Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

Farlight Devlog Log 02: Action Design | Farlight 84 Welcome to the second episode of Farlight 84 Devlog series! In today's technical deep-dive, we'll explore our movement and animation systems, showcasing how the team achieved fluid character motion through advanced blending techniques, dynamic acceleration, and character-specific animations built on... show more

Farlight 84

35,916 subscribers

29,362 просмотров • 1 год назад •via X (Twitter)

Наука и технологии Игры Образование

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Farlight Devlog Log 03: Audio Design | Farlight 84 Welcome to the third episode of the Farlight 84 Devlog Series! Today, we’re diving into how Farlight 84’s upgraded audio system transforms your tactical experience—from realistic footsteps and gunfire to personalized hero voice lines and skill sounds. Hear the difference. Play smarter. #Farlight84 #FarlightDevlog

Farlight Devlog Log 03: Audio Design | Farlight 84 Welcome to the third episode of the Farlight 84 Devlog Series! Today, we’re diving into how Farlight 84’s upgraded audio system transforms your tactical experience—from realistic footsteps and gunfire to personalized hero voice lines and skill sounds. Hear the difference. Play smarter. #Farlight84 #FarlightDevlog

Farlight 84

14,656 просмотров • 1 год назад

Tung Tung Tung Sahur is here!! Day 14 of building GTA 6 with a loop of AI agents. Today's progress: - Reloads in. mag drops, new one goes in, old one on the ground. - Shot effects landed. - Full of Tung Tung Tung Sahur walking around the city now We have to actually learn Unreal. if we don't, our prompts stay vague and the agents give vague results. The second we need them to generate blueprints, animation blueprints, any of that, you have to know what to ask for. The more specific i get, the better the output. Tomorrow: aiming + all the full animations on the character.

Tung Tung Tung Sahur is here!! Day 14 of building GTA 6 with a loop of AI agents. Today's progress: - Reloads in. mag drops, new one goes in, old one on the ground. - Shot effects landed. - Full of Tung Tung Tung Sahur walking around the city now We have to actually learn Unreal. if we don't, our prompts stay vague and the agents give vague results. The second we need them to generate blueprints, animation blueprints, any of that, you have to know what to ask for. The more specific i get, the better the output. Tomorrow: aiming + all the full animations on the character.

Ziwen

53,240 просмотров • 1 месяц назад

✨We are excited to open-source Tencent HY-Motion 1.0, a billion-parameter text-to-motion model built on the Diffusion Transformer (DiT) architecture and flow matching. Tencent HY-Motion 1.0 empowers developers and individual creators alike by transforming natural language into high-fidelity, fluid, and diverse 3D character animations, delivering exceptional instruction-following capabilities across a broad range of categories. The generated 3D animation assets can be seamlessly integrated into typical 3D animation pipelines.🎮🎥 Highlights: 🔹Billion-Scale DiT: Successfully scaled flow-matching DiT to 1B+ parameters, setting a new ceiling for instruction-following capability and generated motion quality. 🔹Full-Stage Training Strategy: The industry’s first motion generation model featuring a complete Pre-training → SFT → RL loop to optimize physical plausibility and semantic accuracy. 🔹Comprehensive Category Coverage: Features 200+ motion categories across 6 major classes—the most comprehensive in the industry, curated via a meticulous data pipeline. 🌐Project Page: 🔗Github: 🤗Hugging Face: 📄Technical report:

✨We are excited to open-source Tencent HY-Motion 1.0, a billion-parameter text-to-motion model built on the Diffusion Transformer (DiT) architecture and flow matching. Tencent HY-Motion 1.0 empowers developers and individual creators alike by transforming natural language into high-fidelity, fluid, and diverse 3D character animations, delivering exceptional instruction-following capabilities across a broad range of categories. The generated 3D animation assets can be seamlessly integrated into typical 3D animation pipelines.🎮🎥 Highlights: 🔹Billion-Scale DiT: Successfully scaled flow-matching DiT to 1B+ parameters, setting a new ceiling for instruction-following capability and generated motion quality. 🔹Full-Stage Training Strategy: The industry’s first motion generation model featuring a complete Pre-training → SFT → RL loop to optimize physical plausibility and semantic accuracy. 🔹Comprehensive Category Coverage: Features 200+ motion categories across 6 major classes—the most comprehensive in the industry, curated via a meticulous data pipeline. 🌐Project Page: 🔗Github: 🤗Hugging Face: 📄Technical report:

Tencent Hy

328,874 просмотров • 7 месяцев назад

From July 2 to 6, 1337 & UM6P - University Mohammed VI Polytechnic took part in the #MoroccanGamingExpo, showcasing how code becomes creation through the talent, energy, and vision of our students. On our stand, we featured 5+ fully developed video game projects, built entirely by students — blending immersive design, technical excellence, and original storytelling. We don’t just train developers; we empower digital creators. Our students also reached the finals of the Mobile Game Idea Competition, proving their ability to pitch bold, impactful concepts in front of a national audience. During the event, @YassirBoux shared 1337’s philosophy in his talk: "Code, Create, Innovate: the 1337 Vision for the Video Game Industry", exploring how our model nurtures creativity, autonomy, and innovation through tech. From game demos to inspiring conversations — discover how 1337 students are shaping the future of gaming in Morocco. #1337School #UM6P #MoroccanGamingExpo #GameDev #TechForImpact #Innovation #DigitalCreativity #StudentProjects #MadeInMorocco

From July 2 to 6, 1337 & UM6P - University Mohammed VI Polytechnic took part in the #MoroccanGamingExpo, showcasing how code becomes creation through the talent, energy, and vision of our students. On our stand, we featured 5+ fully developed video game projects, built entirely by students — blending immersive design, technical excellence, and original storytelling. We don’t just train developers; we empower digital creators. Our students also reached the finals of the Mobile Game Idea Competition, proving their ability to pitch bold, impactful concepts in front of a national audience. During the event, @YassirBoux shared 1337’s philosophy in his talk: "Code, Create, Innovate: the 1337 Vision for the Video Game Industry", exploring how our model nurtures creativity, autonomy, and innovation through tech. From game demos to inspiring conversations — discover how 1337 students are shaping the future of gaming in Morocco. #1337School #UM6P #MoroccanGamingExpo #GameDev #TechForImpact #Innovation #DigitalCreativity #StudentProjects #MadeInMorocco

