introducing MiniMax H3. this new model matches seedance’s features... at a fraction of the cost, and it will soon be open-weights! learn more👇show more

MiniMax M2.7 made this Monica Apartment in Three.js literally... in 4 months we got same level of model in coding at lower cost they will opensource it soon , and MiniMax M3 will be multimodal / 1 T modelshow more

The new open-weights Hailuo AI (MiniMax) H3 is live... on OpenRouter thanks to MiniMax (official)! H3 is a lightweight video model for text, image, audio, & video input, with native audio-visual output. Built for instruction-led edits, text/brand rendering, and video-2-video motion transfer.show more

MiniMax H3 (Hailuo-03) is now available on fal. -... Open-weight multimodal video model with native stereo audio on every generation. - Combines up to 9 images, 3 video clips, and 3 audio clips as references - Holds subjects, motion, and audio consistent - Weights will be released soon.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

Want better MiniMax-H3 LoRAs? DiffSynth-Studio just open-sourced two things... worth checking out. 🔥 ⚙️ The MiniMax-H3 Training Adapter, a rank 64 LoRA. Combined with differential training, it helps you train higher quality LoRAs: 🔗 📦 The self-generated dataset behind the adapter, fully open as well: 🔗 One more thing: the adapter will soon power MiniMax-H3 LoRA training on ModelScope Civision. Stay tuned. 🚀show more

Hailou MiniMax H3 vs. Seedance 2.0 with 9 Reference... images. Only one model used all 9 images... and only one model generated a better output at 1/3 the cost...show more

I've been testing the new omni model H3 #MiniMaxH3... Very solid one I have to say, especially the grading is very clean and delivers at 2k standard res. This is one of the test done with img2vid Well done to MiniMax Design (H3)! Next will be to check multishots and video ref!show more

In this setup, a Blender blockout provides the motion... and composition while a reference image guides the environment, subject, and textures with MiniMax H3. With open weights, you can previs the final look locally for free or run it on Comfy Cloud. To try this workflow, link below 👇show more

Hailuo / MiniMax H3 is here! 🚀 Just ran... my first experiment with the new H3 model using an idea I previously tested on the 2.3 version — and the results are surprisingly impressive. This was a true one-shot generation: first attempt, no retries, no selecting the best take. More experiments coming soon as I explore what H3 can really do. 🔥 Diving deeper into Hailuo AI (MiniMax) ✨ #MiniMaxH3show more

Seedance 2.5 tends to pick up more natural movement... and follow 3D blockouts more closely—but sometimes the results are nearly 1:1 with MiniMax. MiniMax ran at a fraction of the credit cost in this Comfy Cloud test, or can be run locally for free. Both have their place. It comes down to the use case, the results you need, and how much room you have to iterate. To try this workflow, link below 👇show more

Introducing Videorc A fully open source recording studio and... livestream platform. The future of video should be open. Features you won't find anywhere else 👇show more

Your agency's rate card didn't move this year. Your... cost per video just dropped 70%. TopviewAI is running MiniMax H3 at a third of the going rate.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

Hailuo H3 is here, and it's already exceeding expectations.... This is my first fighting scene generated with the new model, and the action looks incredibly smooth. The motion, camera work, and overall consistency feel like a major leap forward. Looking forward to pushing it even further. MiniMax Design (H3) #MiniMaxH3show more

i gave minimax h3 one detailed prompt and it... directed its own commercial, camera angles, lighting changes, slow motion shot, all included this is the ai model ad agencies should be testing right now #MiniMaxH3 Hailuo AI (MiniMax)show more

Player stats UI animation with GPT Image 2 and... MiniMax H3. This model is amazing for UI animations. Give GPT Image 2 your character image and ask it to create a stats UI. Then use that UI as a reference for MiniMax H3. You can check the prompt in the replies.show more

MiniMax-H3 open source: a general-purpose multimodal generative model that... unified understanding of multimodalof text, images, video, and audio, and is capable of generating audio and video with native stereo sound, supporting up to 15 seconds at 2K resolution.show more

i'm speechless! i got MiniMax-H3 running fully offline on... a mac studio! 15 seconds, three shots, 32kHz stereo denoised jointly with the picture. took 39 minutes! Weights MiniMax Design (H3), Mac engine David Dalcu 🤗 I have ZERO knowledge of making any movies! Sound on and enjoy!show more

🎉 Congrats to MiniMax (official) 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 to 15 seconds at up to 2K and 24 FPS. The MP4 comes back with H.264 video and a synchronized stereo track already muxed in. It serves over the OpenAI-compatible /v1/videos endpoint, synchronous or async with job polling. 🔊 The video ⬇️ was made with H3, served on vLLM-Omni.show more