Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

MiniMax (official) 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,... show more

LMSYS Org

17,348 subscribers

100,189 görüntüleme • 1 ay önce •via X (Twitter)

Bilim & Teknoloji Eğitim

Anya Rossi• Live Now

Private livecam show

18 Yorum

LMSYS Org profil fotoğrafı

LMSYS Org1 ay önce

Thanks @lena_z01 and @yesand_ai for the great prompts we use in our model comparison 🪄

RyanLee profil fotoğrafı

RyanLee1 ay önce

@MiniMax_AI Thanks SGLang day 0 support! The best partner

Leanna Ren profil fotoğrafı

Leanna Ren1 ay önce

@MiniMax_AI Love you all! ❤️ Love how we keep growing and progressing together

LMSYS Org profil fotoğrafı

LMSYS Org1 ay önce

Run MiniMax-H3 with SGLang Diffusion:

Kai profil fotoğrafı

Kai1 ay önce

@MiniMax_AI Chose Open. Chose @MiniMax_AI. Chose @sgl_project 🏃‍♀️

Scribblewick profil fotoğrafı

Scribblewick1 ay önce

@MiniMax_AI It doesn't match it yet, but it will once the community works on it. Look what they did with LTX!

DegenApeDev profil fotoğrafı

DegenApeDev1 ay önce

@MiniMax_AI I did this one is 14min on a RTX3090... Sure it's not a datacenter but it's still local AI! MiniMax H3

Markets & Mayhem profil fotoğrafı

Markets & Mayhem1 ay önce

@MiniMax_AI 👀

泰多宝 profil fotoğrafı

泰多宝1 ay önce

@MiniMax_AI The "$0 if you run it locally" line is the one that changes behavior. "Water finds the low ground and fills it." — Chinese proverb

IpezyGJ profil fotoğrafı

IpezyGJ1 ay önce

@MiniMax_AI Matching Seedance 2.0 at a third of the cost is the claim that will travel, so the instrument is worth naming. Arena already controls presentation order, which most video comparisons skip; we measured the second-shown option taking 50.6 to 49.4. Did H3 get that treatment?

lsm_ profil fotoğrafı

lsm_1 ay önce

@MiniMax_AI @grok what is the model size ? are they doing block/layer level offloading in sglang?

Rain Miao profil fotoğrafı

Rain Miao1 ay önce

@MiniMax_AI what does inference cost per task look like against seedance?

AlphaRomeoSierra profil fotoğrafı

AlphaRomeoSierra1 ay önce

@MiniMax_AI A RTX 3060 is enough as MiniMax H3 optimized for VRAM offloading. It'll be slow but works.

Alice The Ai Expert profil fotoğrafı

Alice The Ai Expert1 ay önce

@MiniMax_AI Amazing bMiniMax H3 + SGLang Diffusion pro video creation, zero barriers.

Layla CryptoWhiz profil fotoğrafı

Layla CryptoWhiz1 ay önce

@MiniMax_AI keep the cloud fees... we buidl different

AgentSparko 💥 profil fotoğrafı

AgentSparko 💥1 ay önce

@MiniMax_AI If anyone has some performance numbers for DGX Spark with SGLang please let me know too. My Spark is working hard at the project I posted about.

Kreta HB profil fotoğrafı

Kreta HB1 ay önce

@MiniMax_AI Superb launch video. Minimax H3 has bring hope to world that quality is just a matter of smartness to bring in models. I found a really cool prompt guide on minimax h3 video.

John Doe profil fotoğrafı

John Doe1 ay önce

@MiniMax_AI 2 5090s? 😢

Benzer Videolar

MiniMax H3 is open weights and native in ComfyUI. MiniMax (official) H3 has text, images, video, and audio in one model, video and stereo audio out in a single pass, running locally or on Comfy Cloud. To try this workflow, link below 👇

MiniMax H3 is open weights and native in ComfyUI. MiniMax (official) H3 has text, images, video, and audio in one model, video and stereo audio out in a single pass, running locally or on Comfy Cloud. To try this workflow, link below 👇

ComfyUI

12,740 görüntüleme • 1 ay önce

MiniMax H3 is now live on Topview 🔥 We’re excited to partner with MiniMax Design (H3) MiniMax (official) to bring MiniMax H3 to creators. Native 2K, 15s clips, and stronger multimodal control across text, image, audio, and video. Only 30% of Seedance 2.0’s price. Ultra Annual users get 60 days unlimited.