1337 School

30,828 просмотров • 1 год назад

🏃 Movement + Animation Update: Following feedback on the Official Trailer from December, we've been further tuning and polishing Stuffy's movement to make it more responsive and fluid. We hope this video is a promising glimpse of our much-requested progress in this area! What's New? - Stuffy is now ~10% smaller, granting more playable space and control (to accurately fit inside of a 'layered' segment, land tight jumps, etc.) - Stuffy's run speed was increased, and with better acceleration. - Stuffy now reacts to 'extreme' rising and falling velocities, so they'll flail around dramatically when popping out of a Blink Bubble, bouncing on a Trampoline, or falling from big jumps. - We've updated and added all-new animations and the method of blending them. This includes animations for idle jump and land, running jump and land, quick turn while running, and more. - We've increased Stuffy's max jump height, strength, and overall weight. - We've also increased the global gravity for less floaty physics. - A more visible drop shadow was added to help judge landing. Why these changes? From our own testing and public feedback, we realized the physics were not properly tuned after a big refactoring made in 2023... resulting in a floaty look. Sadly, the fixes weren't investigated in time for the trailer! Our goal was always to improve the animation blending and movement style. Thanks to your feedback, we were able to pinpoint the biggest problems and begin fixing them. 💖 Our work isn't done! You'll notice some bugs in the video. 🐞 We plan to continue polishing the movement with time, including new animations that help Stuffy react to the environment even better. However, this is a step in the right direction and it feels much nicer to use (and look at)! You'll also spot some of the Wardrobe in action!

🏃 Movement + Animation Update: Following feedback on the Official Trailer from December, we've been further tuning and polishing Stuffy's movement to make it more responsive and fluid. We hope this video is a promising glimpse of our much-requested progress in this area! What's New? - Stuffy is now ~10% smaller, granting more playable space and control (to accurately fit inside of a 'layered' segment, land tight jumps, etc.) - Stuffy's run speed was increased, and with better acceleration. - Stuffy now reacts to 'extreme' rising and falling velocities, so they'll flail around dramatically when popping out of a Blink Bubble, bouncing on a Trampoline, or falling from big jumps. - We've updated and added all-new animations and the method of blending them. This includes animations for idle jump and land, running jump and land, quick turn while running, and more. - We've increased Stuffy's max jump height, strength, and overall weight. - We've also increased the global gravity for less floaty physics. - A more visible drop shadow was added to help judge landing. Why these changes? From our own testing and public feedback, we realized the physics were not properly tuned after a big refactoring made in 2023... resulting in a floaty look. Sadly, the fixes weren't investigated in time for the trailer! Our goal was always to improve the animation blending and movement style. Thanks to your feedback, we were able to pinpoint the biggest problems and begin fixing them. 💖 Our work isn't done! You'll notice some bugs in the video. 🐞 We plan to continue polishing the movement with time, including new animations that help Stuffy react to the environment even better. However, this is a step in the right direction and it feels much nicer to use (and look at)! You'll also spot some of the Wardrobe in action!

Restitched 🧵🧸

17,118 просмотров • 1 год назад

Title: Origins of The Federal Reserve: Part III - Bankers, Reform, and Power (1900s to Today) Description: Welcome to Part III of our deep dive into the origins of the Federal Reserve! In this episode, we journey back to the dawn of the 20th century, where powerful bankers ignited a banking reform movement to centralize control and pave the way for the Federal Reserve. Discover how the Federal Reserve Act was stealthily passed amidst political intrigue, and explore its far-reaching impact on the U.S. economy and society since its inception in 1913. From secret meetings to modern-day consequences, this video uncovers the hidden history of America’s central bank. Missed Parts I and II? Check them out here: Don’t forget to like, subscribe, and hit the bell for more in this series! What are your thoughts on the Fed’s origins? Drop a comment below! #FederalReserve #BankingHistory #USEconomy #HistorySeries

Title: Origins of The Federal Reserve: Part III - Bankers, Reform, and Power (1900s to Today) Description: Welcome to Part III of our deep dive into the origins of the Federal Reserve! In this episode, we journey back to the dawn of the 20th century, where powerful bankers ignited a banking reform movement to centralize control and pave the way for the Federal Reserve. Discover how the Federal Reserve Act was stealthily passed amidst political intrigue, and explore its far-reaching impact on the U.S. economy and society since its inception in 1913. From secret meetings to modern-day consequences, this video uncovers the hidden history of America’s central bank. Missed Parts I and II? Check them out here: Don’t forget to like, subscribe, and hit the bell for more in this series! What are your thoughts on the Fed’s origins? Drop a comment below! #FederalReserve #BankingHistory #USEconomy #HistorySeries

Manifest History

17,258 просмотров • 1 год назад

Learn how to build an optimized LLM inference system from the ground up in our new short course, Efficiently Serving LLMs, built in collaboration with Predibase by Rubrik and taught by Travis Addair. Whether you're serving your own LLM or using a model hosting service, this course will give you a deep understanding of the optimizations required to efficiently serve many users at once. - Learn how LLMs generate text one token at a time, and how techniques like KV caching, continuous batching, and quantization speed things up and optimize memory usage for serving multiple users. - Benchmark the performance of these LLM optimizations to explore the trade-offs between quickly responding to an individual user’s request vs. serving many users at once. - Use techniques like low-rank adaptation (LoRA) to efficiently serve hundreds of unique, custom fine-tuned models on a single device, without sacrificing throughput. - Use Predibase's LoRAX framework to see optimization techniques in action on a real LLM server. Sign up here:

Learn how to build an optimized LLM inference system from the ground up in our new short course, Efficiently Serving LLMs, built in collaboration with Predibase by Rubrik and taught by Travis Addair. Whether you're serving your own LLM or using a model hosting service, this course will give you a deep understanding of the optimizations required to efficiently serve many users at once. - Learn how LLMs generate text one token at a time, and how techniques like KV caching, continuous batching, and quantization speed things up and optimize memory usage for serving multiple users. - Benchmark the performance of these LLM optimizations to explore the trade-offs between quickly responding to an individual user’s request vs. serving many users at once. - Use techniques like low-rank adaptation (LoRA) to efficiently serve hundreds of unique, custom fine-tuned models on a single device, without sacrificing throughput. - Use Predibase's LoRAX framework to see optimization techniques in action on a real LLM server. Sign up here:

