Utut Animations @ututltd

🌧️Severe Weather Update – Heavy Rain🌧️ 🟠A Heavy Rain Warning is now in force for the Bay of Plenty area west of Kawerau 🟠A Heavy Rain Warning has been issued for Gisborne north of Tolaga Bay. 🟡 A Heavy Rain Watch has also been issued for the Bay of Plenty area about and east of Kawerau. Streams and rivers may rise rapidly. Surface flooding, slips, and difficult driving conditions are possible. Avoid low-lying areas and drive cautiously. Latest warnings: metservice.com/warnings/home @BOPCivilDefence

Watch Flow Studio’s Nikola Todorovic walk through one of many workflows possible in 3D Editor + Canvas, including how Marble by @theworldlabs can support the world-building stage.

Only if sites could be this interactive ❤️‍🔥 Fable 5 + Threejs Live: robot-game-3d-sq5l.vercel.app

📢 Multi-View Image to 3D just got a major upgrade! Now your textures generate from multiple views too. So a few references of the same object bring the whole model back with much higher accuracy and consistency, from structure to texture.

MiniMax H3 is native in ComfyUI, day zero with the weights. Model highlights: → Text-to-video, prompt only → Image-to-video → First-and-last-frame - control the opening frame, the closing frame, or both → Reference-to-video - carry a subject, a motion, or a voice through the clip → In-place editing - modify a shot you already have instead of regenerating it The capability @MiniMax_AI leads with is multimodal context understanding, and it's what collapses those five tasks into one model. H3 takes images, audio, and video together and resolves them against a prompt that explains how they relate. Download the workflows & learn more in our blog 👇

An new era has begun!

MiniMax (official) @MiniMax_AI

2 weeks ago

MiniMax-H3 Is Now Publicly Available huggingface.co/MiniMaxAI/Mini…

230 609 5K 1.8M 2K

MiniMax H3 open weights are out, with the nodes already in ComfyUI. One Blender blockout, run against Seedance 2.0 at a fraction of the cost per generation, leaving more room for experimentation and iteration. To try this workflow, link below 👇

Open weights are step one. Making them easy to serve is step two. H3 now has Day 0 support in @vllm_project's vLLM-Omni, complete with an OpenAI-compatible video endpoint. Huge thanks to the vLLM team for bringing H3 into the open inference stack. ⚡ #MiniMaxH3 #OpenWeights

vLLM @vllm_project

2 weeks ago

🎉 Congrats to @MiniMax_AI on releasing the open weights for MiniMax H3! Day-0 support in vLLM-Omni! One model reads text, images, video, and audio as a single context and returns video with native stereo audio. Text-to-video, first/last-frame, and multi-reference generation, 4

18 42 818 130K 148

H3 now has Day 0 support in @lmsysorg -- local, customizable, and ready to build on across @NVIDIAAI and @AMD hardware. #MiniMaxH3 #OpenWeights

LMSYS Org @lmsysorg

2 weeks ago

@MiniMax_AI H3 is live in SGLang Diffusion, with day-0 serving support 🎬 This open model matches Seedance 2.0 at 1/3 the cost, or $0 if you run it locally on 2x 5090 or 1 RTX 6000. With SGLang Diffusion, you can build visual concepts, motion design, e-commerce creatives,

18 19 346 98K 91

Race it 👇 f.mtr.cool/tbyblygkxq This is what #PhaserGameAgent v2 can do 🏎️ "Phaze Drift" by iLKke: a full 3D neon racer, 8 laps, boost gates, lasers and all, built from a prompt ⚡💥 #gamedev #phaserjs

I don't think i can go back to regular software anymore exploring a crazy combo of real-time depth estimation, raymarched SDFs, StreamDiffusion and BiRefNet. The entire setup was authored by GPT 5.6 Sol and Luna in Sentinel over MCP while I steered it in real-time.

JUST IN: Anthropic's valuation takes a hit following the release of China's Kimi K3 AI model. Now a 67% chance it hits $1,500,000,000,000.00 by the end of the year.

This PixVerse C1 prompt is absolutely wild. ⚡️ Prompt below 👇 Dynamic FPV shot: The camera races through a futuristic city during a violent rainstorm, skimming inches above flooded streets as neon reflections stretch across the water. Cars slide, streetlights explode, and waves of rainwater crash against glass buildings. The camera dives into a tunnel where the flood accelerates like a river, carrying sparks, debris, and shattered signs. A massive electrical explosion lights up the entire corridor, freezing millions of raindrops in midair. The droplets, smoke, and glowing reflections spiral together, naturally forming the word "RUSH" before the flood bursts out of the tunnel into the city. Cyberpunk action, liquid chaos, cinematic realism, ultra dynamic. Want more prompts like this?

TheDuckCow, the developer behind Godot Road Generator, has shared a newly merged update adding traffic lanes for procedural intersections. Check out the plug-in: 80.lv/articles/godot…

Show Codex a workflow once. Reuse it as a skill. Record & Replay lets you show Codex a recurring task, like filing an expense report or submitting a time-off request. Codex turns that demo into an inspectable, editable skill. You control when recording starts and stops.

Ideogram X Comfy Founders Live x.com/i/broadcasts/1…

Stumbled upon World of Claudecraft, an open source MMO created with Fable 5 (RIP). It's shockingly full featured - you can accept quests, trade items, duel, earn rewards, and more. And you can interact with other live players! Fun look at the future of vibecoding real games 👀

This is my loop I built a SaaS that posts to Instagram + TikTok 24/7 I don't write the captions. I don't pick the music. I don't touch it The stack that runs it while I sleep: > PHP 8.3, no framework > Caddy web server > SQLite in WAL mode > Cloudflare R2 for video storage > Cloudflare Tunnel, no open ports > Stripe for billing > OpenAI writes every caption > ffmpeg muxes the music > Zernio publishes to IG + TikTok > Vanilla JS + CSS on the front > one cron job that loops forever No Next.js. No Kubernetes. No VC

Microsoft Research introduces Mirage Latent spatial memory stores 3D scenes directly as latent tokens, skipping the costly RGB render-and-reencode loop. The result is up to 10.57x faster video generation, 55x lower memory use, and state-of-the-art consistency on WorldScore.