MiniMax M2.7🆚MiniMax M2.5 - Website about recently released video... games The release of M2.7 should be close. MiniMax M2.5 was released two days after it appeared on the Arenashow more

MiniMax M2.5 casually responding at ~50 tok/s with MLX... (M3 Ultra). The model was released one hour ago 🥳show more

We’re partnering with MiniMax (official) across product and models... to make their upcoming releases the best for Hermes Agent users. MiniMax models are already some of the most-used in Hermes Agent. If you haven’t tried MiniMax M2.7 in Hermes Agent, try it today in the Nous Portal!show more

I am using Minimax M2.5 heavily without worrying about... the usage limit The Plus plan is all you need It gives 300 prompts per 5 hours which is more than enough for me.show more

MiniMax M2.5 is benchmaxed. I gave 4 models the... same prompt: Create a neon "OPEN" sign in HTML. GLM 5: Clean, classic neon. Nailed it. Claude Opus 4.6: Stylized with glow. Solid. Gemini 3 Pro: Cursive with bloom lighting. Creative. MiniMax M2.5: Spelled it "O b∈ N" with broken spacing. This model ranks #2 on BridgeBench with a 59.7 score and 100% completion rate. But it can't spell a 4-letter word. Benchmarks don't tell the whole story. A model can ace structured tasks and fail basic creative prompts. High score ≠ production ready.show more

This is one of the cheapest AI coding stacks... I’ve seen. Alibaba Cloud just dropped a coding plan starting at $10/month. With qwen3.5-plus, kimi-k2.5, glm-5, and MiniMax-M2.5, it already supports tools like Claude Code, Codex, OpenClaw, Cline, and more. Link to try: 👇show more

nothing in this video was filmed, minimax h3 generated... the whole thing from one prompt.. what stands out is it didnt just animate a creature on top of a scene, it generated the found footage look itself, shake, grain, focus hunting, and all #MiniMaxH3 Hailuo AI (MiniMax)show more

Introducing MiniMax H3 on Argil Some days, the future... decides to accelerate. Two days ago, we launched the new version of Argil. Today, I’m extremely happy to announce our partnership with MiniMax (official): H3 is live in Argil. We tested it internally. The quality is really solid. An intelligence that reads text, images, video and audio as one language. That captures creative intent at a glance and already delivers production-ready content. MiniMax H3 will soon be open source. And that’s a real game changer. For the occasion, Golden Ticket: 40% off Pro & Business yearly during MiniMax Hive until tonight. Comment "argil" I’ll send you the code in DM. To those who create: the field just got wider. Link 👇show more

48 hours after releasing VDN-H3 for MiniMax (official) H3,... the community already shipped 2 independent ComfyUI integrations with 9 multimodal workflows. This makes it much easier for people to use them! Meanwhile, VDN was trained only on T2VA, but the community immediately pushed beyond our original scope, validating I2VA/FL2VA with no retraining. Huge credit to everyone building on it. A great sign of how composable MiniMax (official) H3 is! RyanLee MiniMax Design (H3)show more

Minimax H3 Max Turbo just got added to Krea... Krea and the generation speed is insane. It generated a 15-second video in about 16 seconds seriously mind-blowing. For the prompt, I adapted one shared by Koda, one of my favorite creators. Thanx!! #krea #Minimax #minimaxh3maxturboshow more

SN50 is REALLY FAST. And you don't have to... just take our word for it. ⚡️ @SemiAnalysis independently benchmarked SN50 running MiniMax (official) M2.7 at ~800 t/s. That's consistent with the 800+ t/s we demonstrated at RAISE Summit, validated by Artificial Analysis. Fast inference just got another third-party stamp of approval.show more

When the new model drops and your entire workflow... turns into pure chaos. 🤯 White cat mascot coding at 3 AM, shark onesie on the couch, a real cat riding an alligator… this is the kind of unhinged creativity that #MiniMaxH3 is about to unlock. Made with MiniMax Design (H3) × MiniMax (official). The future of AI video is going to be wild.show more

i generated this video using two blurry pics of... myself from two years ago at griffith observatory with the MiniMax H3 model. it's surprisingly natural and sounds really close to how i actually speak. i haven't followed video generation models enough in the past year, but i'm really curious about the tech behind them. now they can even generate high-fidelity voice, accurate text, and editable video. i still remember the days when we were shocked by gpt-4o and the sora sample video. it's been a long way since then. #MiniMaxH3 MiniMax Design (H3)show more

I tried recreating one of those viral water obstacle... challenge videos… and I couldn’t stop laughing. 😂 This was made with MiniMax H3 on Pollo AI. The best part? MiniMax H3 is currently available with a 365 Days Unlimited plan on Pollo AI. No GPUs. No extra compute. No setup. Just create. 🚀show more

New Minimax model handles 2D animation very nice! So... far very impressive model.... we are so spoiled these days with options it's a great time to be a creator. Worth noting, the sound on this model is significantly better than some of the other options.. Feels close to SD 2.0show more

MINIMAX H3 VIDEO GENERATION IS ABSURDLY POWERFUL. I generated... this 15-second animation of Attack on Titan and I swear to God, it looks just like the anime I didn't even think this level of quality was possible Cost was $0.30 + took 30 secondsshow more

A new approach to AI video generation is here.... MiniMax H3 combines multimodal understanding with generation, allowing it to work with text, images, video, and audio as part of the same creative process. Creators can use multiple references for characters, motion and camera movement, while also controlling edits and voices. Cinematic output reaches up to 2K at 24FPS with native stereo audio. Explore it on MiniMax Design (H3): #MiniMaxH3show more

The slowest part of AI video isn't the quality... — it's the wait, H3 Max on MiniMax Design fixes that. Post-trained by fal for high-speed generation, it renders video faster than Twitch streams — so you can iterate, experiment, and ship in minutesshow more

MiniMax H3 image+audio to video feed an audio into... h3 instead of generating it. i was testing this flow, got shocked with how good the lipsync and movement is implemented it on the i2v version in diffusers, made a demo for it. what do you think? 🔊 ▶️show more

(1/7) Last week FastVideo released FastH3. Today we bring... it local: NVIDIA DGX Spark 💚 and Apple Silicon 🍎through MLX. 8x speedup! FastH3 now supported on NVIDIA DGX Spark and Apple Silicon! over base MiniMax (official) H3 for local generation! This 15 seconds 1344×768 clip was generated on two NVIDIA DGX Sparks. Fully local. NVIDIARTXSpark NVIDIAAIshow more

I think AI Agents are about to completely change... how we prompt video models. I gave the MiniMax Design AI Agent one image and one simple instruction: “Act as an expert FPV director and turn this into something viral.” It analyzed the idea, built the camera logic, movement and pacing, then created a ridiculously detailed prompt for MiniMax H3. This is what came out. 🤯 And yes, I’m sharing the exact prompt + workflow in the thread 👇 #MiniMaxH3 on #MiniMaxDesignshow more