-owned networks where value flows directly between people. Proud to stand behind a project that turns travel into an open, transparent, and self-governing economy. $AORAshow more

A moment suspended between Saudi Arabia's football passion and... coffee tradition. GPT Image 2 + Seedance 2.0 on BudgetPixel AI prompt A highly cinematic, photorealistic single-shot sequence that preserves the exact original location, environment, architecture, objects, lighting conditions, camera perspective, and subject position from the source video. Do not replace, redesign, relocate, or alter the setting in any way. The person remains in the exact spot where they were filmed, maintaining their original pose, facial expression, body position, and interaction with the environment. The subject is wearing the official Saudi Arabia national football team uniform throughout the entire sequence: authentic green Saudi Arabia jersey with white details, official team crest, matching football shorts, athletic socks, and football boots. The uniform must appear naturally integrated into the original scene with realistic fabric folds, stitching, texture, shadows, reflections, and movement-free realism. Every background element, object, texture, structure, shadow, reflection, and environmental detail must remain identical to the original footage. The effect transforms the captured moment into a frozen-time cinematic sequence while keeping the real-world location completely unchanged. The subject is captured at the exact moment they pour a beverage from a transparent cup. Time has completely stopped. The liquid erupts from the cup in a dramatic suspended splash, forming elongated ribbons, twisting streams, intricate arcs, and hundreds of individual droplets frozen midair. Every droplet, splash fragment, and liquid strand appears perfectly suspended in space, creating the impression of a sculptural masterpiece made of liquid. The liquid spilling from the cup must be identical to the liquid inside the cup, with perfectly matching color, texture, thickness, reflections, transparency, and material properties. The beverage can be any type or color, but it must remain visually consistent throughout the scene with extreme realism. The subject remains absolutely motionless, frozen in the precise instant of action. Their posture, facial expression, fingertips, hair strands, jersey fabric folds, shorts texture, socks, football boots, accessories, and every micro-detail are perfectly preserved. Tiny condensation droplets on the cup, reflections on the surface, and subtle imperfections remain locked in place as if the entire world has been paused between two frames of time. The surrounding environment is equally frozen. Every object visible in the original footage remains completely static. Nothing moves. No wind, no shifting light, no falling droplets, no environmental motion. The entire world exists in a state of perfect suspension. The only moving element is the camera. The camera performs a slow, smooth cinematic arc movement around the subject, beginning from the original camera viewpoint and gradually orbiting to one side while maintaining focus on the frozen action. As the camera travels through three-dimensional space, it reveals changing perspectives of the suspended liquid sculpture, the Saudi Arabia football uniform, the subject, and the original environment. Strong spatial parallax is visible throughout the movement. Foreground droplets, liquid strands, the subject, nearby objects, and distant background elements shift relative to one another, creating a powerful sense of depth and dimensionality. The scene feels like moving through a perfectly preserved moment in time. Natural lighting remains consistent and unchanged throughout the shot. Shadows stay fixed, reflections remain stable, and materials such as glass, metal, stone, wood, fabric, football jersey fabric, embroidered team crest, and liquid exhibit highly detailed photorealistic textures. Captured with a premium wide-angle cinema lens, the scene emphasizes depth, scale, and immersive three-dimensional realism. The Saudi Arabia football uniform appears crisp, premium, and authentically detailed, with realistic fabric texture and professional sportswear quality. Core visual concept: The entire world is frozen in time exactly as it appeared in the original footage, like a hyper-detailed sculpture, while a subject wearing the Saudi Arabia national football team uniform pours a beverage that explodes into a suspended liquid masterpiece. The camera freely moves through the frozen moment, revealing dramatic parallax, depth, and cinematic realism from multiple angles. Style: Hyper-realistic, cinematic, ultra-detailed, 3D stop-motion illusion, frozen-time photography, volumetric depth, realistic lighting, film-quality rendering, smooth camera orbit, strong parallax, premium commercial sports production, museum-like suspended motion sculpture, exact environment preservation, original location consistency, photorealistic liquid simulation, luxury football advertisement aesthetic, FIFA World Cup promotional quality, 8K photorealism.show more

This guy built an AI pipeline that generates hyperrealistic... fashion models in 47 minutes and now dropshippers pay him $1,400 to clone the entire system. He got tired of watching e-com brands lose $8K per photoshoot when a single product angle changed so he built a 9-node workflow that generates 127 product videos from one Pinterest photo without hiring a single model. Here's the exact breakdown: → Claude writes a 34-parameter JSON brand DNA before any image is touched target psychographics, price anchor, vibe matrix, anti-inspiration blacklist → Pinterest becomes the model source library but you can't just download and animate → Kling 2.6 takes that static JPG and turns it into 5-second video but only after the prompt architecture is locked → Negative prompt node runs 41 exclusion terms: no plastic skin, no CGI glow, no symmetry artifacts, no doll face, no synthetic lighting → That one step kills the "AI look" that tanks engagement by 67% in the first 3 seconds → TikTok Studio uploads 19 videos in one batch with zero manual captioning because the brand voice was pre-programmed in step one → Atlas scrapes Amazon product links and auto-generates a Shopify store with hero images, pricing tiers, scarcity copy, and mobile-optimized checkout in 90 seconds → The store goes live before the first TikTok video finishes processing The key move 94% of people skip: you can't animate the photo before you inject the negative prompt. If you send a raw Pinterest image straight into image-to-video the face morphs into a wax figure. The fabric loses texture. The hands grow extra fingers. The whole thing screams "AI" and your CTR dies. His system runs the exclusion filter first so the model moves like she's shot on an iPhone 15 Pro in natural light. One brand hit 2.6M views on TikTok in 11 days with zero paid ads and converted at 3.7% because the videos looked like organic UGC not polished studio content. Brands now pay him $1,400 for the full pipeline setup + $340/month to keep the store synced with new product drops and seasonal video batches. The entire system runs on $23/month in API costs and one laptop. No photographer. No model agency. No product samples. Just a prompt template, a Pinterest account, and the discipline to filter out the AI artifacts before you render movement.show more