Andrew Ng

104,727 просмотров • 2 лет назад

MUDANG: Two Hearts | Details Official Trailer ▶️ ▪️Coming to PS5, Xbox and PC in 2026 ▪️Narrative-driven, third-person action adventure that blends "cinematic storytelling with immersive stealth and dynamic combat" ▪️Takes place on a 'volatile' Korean peninsula ▪️Players take the role of two characters, a K-Pop idol named GAVI who is living under constant surveillance, and Ji Jeongtae, an elite North Korean special forces operative fighting through enemy lines "in pursuit of the truth" ▪️Their paths eventually merge into a single, unsettling truth ▪️Built through "state of the art" performance capture pipeline, integrates fluid motion-matched animations, open ended level design, dynamic spatial audio ▪️Combat flexibility lets players choose stealth, CQC (close quarters combat) or all-our gunplay at any moment ▪️"Unmatched level of realism" as many tactics the player will use are "inspired by strategies used in real Korean Special Forces missions, motion captured movements, etc ▪️Open-ended level design for experimentation, multiple routes and vantage points where you can hide in the shadows, hang from pipes, slip through vents, climb buildings, or destroy parts of the environment to set up ambushes ▪️Environmental takedowns, wide range of CQC moves (lethal and nonlethal), gadgets like goggles, EMPs, grenades, lures, and mines, and a "deep arsenal" of firearms ▪️Enemy AI is built "from the ground up" with player versatility in mind and "dynamically" adapts to your actions in real time like listening for footsteps, investigating disturbances, flanking and outmanuevering, etc ▪️Enemies have access to the same gadgets, weapons and CQC techniques as you; heavy infantry push forward with body armor and heavy firepower, saboteurs lurk in the shadows waiting to catch you off guard, and grenadiers bombard your position to force you into the open ▪️There are "formidable" bosses with distinct powers and abilities ▪️Cutscenes carefully crafted for "profound immersion", no cuts, no loading screens, seamless flow between story and gameplay #MudangTwoHearts #XboxShowcase

MUDANG: Two Hearts | Details Official Trailer ▶️ ▪️Coming to PS5, Xbox and PC in 2026 ▪️Narrative-driven, third-person action adventure that blends "cinematic storytelling with immersive stealth and dynamic combat" ▪️Takes place on a 'volatile' Korean peninsula ▪️Players take the role of two characters, a K-Pop idol named GAVI who is living under constant surveillance, and Ji Jeongtae, an elite North Korean special forces operative fighting through enemy lines "in pursuit of the truth" ▪️Their paths eventually merge into a single, unsettling truth ▪️Built through "state of the art" performance capture pipeline, integrates fluid motion-matched animations, open ended level design, dynamic spatial audio ▪️Combat flexibility lets players choose stealth, CQC (close quarters combat) or all-our gunplay at any moment ▪️"Unmatched level of realism" as many tactics the player will use are "inspired by strategies used in real Korean Special Forces missions, motion captured movements, etc ▪️Open-ended level design for experimentation, multiple routes and vantage points where you can hide in the shadows, hang from pipes, slip through vents, climb buildings, or destroy parts of the environment to set up ambushes ▪️Environmental takedowns, wide range of CQC moves (lethal and nonlethal), gadgets like goggles, EMPs, grenades, lures, and mines, and a "deep arsenal" of firearms ▪️Enemy AI is built "from the ground up" with player versatility in mind and "dynamically" adapts to your actions in real time like listening for footsteps, investigating disturbances, flanking and outmanuevering, etc ▪️Enemies have access to the same gadgets, weapons and CQC techniques as you; heavy infantry push forward with body armor and heavy firepower, saboteurs lurk in the shadows waiting to catch you off guard, and grenadiers bombard your position to force you into the open ▪️There are "formidable" bosses with distinct powers and abilities ▪️Cutscenes carefully crafted for "profound immersion", no cuts, no loading screens, seamless flow between story and gameplay #MudangTwoHearts #XboxShowcase

Shinobi602

238,505 просмотров • 1 год назад

.Duolingo's streaks feature is one of the best designed, most clever, and also most impactful growth features ever created. It's the single biggest driver of Duolingo's growth to a $14 billion business, and is endlessly copied by other startups. This one feature has created billions of dollars in value, and continues to pay dividends. In a new series, I go behind the product to understand how the most important products and product features came to be—the origin story, how it evolved, how the team and processes are set up, the biggest lessons and wrong turns along the way, and more. In today's episode, I sit down with, Jackson Shuttleworth, Group PM at Duolingo, who leads the retention team and the powerful streak feature. In our conversation, we dive deep into: 🔸 The evolution of the streak feature 🔸 Biggest wins and misses from 600+ experiments 🔸 Keys to building a streaks mechanic in your product 🔸 Tips for building engaging notification systems 🔸 How to build a high-velocity product team 🔸 Much more Listen now 👇 • YouTube: • Spotify: • Apple: Thank you to our wonderful sponsors for supporting the podcast: 🏆 pendo.io — The only all-in-one product experience platform for any type of application: 🏆 Vanta — Automate compliance. Simplify security: 🏆Coda — The all-in-one collaborative workspace:

.Duolingo's streaks feature is one of the best designed, most clever, and also most impactful growth features ever created. It's the single biggest driver of Duolingo's growth to a $14 billion business, and is endlessly copied by other startups. This one feature has created billions of dollars in value, and continues to pay dividends. In a new series, I go behind the product to understand how the most important products and product features came to be—the origin story, how it evolved, how the team and processes are set up, the biggest lessons and wrong turns along the way, and more. In today's episode, I sit down with, Jackson Shuttleworth, Group PM at Duolingo, who leads the retention team and the powerful streak feature. In our conversation, we dive deep into: 🔸 The evolution of the streak feature 🔸 Biggest wins and misses from 600+ experiments 🔸 Keys to building a streaks mechanic in your product 🔸 Tips for building engaging notification systems 🔸 How to build a high-velocity product team 🔸 Much more Listen now 👇 • YouTube: • Spotify: • Apple: Thank you to our wonderful sponsors for supporting the podcast: 🏆 pendo.io — The only all-in-one product experience platform for any type of application: 🏆 Vanta — Automate compliance. Simplify security: 🏆Coda — The all-in-one collaborative workspace:

Lenny Rachitsky

60,345 просмотров • 1 год назад

🌐 New website is now live! First up is the light mode, with dark mode coming soon. We're thrilled about what's next— ready to scream for these upcoming updates? 🌀 Brand New Roadmap (some product timelines may be adjusted based on development progress) 🌀 Kingnet AI V2 Official Release – A completely revamped dApp experience! Next week, we’ll officially open access to the Animation Generator and Agent, making interactions smarter and simpler than the first-gen version 🌀 Public Docs & GitHub Code Open-Source 🌀 Official Deployment on Solana & BNB Chain – Users will be able to pay on-chain to generate custom assets and export them (FBX format for direct download and use). TON integration will follow. 🌀$KNET’s First Utility Feature As always, we’ve included a surprise at the end of our video, showcasing the full workflow of AI text-to-3D model to in-game motion model: 1️⃣ Enter the Agent virtual assistant, use text prompts to generate a 3D character motion model. 2️⃣ The Agent generates a 3D base model, automatically bakes and saves textures. 3️⃣ Auto-rigging, joint adjustments, and natural motion generation. 4️⃣ Users can pay to download the FBX file with animations. 5️⃣ The file can be directly imported into Unity or Unreal Engine, with options to import animations, set animation cuts & loops—ready for in-game use! Continuous Delivery.