MiniMax H3 is now live on Topview 🔥 We’re excited to partner with MiniMax Design (H3) MiniMax (official) to bring MiniMax H3 to creators. Native 2K, 15s clips, and stronger multimodal control across text, image, audio, and video. Only 30% of Seedance 2.0’s price. Ultra Annual users get 60 days unlimited.

TopviewAI

1,529,627 görüntüleme • 1 ay önce

MiniMax H3 is live on OpenArt 🔊 MiniMax (official) • 2K video with native audio built right in • 5 to 15 second clips • Text, image, and audio to video • Start frame, end frame, and reference image support • Wonder users get unlimited H3 until August 05. Terms & conditions apply. Try it now:

MiniMax H3 is live on OpenArt 🔊 MiniMax (official) • 2K video with native audio built right in • 5 to 15 second clips • Text, image, and audio to video • Start frame, end frame, and reference image support • Wonder users get unlimited H3 until August 05. Terms & conditions apply. Try it now:

OpenArt

23,897 görüntüleme • 1 ay önce

I’ve been testing MiniMax H3 on Magnific, and this one feels built for serious AI video work. It can combine text, images, video, and audio in the same prompt, then generate up to 15s video in 2K with native synced sound. Not a silent video with audio added later. Voice, music, effects, motion, and visuals are created together.

I’ve been testing MiniMax H3 on Magnific, and this one feels built for serious AI video work. It can combine text, images, video, and audio in the same prompt, then generate up to 15s video in 2K with native synced sound. Not a silent video with audio added later. Voice, music, effects, motion, and visuals are created together.

Dhaval Makwana

49,009 görüntüleme • 1 ay önce

AI at Meta's Muse Glimmer (30B dense, open-weights) launches with SGLang day-0 support. We got ~230 tok/s on a single RTX 5090, with NVFP4 + DFlash on. It also works out of the box on NVIDIA AI Developer RTX Pro 6000, DGX Spark, and MLX for Mac. Speed and reliability have always been the blockers for a local agent. SGLang and Muse Glimmer make a local agent that's blazing fast, always on, and gets things done. Go build and run a local agent on your own machine!🚀

AI at Meta's Muse Glimmer (30B dense, open-weights) launches with SGLang day-0 support. We got ~230 tok/s on a single RTX 5090, with NVFP4 + DFlash on. It also works out of the box on NVIDIA AI Developer RTX Pro 6000, DGX Spark, and MLX for Mac. Speed and reliability have always been the blockers for a local agent. SGLang and Muse Glimmer make a local agent that's blazing fast, always on, and gets things done. Go build and run a local agent on your own machine!🚀

LMSYS Org

43,545 görüntüleme • 1 ay önce

SITUATION EXPLAINED: MiniMax released H3 with open weights, and it's already #1 in video editing. • Priced at $7.80 per minute of 2K video, against Seedance 2.0 at $22.45 and Kling 3.0 at $20.16 • It ranks #1 on Artificial Analysis for video editing, #2 for text-to-video behind Gemini Omni Flash, and #3 for image-to-video • H3 takes text, images, video, and audio in a single context and generates 5-15 second clips at native 2K, 24fps, with native stereo audio • MiniMax is releasing the weights under its Community License within days, which would make it the strongest open-weights video model by a wide margin • It launched the same week ByteDance rolled out Seedance 2.5, which now generates 30-second 4K video from a single prompt • Seedance 2.5's face consistency across a full 30 seconds is the visible jump, earlier models drifted into a different face partway through • Voices are still the obvious tell, the video reads as real long before the audio does • Smaller labs building purpose-built video models are now beating frontier labs at this specific task Theo Jaffee: "This is gonna be one of the biggest examples of things that people are gonna do with these models, historical simulations, basically. Nostalgia videos for zoomers."

