🚀 Excited to introduce StreamRender-H3 — bringing real-time interactive worlds to life with diffusion models! Built on Sol-Engine, we post-trained MiniMax (official) H3 Ref2VA into a real-time streaming neural renderer. 🎮 Code drives the world. A game engine handles physics, object states, and player interactions, while H3 generates the... visuals. ⚡ Real-time streaming: 2 denoising steps, 24 FPS, and ~273 ms per chunk on 8×GB200 GPUs. 🎨 One world, endless appearances: Change the reference image and prompt to render the same interactive world in entirely different styles. 🔥 Powered by streaming post-training, distillation, a fast causal H3 VAE, and full-stack inference acceleration. Check out our demo and code! 👇 demo: code:show more

@MiniMax_AI Is 8xGB200 a good starter setup for gaming? jk impressive results

@MiniMax_AI ideally should run this on RTX series GPU~

@Scobleizer @MiniMax_AI Build your own gta 6 before gta 6

@MiniMax_AI Impressive, real time on >$500.000 of GPU though🫤 DLSS5 is promising I can run GTA V in 4K50 with 2x DLSS5 on my RTX 4070Ti Super, maybe the future is low quality 3D with AI filters.

@MiniMax_AI Cool step towards programmable world👏

@MiniMax_AI Sol-Engine and 2 denoising steps and you still need 8x GB200?

@MiniMax_AI yes, because H3 is large(33B) and latency should be as low as possible

@MiniMax_AI Can't you get a similar result with for example 8x 5090s if latency is the main issue?

@MiniMax_AI Great work - we're working on a similar tech, will soon be released on @BaduzGame and work in the browser!

@MiniMax_AI

@MiniMax_AI Amazing work!

@MiniMax_AI super cool!

@MiniMax_AI Will Muse have streaming version？🤔

@MiniMax_AI stay tuned!

@MiniMax_AI sounds very very cool

@MiniMax_AI Well done. Over time, this may be superior to traditional game rendering, especially alongside controller models.

@MiniMax_AI this is amazing Will love to read on it

@MiniMax_AI This makes a lot of sense

@MiniMax_AI amazing!

@MiniMax_AI Neat

@MiniMax_AI 快速转视角的时候，画面能跟得上吗？

@MiniMax_AI How do you handle coherency? Like will everything be the same for the second round of the race, even if coming from a different angle, and point of view ? Or that all the other cars stay exactly the same for the whole experience?

@MiniMax_AI How do you get around MiniMax strict usage license in the US?

@MiniMax_AI amazing!

@MiniMax_AI 👏👏👏

@MiniMax_AI Doesn’t it take 8xGb200 GPUs? 💰

@MiniMax_AI @MoshiMoshiMoan cant wait to buy these skins on the in-game store 😂

@MiniMax_AI Amazing Work!

@MiniMax_AI super cool! I run @glitchlive_ AI livestreaming platform. We are looking for a faster and cheaper way to render realtime streams. Can I use this model as a service?

@MiniMax_AI Letting the game engine own physics and H3 only paint the frames is the right split. 273 ms per chunk on 8×GB200 is the number I'll be watching shrink.

@MiniMax_AI This real-time neural renderer concept is insane

@MiniMax_AI 8×GB200 GPUs. easier to generate the code that then renders on a more normal GPU

@MiniMax_AI This is sick.

@MiniMax_AI 请问有做 inverse-cfg 吗？还是直接训？

@MiniMax_AI Giga Impressive, sadly the HW it requires make it not very practical