Kingnet AI

31,023 просмотров • 1 год назад

Introducing the 10Ka Team 🤝 We've curated a team of exceptionally skilled individuals, each a trailblazer in their respective fields. Together, we possess all the necessary ingredients to realize our vision of becoming the premier project for digital fashion. Let's dive in 👇🏼 Diana Cañas: Breaking Barriers: Diana Cañas Leads the Way in NFT and Digital Fashion Empowerment. As the founder and CEO of 10ka NFT, Diana has taken the industry by storm, brilliantly combining her love for fashion with cutting-edge technologies like NFTs and NFCs. This unique fusion enables her to push the boundaries of the digital fashion realm. Ronin Studio: Ronin is a versatile creative studio specializing in corporate identity and character creation, along with UI/UX design. “Driven by a dedication to emerging trends and artistic/technological innovation, we draw inspiration from both the past and the future of design. Our approach is inherently disruptive, always encouraging us to think beyond conventional boundaries.” Tripton: We are a dynamic creative studio with expertise in 3D production, Visual Shows, and Virtual and Augmented Reality. “Fueled by a passion for pioneering technologies and groundbreaking ideas, we draw inspiration from eminent artists across advertising design, 3D animation, and the broader audiovisual realm.” Virtuozo: Virtuozo is a studio renowned for crafting immersive 3D worlds and captivating virtual experiences. At the helm is our lead 3D generalist, a virtuoso in every sense of the word. With mastery over the craft, he meticulously crafts realistic and aesthetically pleasing 3D models, textures, and animations using state-of-the-art technology. Cristian Torrijos: Blockchain Developer (Solidity, Smart Contracts, Web3) and expert in PHP, MySQL, and ReactJS. “Specializing in the development of Web3 and Web2 projects, we ensure the quality and longevity of our creations, delivering projects that are not only innovative but also enduring.” Domi Vakero: Digital Artist from the South of Spain proficient in 2D, 3D, and AI. With extensive expertise in the illustration and modeling of both 2D and 3D characters, we bring visions to life with creativity and precision. This is just some of the extensive team behind 10KA. We are dedicated to building & becoming one of the leading projects on Ethereum 🫡

Introducing the 10Ka Team 🤝 We've curated a team of exceptionally skilled individuals, each a trailblazer in their respective fields. Together, we possess all the necessary ingredients to realize our vision of becoming the premier project for digital fashion. Let's dive in 👇🏼 Diana Cañas: Breaking Barriers: Diana Cañas Leads the Way in NFT and Digital Fashion Empowerment. As the founder and CEO of 10ka NFT, Diana has taken the industry by storm, brilliantly combining her love for fashion with cutting-edge technologies like NFTs and NFCs. This unique fusion enables her to push the boundaries of the digital fashion realm. Ronin Studio: Ronin is a versatile creative studio specializing in corporate identity and character creation, along with UI/UX design. “Driven by a dedication to emerging trends and artistic/technological innovation, we draw inspiration from both the past and the future of design. Our approach is inherently disruptive, always encouraging us to think beyond conventional boundaries.” Tripton: We are a dynamic creative studio with expertise in 3D production, Visual Shows, and Virtual and Augmented Reality. “Fueled by a passion for pioneering technologies and groundbreaking ideas, we draw inspiration from eminent artists across advertising design, 3D animation, and the broader audiovisual realm.” Virtuozo: Virtuozo is a studio renowned for crafting immersive 3D worlds and captivating virtual experiences. At the helm is our lead 3D generalist, a virtuoso in every sense of the word. With mastery over the craft, he meticulously crafts realistic and aesthetically pleasing 3D models, textures, and animations using state-of-the-art technology. Cristian Torrijos: Blockchain Developer (Solidity, Smart Contracts, Web3) and expert in PHP, MySQL, and ReactJS. “Specializing in the development of Web3 and Web2 projects, we ensure the quality and longevity of our creations, delivering projects that are not only innovative but also enduring.” Domi Vakero: Digital Artist from the South of Spain proficient in 2D, 3D, and AI. With extensive expertise in the illustration and modeling of both 2D and 3D characters, we bring visions to life with creativity and precision. This is just some of the extensive team behind 10KA. We are dedicated to building & becoming one of the leading projects on Ethereum 🫡

10KA👟

39,304 просмотров • 2 лет назад

🚨 We’re officially launching : ANIMA STUDIO 🚨 ⭐️ To celebrate, we’re kicking off a 30-DAY CHALLENGE ⭐️ Every day, you’ll find a new case study across our platforms – showcasing our creative vision and technical expertise. Expect: - Brand ads (real or fictional collabs) 👟 - Short films 🎥 - Product reels 📱 - Character design 🦖 - Set design ⛰️ - Art direction 🎨 ..and more. All powered by AI tools + design expertise. We've been producing visuals (images & videos) for brands, entrepreneurs & companies for over 6 months — and have been doing it manually for over 3 years. But Anima Studio is a much bigger vision. We’re blending our roots in design with cutting-edge AI to build something new. In fact, months before this announcement, we started working with a major US production (multi-million budget). 🇺🇸 We can’t say more for now — but it’s moving fast. Our studio covers a full creative scope: - Art Direction 🎨 - Visual / Communication Design & Branding 👁️ - Ad Creation & Deep Brand Identity 🛜 And for Film & Entertainment 🎬 : - Pre-production (worldbuilding, chara & set design) ⭐️ - Production/Post-prod (AI animation, VFX…) 📺 - Transmedia (comics, merch, narrative extensions…) 🪐 - Short Film 🍿 And a lot of innovative ideas to come. We’re still continuing our content creation & training activities on AI & design. Today, we’re just sharing a fun little teaser to launch the challenge — but a proper trailer is coming soon. 💛 Thank you all for the support. 🙏 This wouldn’t be possible without your encouragement. See you tomorrow for the first fictional ad of the challenge! Let’s go. 🚀