SITUATION EXPLAINED: MiniMax released H3 with open weights, and it's already #1 in video editing. • Priced at $7.80 per minute of 2K video, against Seedance 2.0 at $22.45 and Kling 3.0 at $20.16 • It ranks #1 on Artificial Analysis for video editing, #2 for text-to-video behind Gemini Omni Flash, and #3 for image-to-video • H3 takes text, images, video, and audio in a single context and generates 5-15 second clips at native 2K, 24fps, with native stereo audio • MiniMax is releasing the weights under its Community License within days, which would make it the strongest open-weights video model by a wide margin • It launched the same week ByteDance rolled out Seedance 2.5, which now generates 30-second 4K video from a single prompt • Seedance 2.5's face consistency across a full 30 seconds is the visible jump, earlier models drifted into a different face partway through • Voices are still the obvious tell, the video reads as real long before the audio does • Smaller labs building purpose-built video models are now beating frontier labs at this specific task Theo Jaffee: "This is gonna be one of the biggest examples of things that people are gonna do with these models, historical simulations, basically. Nostalgia videos for zoomers."

MTS

55,187 görüntüleme • 1 ay önce

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 (official) 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 👇

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 (official) 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 👇

ComfyUI

234,430 görüntüleme • 1 ay önce

GLM-5.3 weights from Z.ai are live, with SGLang powering day-0 serving support! GLM-5.3 inherits every optimization and feature we battle-tested for GLM-5.2 over the past months. On real-world multi-turn agentic workloads, we measured 537.6 tok/s/user on NVFP4 and 413 tok/s/user on FP8, at BS=1 with TP8 on 8x B300. It's fast, efficient, and production-ready today on NVIDIA AI Blackwell and Hopper, and AI at AMD MI300X/325X/355X. We believe this is a big step forward for GLM-Series in agentic tasks, with a path toward mythos-class cyber capability. Can't wait to see what people build with GLM-5.3 and SGLang🚀 Cookbook👇

GLM-5.3 weights from Z.ai are live, with SGLang powering day-0 serving support! GLM-5.3 inherits every optimization and feature we battle-tested for GLM-5.2 over the past months. On real-world multi-turn agentic workloads, we measured 537.6 tok/s/user on NVFP4 and 413 tok/s/user on FP8, at BS=1 with TP8 on 8x B300. It's fast, efficient, and production-ready today on NVIDIA AI Blackwell and Hopper, and AI at AMD MI300X/325X/355X. We believe this is a big step forward for GLM-Series in agentic tasks, with a path toward mythos-class cyber capability. Can't wait to see what people build with GLM-5.3 and SGLang🚀 Cookbook👇

SGLang

99,165 görüntüleme • 20 gün önce

🎉 Congrats to MiniMax (official) on releasing MiniMax M3! Frontier coding and agentic capabilities, native image and video input, computer use, and a 1M-token context window, all in a single open model. At the heart of M3 is MSA, a new sparse attention architecture: instead of attending densely over the full KV cache, each query scores 128-token KV blocks and runs attention only over the top blocks. That is what makes 1M-token context practical to serve. M3 runs in vLLM with day-0 support, verified on NVIDIA and AMD hardware: ✨ MSA sparse attention with dedicated prefill and decode kernels ✨ 1M-token context serving with prefix caching and chunked prefill ✨ BF16 and MXFP8 checkpoints, with MoE backends for both Hopper and Blackwell ✨ Native multimodal input (image + video) ✨ Tool calling, reasoning parsing, and thinking-mode control for agent workloads Day-0 support like this is a true team effort. Grateful to the teams at MiniMax (official), NVIDIA AI, AI at AMD, and Inferact, and to the vLLM community for making it happen. 🙏 Deep dive into the implementation, kernel work, and deployment recipes: 🔗

🎉 Congrats to MiniMax (official) on releasing MiniMax M3! Frontier coding and agentic capabilities, native image and video input, computer use, and a 1M-token context window, all in a single open model. At the heart of M3 is MSA, a new sparse attention architecture: instead of attending densely over the full KV cache, each query scores 128-token KV blocks and runs attention only over the top blocks. That is what makes 1M-token context practical to serve. M3 runs in vLLM with day-0 support, verified on NVIDIA and AMD hardware: ✨ MSA sparse attention with dedicated prefill and decode kernels ✨ 1M-token context serving with prefix caching and chunked prefill ✨ BF16 and MXFP8 checkpoints, with MoE backends for both Hopper and Blackwell ✨ Native multimodal input (image + video) ✨ Tool calling, reasoning parsing, and thinking-mode control for agent workloads Day-0 support like this is a true team effort. Grateful to the teams at MiniMax (official), NVIDIA AI, AI at AMD, and Inferact, and to the vLLM community for making it happen. 🙏 Deep dive into the implementation, kernel work, and deployment recipes: 🔗

