MiniMax H3

HyperFlow started with a question we keep exploring: how far can a focused training loop take a strong base model? We took ＠MiniMax H3, ran data-free flow self-distillation on it. The model generates its own outputs, filters for quality, and teaches itself. No external data. No human labels. Better camera control. Better consistency. Better material detail. Significantly lower inference cost. The same distillation method that powers RSI in our own models, now proven on an open foundation. The technique travels. Open source. Go build.

@video_rebirth

We're open-sourcing H3 HyperFlow. > A data-free flow self-distillation technology built on @MiniMax_AI H3. No external training data. Significantly reduces inference cost while preserving frontier model quality. > Full demo:

• videorebirth.com

Minimax H3 😃 👄🗣️ ASMR Trigger & Audio LoRA > This lora is designed for High quality (T2V/I2V) ASMR audio and soft whisper acoustics video generation > 👇

@SD_Tutorial

Minimax H3 😃 👄🗣️ ASMR Trigger & Audio LoRA > This lora is designed for High quality (T2V/I2V) ASMR audio and soft whisper acoustics video generation > 👇

• huggingface.co

Kijai's 😃 Minimax H3 Vae use less VRAM that not only speeds up the int8 VAE even more, but also the original fp16 VAE. 👇

• huggingface.co

We're proud to contribute as an AI partner to the newly launched @Singtel AI Pass, supporting Singapore's SkillsFuture AI Subscription initiative. 🇸🇬 MiniMax H3 (@Hailuo_AI), MiniMax Agent (@MiniMaxAgent) and MiniMax Audio are all part of the program, giving eligible learners across 200+ SWDA-supported AI courses hands-on access to premium AI tools and the opportunity to build practical, real-world AI skills. This partnership brings our mission, "Intelligence with Everyone" to life, and we're excited to see learners across Singapore turn curiosity into skills, ideas into action, and build confidently with AI. Learn more:

• singtel.com

If you use video models in your pipeline, would highly recommend checking out @PrunaAI I heavily use them with @GradiumAI voices and TTS.

@johnrachwan

We just launched what I believe is the best video model in the world. > • Faster than real-time generation at both 480p and 768p • SOTA-level quality, built on MiniMax H3 • Prompt upsampling in ~1 second > This was a massive ML + engineering achievement by the @PrunaAI team. > And somehow, what we’re shipping next week is even more exciting.

You can run locally Minimax H3-NS/FW Uncensored model. - Ref-to-video NSFW for H3 - se/x/ytime v1.2 for se/?-scene motion - time scenes + coherent motion first, then detail. - Not a checkpoint. - A late-night adapter. - softer sharper detail, slightly more surreal - audio that doesn’t fall apart if you use the right sampler. -

@0x0SojalSec

Uncensored MiniMax-H3-encoder run locally. > - Qwen3-VL encoder, INT8 + ConvRot, built for ComfyUI. - Smaller file than BF16. - Loader: CLIPLoader to minimax - Same node path. - Uncensored label, > -

• huggingface.co
• huggingface.co

fal head of engineering @isidentical reveals how reinforcement learning turned H3 Max into a frontier video model that generates 5 seconds of video in under 3 seconds, down from nearly 2 minutes: "It's probably the only frontier video model from a quality and output and adherence perspective that can generate videos in real time." "We took this open source base MiniMax H3 video model, what we wanted to do was not just make it faster, but improve its quality ahead of anything else by implementing reinforcement learning for verifiable concepts like video editing and prompt adherence." "We were able to get the model from 120 seconds for a 5-second video generation, almost 2 minutes, to under 3 seconds for a 5-second video generation. Almost double real time, while improving its quality ahead of the open source version and ahead of many frontier closed source models." @fal

@fal

Introducing H3 Max, new post-trained video model by fal Research. > H3 Max ranks #1 for overall qu

Minimax H3 by Hao AI Lab “FastVideo FastH3 V2” is now available on HuggingFace

@haoailab

(1/8) Open weight FastVideo FastH3 V2 is ready! Up to 9x speedup on @NVIDIA Blackwell with lossless quality! > Lossless quality compared to @MiniMax_AI 50-step H3! Judge for yourself below! > - Collab with @nuvalab , NVIDIA FastGen, NVIDIA Enterprise Products - Day 0 @ComfyUI template available! - Day 0 API serving available on @reactorworld ! - Omni-ref is currently training 👨‍🍳 > More comparisons and info below!