Anima

74,212 просмотров • 1 год назад

Thrilled to announce Kingnet AI V2 is now officially live ! We have officially deployed on the BNB Chain first ! Whether you're an enthusiast or a professional game developer, come and try it out now： Each generated asset costs approximately $3 and supports export in professional game-editing formats. We will soon support exporting assets in NFT on-chain formats, empowering Web3 users and partners with seamless integration. Jump down more rabbit holes next.👇 📔 Product Introduction： By conversing naturally with agent Joi, users can achieve a complete automated game development cycle - from requirement proposal to finished product delivery. Users simply need to describe their game concepts and design requirements in natural language, and Joi will automatically utilize built-in generator including: • Animation Generator： AI-driven motion generation with auto-rigging technology for instant character animation • Map Generator： Procedural map generation with built-in logic validation for consistent world-building • Numerical Generator： Automated game economy tuning for fair yet challenging gameplay systems • Editable Code Generator： Generates clean, maintainable game logic code with multi-platform/multi-language support • Interface Generator： Intelligent layout engine that optimizes user experience and interaction flow Joi intelligently generates all necessary game components, performs multi-dimensional feasibility checks, and ultimately completes game synthesis, packaging and deployment. Users can directly click to try the game on the chat interface, or download the complete editable code package to achieve rapid iteration and secondary development. 🎯 Core Architecture： 1/ Natural Language Understanding & Multimodal Intent Parsing: Utilizing advanced deep learning NLP models (e.g., Transformer-based language understanding models), Joi precisely interprets user natural language inputs and extracts core game design intents and parameters. Through semantic segmentation and entity recognition, complex requirements are decomposed into specific tasks for animation, map, numerical systems, UI, and code modules. 2/ Modular Editor System & API Integration: Joi employs a unified API framework to enable seamless collaboration between editor modules, ensuring high compatibility in data formats and workflows. 3/ Intelligent Validation & Quality Assurance: The system incorporates multi-dimensional verification mechanisms including animation continuity checks, map pathfinding and physical logic validation, game balance analysis, UI interaction consistency verification, and static/dynamic code security testing. Automated testing and feedback loops ensure outputs meet high-standard game design specifications. 4/ Automatic Synthesis, Packaging & Instant Deployment: Verified resources are automatically integrated to complete game compilation, packaging and deployment. Supports one-click generation of playable online links and downloadable complete code packages for immediate testing or deep customization/iterative development. 5/ Interactive Chat Interface & Seamless UX: The entire workflow is completed within the chat interface, significantly reducing traditional game development's communication and operational barriers. Users accomplish complex game design and development through conversation while receiving real-time feedback and adjustment suggestions, democratizing game creation. 6/ Industry-Disrupting Value: Transforms traditional manual development into AI-driven automated pipelines.

Thrilled to announce Kingnet AI V2 is now officially live ! We have officially deployed on the BNB Chain first ! Whether you're an enthusiast or a professional game developer, come and try it out now： Each generated asset costs approximately $3 and supports export in professional game-editing formats. We will soon support exporting assets in NFT on-chain formats, empowering Web3 users and partners with seamless integration. Jump down more rabbit holes next.👇 📔 Product Introduction： By conversing naturally with agent Joi, users can achieve a complete automated game development cycle - from requirement proposal to finished product delivery. Users simply need to describe their game concepts and design requirements in natural language, and Joi will automatically utilize built-in generator including: • Animation Generator： AI-driven motion generation with auto-rigging technology for instant character animation • Map Generator： Procedural map generation with built-in logic validation for consistent world-building • Numerical Generator： Automated game economy tuning for fair yet challenging gameplay systems • Editable Code Generator： Generates clean, maintainable game logic code with multi-platform/multi-language support • Interface Generator： Intelligent layout engine that optimizes user experience and interaction flow Joi intelligently generates all necessary game components, performs multi-dimensional feasibility checks, and ultimately completes game synthesis, packaging and deployment. Users can directly click to try the game on the chat interface, or download the complete editable code package to achieve rapid iteration and secondary development. 🎯 Core Architecture： 1/ Natural Language Understanding & Multimodal Intent Parsing: Utilizing advanced deep learning NLP models (e.g., Transformer-based language understanding models), Joi precisely interprets user natural language inputs and extracts core game design intents and parameters. Through semantic segmentation and entity recognition, complex requirements are decomposed into specific tasks for animation, map, numerical systems, UI, and code modules. 2/ Modular Editor System & API Integration: Joi employs a unified API framework to enable seamless collaboration between editor modules, ensuring high compatibility in data formats and workflows. 3/ Intelligent Validation & Quality Assurance: The system incorporates multi-dimensional verification mechanisms including animation continuity checks, map pathfinding and physical logic validation, game balance analysis, UI interaction consistency verification, and static/dynamic code security testing. Automated testing and feedback loops ensure outputs meet high-standard game design specifications. 4/ Automatic Synthesis, Packaging & Instant Deployment: Verified resources are automatically integrated to complete game compilation, packaging and deployment. Supports one-click generation of playable online links and downloadable complete code packages for immediate testing or deep customization/iterative development. 5/ Interactive Chat Interface & Seamless UX: The entire workflow is completed within the chat interface, significantly reducing traditional game development's communication and operational barriers. Users accomplish complex game design and development through conversation while receiving real-time feedback and adjustment suggestions, democratizing game creation. 6/ Industry-Disrupting Value: Transforms traditional manual development into AI-driven automated pipelines.

Kingnet AI

45,966 просмотров • 1 год назад

Max Fleischer's trippy version of "Snow White" from 1933 remains a fascinating and bizarre piece of animation history. In this short Betty Boop cartoon, Fleischer and his team condensed and twisted the classic Snow White tale, taking viewers on a surreal journey that defies expectations. One of the standout moments in the cartoon is the inclusion of Cab Calloway, a renowned jazz singer of the time. In the middle of the animated film, Calloway appears and performs the hauntingly beautiful "St. James Infirmary Blues." The scene is a rare live-action segment, originally from another cartoon of the era titled "Minnie the Moocher," which was another iconic song associated with Calloway. Interestingly, the footage and music used in the beginning of "Minnie the Moocher" are clearly the same recording as the song "St. James Infirmary Blues" featured in the Betty Boop cartoon. In a clever editing move, the two pieces of audio are seamlessly joined together, creating a seamless transition between the two cartoons. Calloway's appearance in the cartoon is truly mesmerizing. He begins by singing the tune as Koko the Clown, a character created by Fleischer, and then undergoes a transformation into a ghostly figure. The animation beautifully captures Calloway's distinctive enunciation and signature dance moves, accompanied by a barrage of wild and imaginative visuals. In addition to the captivating animation, the cartoon also incorporates scenes from the 1980 film "The Blues Brothers," in which Cab Calloway once again performs "Minnie the Moocher." This inclusion adds an extra layer of intertextuality, as viewers are introduced to Calloway through this iconic performance. "Betty Boop in Snow White" is a testament to Max Fleischer's creativity and willingness to push the boundaries of animation. The cartoon showcases his unique vision and knack for blending different artistic mediums, resulting in a truly trippy and memorable viewing experience. Directed by Dave Fleischer and animated by Roland C. Crandall, the cartoon exemplifies the Fleischer Studio's distinctive style, characterized by fluid animation, vibrant colors, and a surreal atmosphere. Their innovative techniques and bold storytelling continue to inspire animators and artists to this day. Despite being a departure from the traditional Snow White narrative, Max Fleischer's version remains a remarkable piece of animation history. It stands as a testament to the power of imagination and creativity in bringing beloved stories to life in new and unexpected ways.