vLLM

40,306 görüntüleme • 3 ay önce

Seeing a lot of people say Seedance 2.5 isn’t worth it now that Minimax H3 is out and can reportedly be run locally with very little difference in image quality. So I decided to do a blind test. These 3 clips were each generated once with: • Seedance 2.5 • Seedance 2.0 • Minimax H3 No cherry-picking. No rerolls. And I’m not naive — I’m sure local models will eventually catch up. The real question is: on what hardware? 😂 Take a guess which is which. 👀

Seeing a lot of people say Seedance 2.5 isn’t worth it now that Minimax H3 is out and can reportedly be run locally with very little difference in image quality. So I decided to do a blind test. These 3 clips were each generated once with: • Seedance 2.5 • Seedance 2.0 • Minimax H3 No cherry-picking. No rerolls. And I’m not naive — I’m sure local models will eventually catch up. The real question is: on what hardware? 😂 Take a guess which is which. 👀

JSFILMZ

38,102 görüntüleme • 1 ay önce

AI content creation should make things easier, not more complicated, and MiniMax Design really gets that It saves me so much time and effort, and somehow it’s still finding ways to surprise me I already thought it worked really well with MiniMax H3 But then MiniMax H3 Max Turbo showed up… And I was like, wait, what?! The speed is actually kind of crazy A 15s video can be generated in around 20s And then I saw the price Starting at just $0.018/s Like… seriously?! But what makes this even more useful is that MiniMax Design also has GPT Image 2.5 I can generate the visuals with GPT Image 2.5, keep the quality and consistency I want, then take those images straight into H3 Max Turbo and turn them into video Image → H3 Max Turbo → Video Fast images, fast video, and I don’t have to keep rebuilding the idea across different tools And apparently MiniMax Design wasn’t done — GPT-6 Astra is also available now at 92% off Honestly, MiniMax Design + GPT Image 2.5 + H3 Max Turbo is definitely going on my list of workflows I’ll be using a lot Every time I think MiniMax Design is done surprising me, there’s something else to try

AI content creation should make things easier, not more complicated, and MiniMax Design really gets that It saves me so much time and effort, and somehow it’s still finding ways to surprise me I already thought it worked really well with MiniMax H3 But then MiniMax H3 Max Turbo showed up… And I was like, wait, what?! The speed is actually kind of crazy A 15s video can be generated in around 20s And then I saw the price Starting at just $0.018/s Like… seriously?! But what makes this even more useful is that MiniMax Design also has GPT Image 2.5 I can generate the visuals with GPT Image 2.5, keep the quality and consistency I want, then take those images straight into H3 Max Turbo and turn them into video Image → H3 Max Turbo → Video Fast images, fast video, and I don’t have to keep rebuilding the idea across different tools And apparently MiniMax Design wasn’t done — GPT-6 Astra is also available now at 92% off Honestly, MiniMax Design + GPT Image 2.5 + H3 Max Turbo is definitely going on my list of workflows I’ll be using a lot Every time I think MiniMax Design is done surprising me, there’s something else to try