• huggingface.co

Thank you, Japan, for the incredible support! 🇯🇵 The "IP × AI" Summit, co-hosted by KAGAMI AI and MiniMax, has officially concluded. More than 150 companies from Japan and the U.S. joined us, alongside distinguished guests, including AKB48 producer Yasushi Akimoto, KAGAMI AI Chairman Takami Kondo, and KADOKAWA editor and producer Motoi Chujo. Global AI leaders @runwayml, @higgsfield, @krea_ai, and @HeyGen came together to explore the future of IP and generative AI. At the summit, MiniMax unveiled H3 IP Edition, bringing the power of MiniMax H3 together with officially licensed Japanese IP for a new generation of AI-powered storytelling. The summit received extensive coverage from major Japanese media, including a dedicated segment on TV Tokyo's WBS, @wbs_tvtokyo. Even more excitingly, over 60 companies have already expressed interest in adopting MiniMax H3 IP Edition. This marks a pivotal step toward bringing officially licensed Japanese IP into the generative AI era. Japanese IP × Global AI. A new

TaoMate-H3 turns MiniMax H3 into a low-latency streaming audio-video generator built for continuous creation. 🤖 ⚡ Runs the DiT 11.45× faster and delivers the first playable video 10.60× faster than standard MiniMax H3 in the reported 480×864, 10-second test. 🎬 Generates synchronized video, speech, and sound in five-second chunks instead of waiting for the full sequence. 🔄 Clean KV cache and integrated audio guidance preserve identity, voice, and motion as prompts change across chunks. 🧩 A three-step LoRA supports continuous portrait or landscape generation at 480p, 768p, and aligned 1080p. Inference code and 4-GPU or 8-GPU deployment are included. 📜 MiniMax H3 Community License.

• modelscope.ai

H3 keeps getting faster. ⚡️ @sgl_project + VDN-H3 now push MiniMax H3 beyond 2× real-time denoising on 8× B200 - generating 14.4s of 768p video in 9.0s end-to-end after warmup, with no measured quality regression. Open models compound through open ecosystems. 🚀

@sgl_project

SGLang-Diffusion with VDN-H3 now generates 14.4s of 768p video in just 9.0s 🚀 > On 8× B200, 8 step denoising takes just 6.9s, reaching over 2× real time. The 9.0s figure covers the full generation request after warmup. > No measured quality regression versus dense 50-step H3 across 103 test prompts. 🧵

Open weights. Shared progress. MiniMax H3 is moving fast. We built MiniMax H3 for video generation with native stereo audio and multimodal reference control. The open-source community is making that capability faster, more accessible, and easier to build on. Recent highlights: • FastH3 — FastVideo, Nuva Lab and NVIDIA: 4-step distillation, now running on DGX Spark and Apple Silicon. • Sol-H3 — NVIDIA’s SANA team: now on DGX Spark with a two-stage H3 + LTX-2.5 pipeline. On 8×B300, the team reports 15 seconds of 768p video + audio in 6.6 seconds of warm inference.* • VDN — Haocheng Xi and the OpenVDN team: rethinking attention for faster H3 inference, with weights, training and inference code released. • PDD — NVIDIA’s distillation method, brought to H3 by Alibaba PAI as 8-step Acc-LoRAs, now supported in ComfyUI. • LightX2V — 4- and 8-step Turbo LoRAs, with workflows for text, image and reference-conditioned video + audio. Behind every release are people training, optimizing, quantizing, testing and sh

Taomate H3 by Alibaba, a new acceleration method for Minimax H3. This streams the generation in small chunks and supports continuous, long videos.

• github.com

MiniMax H3 is now on my preferred image and video generator on Apple Silicon! I need to try it!

@drawthingsapp

🚨 MiniMax H3 is RIGHT HERE in Draw Things！Go try it NOW！ > 🔄 Draw Things v26.0910.1 was released in the iOS / macOS AppStore 2 hours ago. This version brings: > 🔹 Support MiniMax H3 series models, including LoRAs and TeaCache; 🔹 Support importing Krea 2 series models. 🔹 Fix some performance issues on M4 Apple Neural Engine. > gRPServerCLI and draw-things-cli both are updated to 26.0910.1 with above related updates.