Max Fleischer's trippy version of "Snow White" from 1933 remains a fascinating and bizarre piece of animation history. In this short Betty Boop cartoon, Fleischer and his team condensed and twisted the classic Snow White tale, taking viewers on a surreal journey that defies expectations. One of the standout moments in the cartoon is the inclusion of Cab Calloway, a renowned jazz singer of the time. In the middle of the animated film, Calloway appears and performs the hauntingly beautiful "St. James Infirmary Blues." The scene is a rare live-action segment, originally from another cartoon of the era titled "Minnie the Moocher," which was another iconic song associated with Calloway. Interestingly, the footage and music used in the beginning of "Minnie the Moocher" are clearly the same recording as the song "St. James Infirmary Blues" featured in the Betty Boop cartoon. In a clever editing move, the two pieces of audio are seamlessly joined together, creating a seamless transition between the two cartoons. Calloway's appearance in the cartoon is truly mesmerizing. He begins by singing the tune as Koko the Clown, a character created by Fleischer, and then undergoes a transformation into a ghostly figure. The animation beautifully captures Calloway's distinctive enunciation and signature dance moves, accompanied by a barrage of wild and imaginative visuals. In addition to the captivating animation, the cartoon also incorporates scenes from the 1980 film "The Blues Brothers," in which Cab Calloway once again performs "Minnie the Moocher." This inclusion adds an extra layer of intertextuality, as viewers are introduced to Calloway through this iconic performance. "Betty Boop in Snow White" is a testament to Max Fleischer's creativity and willingness to push the boundaries of animation. The cartoon showcases his unique vision and knack for blending different artistic mediums, resulting in a truly trippy and memorable viewing experience. Directed by Dave Fleischer and animated by Roland C. Crandall, the cartoon exemplifies the Fleischer Studio's distinctive style, characterized by fluid animation, vibrant colors, and a surreal atmosphere. Their innovative techniques and bold storytelling continue to inspire animators and artists to this day. Despite being a departure from the traditional Snow White narrative, Max Fleischer's version remains a remarkable piece of animation history. It stands as a testament to the power of imagination and creativity in bringing beloved stories to life in new and unexpected ways.

Historic Vids

21,299,277 просмотров • 3 лет назад

Two big steps towards our vision for @NotebookLM as the ultimate research platform: • Integrating Deep Research, with a set of only-at-Notebook features that let you explore the retrieved sources • Launching a series of Featured Notebooks curated by Google Research These developments are designed to enhance the full life cycle of research and scholarship: using the power of AI to assemble the knowledge base you need to advance your understanding, and then making your work accessible and intelligible to a wider audience using all the explanatory tools that Notebook offers. If you've used DeepResearch in the Gemini app, you already know that it's a pioneering advance in assembling complex, grounded information on any topic imaginable—collecting an entire trove of material for you and writing a nuanced research report that summarizes the findings. But because NotebookLM is designed to manage and explore potentially hundreds of sources, the Deep Research report is only the beginning of your journey. In our integration, Deep Research gives you an overview all of the sources it found during its research phase, with annotated commentary explaining how each source related to your original query. You can then choose to import some or all of the sources to the notebook, along with the report itself, which you can then explore or transform using the full suite of tools that Notebook offers: grounded chat with citations, Mind Maps, Audio/Video overviews, and much more. And it's that suite of tools that make the Google Research Featured Notebooks so compelling as well. Each notebook contains a curated collection of articles on a specific topic, published by the Google Research team. Think of them as a kind of knowledge base of Google's best thinking on a series of compelling research questions: How do scientists link genetics to health? How will quantum computing be useful? If you're a specialist in these fields, you can read the original papers or ask nuanced questions in chat and advance your understanding of the latest developments. But these notebooks can also make the complex but important topics understandable to non-specialists or students. Each notebook comes with pre-generated audio and video overviews, flashcards, and other Studio artifacts designed to make the scientific and technological concepts accessible and interesting. And you can always explore the material with our new "Learning Guide" chat mode that effectively gives you a personal tutor to enhance your understanding. There's much more to come on this front, but you can see in these two announcements how we see Notebook as both a workbench for conducting research and a publishing platform for sharing the results of that research once you're ready to make it public. Deep Research is rolling out this week to all users. The first two Google Research notebooks are live now, both of them deep dives into our most recent discoveries involving genetics and health. (Links in the following tweets.) We'll be publishing new notebooks in the series every other week or so for the next few months.

Two big steps towards our vision for @NotebookLM as the ultimate research platform: • Integrating Deep Research, with a set of only-at-Notebook features that let you explore the retrieved sources • Launching a series of Featured Notebooks curated by Google Research These developments are designed to enhance the full life cycle of research and scholarship: using the power of AI to assemble the knowledge base you need to advance your understanding, and then making your work accessible and intelligible to a wider audience using all the explanatory tools that Notebook offers. If you've used DeepResearch in the Gemini app, you already know that it's a pioneering advance in assembling complex, grounded information on any topic imaginable—collecting an entire trove of material for you and writing a nuanced research report that summarizes the findings. But because NotebookLM is designed to manage and explore potentially hundreds of sources, the Deep Research report is only the beginning of your journey. In our integration, Deep Research gives you an overview all of the sources it found during its research phase, with annotated commentary explaining how each source related to your original query. You can then choose to import some or all of the sources to the notebook, along with the report itself, which you can then explore or transform using the full suite of tools that Notebook offers: grounded chat with citations, Mind Maps, Audio/Video overviews, and much more. And it's that suite of tools that make the Google Research Featured Notebooks so compelling as well. Each notebook contains a curated collection of articles on a specific topic, published by the Google Research team. Think of them as a kind of knowledge base of Google's best thinking on a series of compelling research questions: How do scientists link genetics to health? How will quantum computing be useful? If you're a specialist in these fields, you can read the original papers or ask nuanced questions in chat and advance your understanding of the latest developments. But these notebooks can also make the complex but important topics understandable to non-specialists or students. Each notebook comes with pre-generated audio and video overviews, flashcards, and other Studio artifacts designed to make the scientific and technological concepts accessible and interesting. And you can always explore the material with our new "Learning Guide" chat mode that effectively gives you a personal tutor to enhance your understanding. There's much more to come on this front, but you can see in these two announcements how we see Notebook as both a workbench for conducting research and a publishing platform for sharing the results of that research once you're ready to make it public. Deep Research is rolling out this week to all users. The first two Google Research notebooks are live now, both of them deep dives into our most recent discoveries involving genetics and health. (Links in the following tweets.) We'll be publishing new notebooks in the series every other week or so for the next few months.