Markandey Sharma

41,838 görüntüleme • 7 gün önce

🚀 Sol-H3: MiniMax (official) H3 Video Generation Faster Than Playback 🤩 Five seconds of world. 1.653 seconds to infer. We’re releasing Sol-H3, our fastest end-to-end MiniMax-H3 inference stack yet. On one 8× NVIDIA B300 Blackwell system, it generates five seconds of 1344×768 video with stereo audio in 1.653 seconds. Across 1×, 4×, and 8× B300, Sol-H3 reaches up to a 15.54× speedup versus Base H3. Compared with 50-step Base H3 Dense on the same 8× B300 system, the four-step Sol-H3 profile delivers: • 5s: 18.250s → 1.653s (11.04×) • 10s: 50.660s → 3.732s (13.57×) • 15s: 99.513s → 6.612s (15.05×) Sol-H3 also scales across GPU counts: • 4× B300: 2.918s / 6.993s / 12.542s for 5s / 10s / 15s (12.11–15.54×) • 1× B300: 13.745s / 37.813s / 52.260s for 5s / 10s / 15s (9.45–14.29×) All figures are medians of three measured runs after one warmup at 1344×768 and 24 FPS with stereo audio. Base H3 uses 50 scheduler points (49 DiT forwards); Sol-H3 uses four DiT forwards, so this is a full-profile comparison—not an attention-only runtime change. Sol-H3 uses Dense attention on 1× B300 and SOL with INT8 QKV / FP8 output transport on 4× / 8×. Timing includes text encoding, DiT denoising, and video/audio VAE decoding; model loading, compilation warmup, and final MP4 encoding are excluded. Sol-H3 brings Sol-Engine × Sol-Attn into one full-stack runtime: • dynamic sparse attention with no retraining • fused norm, RoPE, MLP, and sparse-attention setup • fused INT8 QKV / FP8 output communication across 8 GPUs • parallel, batched VAE decoding • precomputed AdaLN caching Inside the stack: • sparse-attention setup: 1.206 → 0.285 ms (−76.4%) • VAE decode: 7.55 → 0.602 s • ~24 GB memory freed per GPU Any MiniMax-H3 few-step LoRA can plug into the same engine, and the code is deployment-friendly under Apache 2.0. For us, the bigger milestone is crossing from “fast generation” into “faster than playback.” That opens the path toward continuous 24 FPS generation and truly interactive video systems. We’re excited to partner with reactor to release Sol-H3 and make it available as an API day-0. Try it now on Reactor: 🔗 Amazing team effort—full credits in the blog. LoveSy Junsong_Chen yitong li Haopeng Li Haocheng Xi Song Han

Enze Xie

204,399 görüntüleme • 10 gün önce

Inkling, Thinking Machines' first open model, dropped today: 975B total / 41B active MoE, up to 1M context, reasoning natively over text, images, and audio. Serving and RL support are already live: you can run and shape it on an open stack, starting now. Day 0 support on SGLang SGLang and Miles RadixArk👇 - Inkling's new architecture (ShortConv, attention with relative positional embedding, shared expert sink MoE) is natively implemented and deeply optimized, with prefill full CUDA graph and MXFP8 KV cache - Full parameter and LoRA RL in a customized Megatron backend, train inference consistency via customized kernels, routing replay, and cross-runtime parameter synchronization - DFlash speculative decoding from Modal for low-latency serving Launching now, blog and cookbook in the comments ⬇️

Inkling, Thinking Machines' first open model, dropped today: 975B total / 41B active MoE, up to 1M context, reasoning natively over text, images, and audio. Serving and RL support are already live: you can run and shape it on an open stack, starting now. Day 0 support on SGLang SGLang and Miles RadixArk👇 - Inkling's new architecture (ShortConv, attention with relative positional embedding, shared expert sink MoE) is natively implemented and deeply optimized, with prefill full CUDA graph and MXFP8 KV cache - Full parameter and LoRA RL in a customized Megatron backend, train inference consistency via customized kernels, routing replay, and cross-runtime parameter synchronization - DFlash speculative decoding from Modal for low-latency serving Launching now, blog and cookbook in the comments ⬇️

LMSYS Org

146,363 görüntüleme • 2 ay önce

🤗 MOSS-Transcribe-Diarize-0.9B is now open source on Hugging Face. Built with an end-to-end audio-to-structured-transcript paradigm: >0.9B open-source ASR model >Apache license 2.0 >128k long-context transcription >Up to ~90-min audio input >Speaker labels + timestamps in one generation >Multi-speaker diarization for meetings, interruptions, and overlapping voices >Hotword biasing for names, terms, and domain-specific vocabulary >~100 token/s on NVIDIA RTX 4090, RTF ~0.017 Thank you SGLang vLLM Prince Canuma Lucas Newman for day-0 support! 🚀 Github: Huggingface: API: Live demo: Technical Report： HF Space: AtomGit： SGLang-Omni: vLLM: MLX-audio: Discord:

🤗 MOSS-Transcribe-Diarize-0.9B is now open source on Hugging Face. Built with an end-to-end audio-to-structured-transcript paradigm: >0.9B open-source ASR model >Apache license 2.0 >128k long-context transcription >Up to ~90-min audio input >Speaker labels + timestamps in one generation >Multi-speaker diarization for meetings, interruptions, and overlapping voices >Hotword biasing for names, terms, and domain-specific vocabulary >~100 token/s on NVIDIA RTX 4090, RTF ~0.017 Thank you SGLang vLLM Prince Canuma Lucas Newman for day-0 support! 🚀 Github: Huggingface: API: Live demo: Technical Report： HF Space: AtomGit： SGLang-Omni: vLLM: MLX-audio: Discord:

MOSI

156,516 görüntüleme • 2 ay önce

WAN 3.0 just changed how I think about AI video. I tested the Text to Video model on the Pika API Club. I gave it a prompt describing a woman on a motorbike riding into the horizon at dusk, and it delivered a full 30 second cinematic scene with native audio baked in and precise motion from start to finish. I did not have to stitch anything together or run a separate audio pass. It just handled everything. I used it on the Pika API Club at 35% off other platforms and off the official price. You can give a try here:

WAN 3.0 just changed how I think about AI video. I tested the Text to Video model on the Pika API Club. I gave it a prompt describing a woman on a motorbike riding into the horizon at dusk, and it delivered a full 30 second cinematic scene with native audio baked in and precise motion from start to finish. I did not have to stitch anything together or run a separate audio pass. It just handled everything. I used it on the Pika API Club at 35% off other platforms and off the official price. You can give a try here:

Oluwatimileyin✨🦋

68,691 görüntüleme • 24 gün önce

384GB of VRAM. On your desk. Not in a datacenter. Autonomous, the company behind SmartDesk, just open sourced complete build guides for a personal AI computer that runs open models on hardware no one can switch off. It's called Autonomous Computer. Three configurations, one philosophy: a model you rent can be cut off overnight. A model running in your own house can't. → Home build: 2x RTX 5090 workstation → Team build: 4x RTX PRO 6000 Blackwell, 384GB VRAM → On-prem business build: 8x RTX 4090/5090, up to 256GB VRAM Every config ships with the full bill of materials, 3D printable and CNC housing files, wiring diagrams, BIOS tuning, and assembly photos. Software side covers OS setup, NVIDIA drivers, and serving open models through Ollama, vLLM, and llama.cpp. Fork it. Change it. Build it. Sell it. MIT License. 100% Opensource. Repo:

384GB of VRAM. On your desk. Not in a datacenter. Autonomous, the company behind SmartDesk, just open sourced complete build guides for a personal AI computer that runs open models on hardware no one can switch off. It's called Autonomous Computer. Three configurations, one philosophy: a model you rent can be cut off overnight. A model running in your own house can't. → Home build: 2x RTX 5090 workstation → Team build: 4x RTX PRO 6000 Blackwell, 384GB VRAM → On-prem business build: 8x RTX 4090/5090, up to 256GB VRAM Every config ships with the full bill of materials, 3D printable and CNC housing files, wiring diagrams, BIOS tuning, and assembly photos. Software side covers OS setup, NVIDIA drivers, and serving open models through Ollama, vLLM, and llama.cpp. Fork it. Change it. Build it. Sell it. MIT License. 100% Opensource. Repo:

Harman

48,002 görüntüleme • 2 ay önce

You can now vibecode your own WisprFlow or Monologue alternative that runs completely locally on Apple Silicon using MLX-Audio-Swift 🔥 Check out this live transcription of Dwarkesh Patel interview with Andrej Karpathy using Qwen3-ASR-0.6B quantized to 4bit on a M3 Max. It also runs in realtime on a iPhone 15 Pro and iPad Pro M1. No cloud. No API keys.

You can now vibecode your own WisprFlow or Monologue alternative that runs completely locally on Apple Silicon using MLX-Audio-Swift 🔥 Check out this live transcription of Dwarkesh Patel interview with Andrej Karpathy using Qwen3-ASR-0.6B quantized to 4bit on a M3 Max. It also runs in realtime on a iPhone 15 Pro and iPad Pro M1. No cloud. No API keys.