Steven Johnson

104,833 просмотров • 9 месяцев назад

⚡️🇷🇺🏭 Rostec's unique machine creates an aircraft engine part right at the Metalloobrabotka exhibition. The video shows one of the most technologically advanced domestic machines: the 2000VH five-axis milling machining center. It was created for the needs of the aircraft, engine and defense industries. During the Metalloobrabotka-2025 exhibition, the machine processes one of the most important elements of an aircraft engine - an impeller (blade machine). Such parts are used in aircraft engines. The diameter of this aluminum product is 70 cm, the height is about 30 cm, the weight is about 15 kg. The machine copes with the work perfectly - pay attention to the screen! The equipment was created by our holding company "STAN" . The machine is designed for large-sized parts of complex shape. It is capable of working with products up to 2 m in diameter and weighing up to 5 tons. At the same time, the accuracy achieved is up to hundredths of a millimeter. The model is built on a high-rigidity structure, its internal cavities are filled with synthetic granite. As a result, the vibration resistance of the equipment frame is comparable to heavy cast iron. The machine is equipped with a Russian numerical control system and a liquid cooling system. The use of direct drives allows achieving high dynamic stability and eliminating backlash in movement. Among the built-in functions are systems for measuring tools and parts, monitoring processes and industrial safety. 2000VH has no analogues in technical characteristics among domestic equipment and will replace imported models at Russian enterprises. rostecru

⚡️🇷🇺🏭 Rostec's unique machine creates an aircraft engine part right at the Metalloobrabotka exhibition. The video shows one of the most technologically advanced domestic machines: the 2000VH five-axis milling machining center. It was created for the needs of the aircraft, engine and defense industries. During the Metalloobrabotka-2025 exhibition, the machine processes one of the most important elements of an aircraft engine - an impeller (blade machine). Such parts are used in aircraft engines. The diameter of this aluminum product is 70 cm, the height is about 30 cm, the weight is about 15 kg. The machine copes with the work perfectly - pay attention to the screen! The equipment was created by our holding company "STAN" . The machine is designed for large-sized parts of complex shape. It is capable of working with products up to 2 m in diameter and weighing up to 5 tons. At the same time, the accuracy achieved is up to hundredths of a millimeter. The model is built on a high-rigidity structure, its internal cavities are filled with synthetic granite. As a result, the vibration resistance of the equipment frame is comparable to heavy cast iron. The machine is equipped with a Russian numerical control system and a liquid cooling system. The use of direct drives allows achieving high dynamic stability and eliminating backlash in movement. Among the built-in functions are systems for measuring tools and parts, monitoring processes and industrial safety. 2000VH has no analogues in technical characteristics among domestic equipment and will replace imported models at Russian enterprises. rostecru

SIMPLICIUS Ѱ

40,122 просмотров • 1 год назад

I’ve finally applied #ViduQ3 to a narrative project for SquadBlast . It handles action sequences and explosions with a level of consistency I hadn’t seen before. I achieved camera movements I’ve had in mind for a long time that other models simply wouldn't allow me to implement. The Start-end frame option generates high-quality animations with great control, provided you choose the points wisely and give the model enough time to generate the full movement fluidly. Grok surprised me with its iteration speed. I use it to bring dynamism to establishing shots and dialogue scenes that require quick corrections. If the scene needs movement, it’s my first choice. For more paced scenes or dialogues in wide shots, I prefer Sora 2. It is better suited for maintaining character style in distant shots, where Grok tends to struggle. The music was created in Suno (Industrial Tech-Step). I was looking for a sense of movement through minor-key synth arpeggios and extreme reverb. The "Studio" feature allowed me to precisely control the intro length and the exact point where the kick hits. Finally, a huge thanks to Framer 🇱🇹 for the amazing work on Cartoon Hero and for helping me connect with the professional world, and to OscarAI for his SREFs. I didn't have much time to develop the art style from scratch, so I used one of the SREF he shares. It fit perfectly with the bluish palette and the Otomo-inspired retro sci-fi style I was aiming for. It easily saved me a full day of work. IF ANYONE HAS ANY TECHNICAL KNOW-HOW QUESTIONS RELATED TO ANY SEQUENCE FEEL FREE TO ASK IN THE COMMENTS.

I’ve finally applied #ViduQ3 to a narrative project for SquadBlast . It handles action sequences and explosions with a level of consistency I hadn’t seen before. I achieved camera movements I’ve had in mind for a long time that other models simply wouldn't allow me to implement. The Start-end frame option generates high-quality animations with great control, provided you choose the points wisely and give the model enough time to generate the full movement fluidly. Grok surprised me with its iteration speed. I use it to bring dynamism to establishing shots and dialogue scenes that require quick corrections. If the scene needs movement, it’s my first choice. For more paced scenes or dialogues in wide shots, I prefer Sora 2. It is better suited for maintaining character style in distant shots, where Grok tends to struggle. The music was created in Suno (Industrial Tech-Step). I was looking for a sense of movement through minor-key synth arpeggios and extreme reverb. The "Studio" feature allowed me to precisely control the intro length and the exact point where the kick hits. Finally, a huge thanks to Framer 🇱🇹 for the amazing work on Cartoon Hero and for helping me connect with the professional world, and to OscarAI for his SREFs. I didn't have much time to develop the art style from scratch, so I used one of the SREF he shares. It fit perfectly with the bluish palette and the Otomo-inspired retro sci-fi style I was aiming for. It easily saved me a full day of work. IF ANYONE HAS ANY TECHNICAL KNOW-HOW QUESTIONS RELATED TO ANY SEQUENCE FEEL FREE TO ASK IN THE COMMENTS.