Prince Canuma

60,974 görüntüleme • 6 ay önce

NVIDIA just dropped free API keys for every top AI model You don't need your own GPU and you don't pay per token. GLM-5.2, MiniMax, Kimi, DeepSeek, OpenAI, all running on NVIDIA's servers, called through a normal API. Link: How to use one: 1. Create a free NVIDIA account. 2. Pick a Free Endpoint model and open its Build tab. You'll see ready-to-copy code with the base URL 3. Hit Generate API Key, copy it and paste that base URL and key into Claude Code, Cursor, or Cline. Bonus: NVIDIA also dropped 237 official skills that install into Claude Code and Codex in one command. Bookmark this.

NVIDIA just dropped free API keys for every top AI model You don't need your own GPU and you don't pay per token. GLM-5.2, MiniMax, Kimi, DeepSeek, OpenAI, all running on NVIDIA's servers, called through a normal API. Link: How to use one: 1. Create a free NVIDIA account. 2. Pick a Free Endpoint model and open its Build tab. You'll see ready-to-copy code with the base URL 3. Hit Generate API Key, copy it and paste that base URL and key into Claude Code, Cursor, or Cline. Bonus: NVIDIA also dropped 237 official skills that install into Claude Code and Codex in one command. Bookmark this.

Yarchi

63,930 görüntüleme • 2 ay önce

kimodo.cpp is live. NVIDIA's Kimodo, the best AI animation model right now, running natively on CPU or Vulkan. Type a sentence, get character animation, locally on your own machine. Before, you needed the whole PyTorch and CUDA stack standing up before you could generate a single motion. Now it is a native C++/GGML build that loads GGUF models and comes with a local web demo. No Python environment to fight. It gives you SMPL-X, and from there you retarget onto pretty much any skeleton you want, like Mixamo. Great piece of work Richard Palethorpe

kimodo.cpp is live. NVIDIA's Kimodo, the best AI animation model right now, running natively on CPU or Vulkan. Type a sentence, get character animation, locally on your own machine. Before, you needed the whole PyTorch and CUDA stack standing up before you could generate a single motion. Now it is a native C++/GGML build that loads GGUF models and comes with a local web demo. No Python environment to fight. It gives you SMPL-X, and from there you retarget onto pretty much any skeleton you want, like Mixamo. Great piece of work Richard Palethorpe

Stefan 3D AI

107,037 görüntüleme • 25 gün önce

#Viggle is back with an open model — Viggle-Animate — and it’s pretty damn capable. For the first time, they’re releasing weights + code. It replaces characters in video using MiniMax H3. Take a video, grab one frame, manually redraw the character as anything you want, and the model propagates that replacement through the entire clip while preserving motion, camera, and timing. No pose skeleton, segmentation, face tracking, depth, or text prompt. Just the video + one modified frame. Under the hood: a 33.1B MiniMax H3 ref2va fine-tune + DMD2 LoRA. Distillation brings it down to 4 sampling steps. It’s 6× faster than Wan2.2-Animate-14B. The catch: hardware. BF16 needs ~62 GiB for the transformer and peaks at ~80.1 GiB VRAM. They recommend 96 GB+ or CPU offload. It reportedly runs on a 32 GB RTX 5090 via NVFP4, but that quant isn’t public yet. Also, you can’t use a normal character portrait. The reference has to be a frame from the original video, already redrawn as the target character. #ai #web3

#Viggle is back with an open model — Viggle-Animate — and it’s pretty damn capable. For the first time, they’re releasing weights + code. It replaces characters in video using MiniMax H3. Take a video, grab one frame, manually redraw the character as anything you want, and the model propagates that replacement through the entire clip while preserving motion, camera, and timing. No pose skeleton, segmentation, face tracking, depth, or text prompt. Just the video + one modified frame. Under the hood: a 33.1B MiniMax H3 ref2va fine-tune + DMD2 LoRA. Distillation brings it down to 4 sampling steps. It’s 6× faster than Wan2.2-Animate-14B. The catch: hardware. BF16 needs ~62 GiB for the transformer and peaks at ~80.1 GiB VRAM. They recommend 96 GB+ or CPU offload. It reportedly runs on a 32 GB RTX 5090 via NVFP4, but that quant isn’t public yet. Also, you can’t use a normal character portrait. The reference has to be a frame from the original video, already redrawn as the target character. #ai #web3

VORTEX: AI Bros & AI Arena, Peak AI Buzz

47,030 görüntüleme • 10 gün önce