VoxelPlot

17,771 просмотров • 6 месяцев назад

One shot. One dream. One unforgettable finish. ⚽🔥 Made this cinematic World Cup final using Agent Team inside RoboNeo with visuals powered by Seedance 2.0. Video Prompt 👇 A cinematic 30 second World Cup inspired short film set in a futuristic mega stadium at night. The atmosphere is electric with packed crowds waving flags, flashing lights, giant holographic scoreboards, smoke effects, and cinematic rain reflections on the pitch. Opening scene starts with a young underdog football captain walking through the stadium tunnel in slow motion while hearing the deafening roar of fans. Close up shots of boots touching the wet ground, tense faces, jerseys moving in the wind, and dramatic eye contact between rival teams. Ultra realistic cinematic camera movement, emotional tension, dynamic lighting, realistic crowd reactions, premium sports commercial quality. As the beat intensifies, transition into fast paced World Cup action. Explosive dribbling sequences, impossible skill moves, aggressive tackles, synchronized team movement, dramatic goalkeeper saves, and cinematic slow motion shots of the ball flying across the field. Final hero shot begins at the climax of the match. The captain performs a gravity defying bicycle kick from outside the box while multiple defenders leap in slow motion. Stadium lights flicker, rain particles freeze mid air, crowds erupt, camera rotates around the player in ultra cinematic style as the ball curves perfectly into the top corner of the net. Massive fireworks explode above the stadium while teammates rush in celebration. Hyper realistic visuals, emotional storytelling, cinematic sports trailer pacing, high energy World Cup atmosphere, multi character consistency, smooth action choreography, realistic physics, premium blockbuster film quality, anamorphic lens flare, dramatic sound design, epic final frame with trophy reflection and roaring crowd. #RoboNeo

One shot. One dream. One unforgettable finish. ⚽🔥 Made this cinematic World Cup final using Agent Team inside RoboNeo with visuals powered by Seedance 2.0. Video Prompt 👇 A cinematic 30 second World Cup inspired short film set in a futuristic mega stadium at night. The atmosphere is electric with packed crowds waving flags, flashing lights, giant holographic scoreboards, smoke effects, and cinematic rain reflections on the pitch. Opening scene starts with a young underdog football captain walking through the stadium tunnel in slow motion while hearing the deafening roar of fans. Close up shots of boots touching the wet ground, tense faces, jerseys moving in the wind, and dramatic eye contact between rival teams. Ultra realistic cinematic camera movement, emotional tension, dynamic lighting, realistic crowd reactions, premium sports commercial quality. As the beat intensifies, transition into fast paced World Cup action. Explosive dribbling sequences, impossible skill moves, aggressive tackles, synchronized team movement, dramatic goalkeeper saves, and cinematic slow motion shots of the ball flying across the field. Final hero shot begins at the climax of the match. The captain performs a gravity defying bicycle kick from outside the box while multiple defenders leap in slow motion. Stadium lights flicker, rain particles freeze mid air, crowds erupt, camera rotates around the player in ultra cinematic style as the ball curves perfectly into the top corner of the net. Massive fireworks explode above the stadium while teammates rush in celebration. Hyper realistic visuals, emotional storytelling, cinematic sports trailer pacing, high energy World Cup atmosphere, multi character consistency, smooth action choreography, realistic physics, premium blockbuster film quality, anamorphic lens flare, dramatic sound design, epic final frame with trophy reflection and roaring crowd. #RoboNeo

Leonardo

46,724 просмотров • 2 месяцев назад

Stratosphere was our biggest and heaviest character on #Transformers ROTB. He was a real challenge to deal with on the Modeling, Texturing, and Rendering side. He had 1434 UDIMs due to his immense scale and was made up of tens of thousands of objects. His level of detail was truly something else. His vehicle form was also a behemoth. We had also built a mortar for his robot form and a cannon for his vehicle form but neither of these made it into the film as his part in the final battle was cut out. He was originally supposed to help out in the final battle, using both of these weapons against the Sweepers and Predacons. The decision to cut him from the final act came very late as all of his assets were final at that point. We were never told the reason why his role was cut from the film. I had to re-design my texturing system in Mari when working on him to ensure that it could handle such a complex and large character. I had to simplify a lot of the procedural systems and even had to branch off some of them into their own files to ensure that artists could work with somewhat decent performance. We ran into a lot of issues pushing him through our pipeline, both as a model as well as rendering him due to the sheer amount of objects and textures that had to be processed. For shots, it was requested by Lighting that we reduce his memory footprint as Google had complained he was taking up too much memory and their I/O for rendering on the cloud was being affected. The leadership team and I decided that the best way to do this was to half the texel density on the parts that wouldn't be visible in our approved shots and to also half the resolution of the textures in the parts not visible to camera. This allowed us to optimize his memory footprint both in shots as well as storage and I/O. It was massive technical undertaking working on Stratosphere, so much so that we had to delay getting him into shots as we simply couldn't push him through with our normal tooling. I really enjoyed the challenge that he posed for us as a team. CREDITS: Primary Modeling by Oscar Lowe Support Modeling by Arthur Grandjean and his team Final Texturing & Lookdev by Yaz Raji Video credits: Breakdown shot by MPC Film footage by Paramount

Stratosphere was our biggest and heaviest character on #Transformers ROTB. He was a real challenge to deal with on the Modeling, Texturing, and Rendering side. He had 1434 UDIMs due to his immense scale and was made up of tens of thousands of objects. His level of detail was truly something else. His vehicle form was also a behemoth. We had also built a mortar for his robot form and a cannon for his vehicle form but neither of these made it into the film as his part in the final battle was cut out. He was originally supposed to help out in the final battle, using both of these weapons against the Sweepers and Predacons. The decision to cut him from the final act came very late as all of his assets were final at that point. We were never told the reason why his role was cut from the film. I had to re-design my texturing system in Mari when working on him to ensure that it could handle such a complex and large character. I had to simplify a lot of the procedural systems and even had to branch off some of them into their own files to ensure that artists could work with somewhat decent performance. We ran into a lot of issues pushing him through our pipeline, both as a model as well as rendering him due to the sheer amount of objects and textures that had to be processed. For shots, it was requested by Lighting that we reduce his memory footprint as Google had complained he was taking up too much memory and their I/O for rendering on the cloud was being affected. The leadership team and I decided that the best way to do this was to half the texel density on the parts that wouldn't be visible in our approved shots and to also half the resolution of the textures in the parts not visible to camera. This allowed us to optimize his memory footprint both in shots as well as storage and I/O. It was massive technical undertaking working on Stratosphere, so much so that we had to delay getting him into shots as we simply couldn't push him through with our normal tooling. I really enjoyed the challenge that he posed for us as a team. CREDITS: Primary Modeling by Oscar Lowe Support Modeling by Arthur Grandjean and his team Final Texturing & Lookdev by Yaz Raji Video credits: Breakdown shot by MPC Film footage by Paramount

Rassoul Edji

268,448 просмотров • 1 год назад