Magnific Spotlight: MiniMax H3
New model. New possibilities. Come see what it can do.
MiniMax just open-sourced H3 — a general-purpose video model that reads text, images, video, and audio as one context, and generates 2K video with native stereo sound in the same pass. No bolted-on audio stage. No separate tool for edits — just describe the change in a sentence: swap a product, relight a scene, replace a line of dialogue.
It's already #1 in Video Editing, #2 in Text-to-Video, and #3 in Image-to-Video on the Artificial Analysis leaderboard. And now it's live in Magnific.
This is the first edition of Magnific Spotlight — a new series where we bring the newest models straight to you, fresh off launch. Relaxed vibe, no fluff, just exploration.
On the agenda:
🎬 Showcase — real projects the community has already made with H3
🛠️ Workflow — a live walkthrough finding H3's best practices, in real time
Schedule
5:30 PM — Welcome, Food & Networking
Arrive, grab food and drinks, and connect with fellow creators and builders.
6:00 PM — Introductions + H3 Video Showcase
A quick introduction to Magnific and MiniMax, followed by a showcase of projects created with H3.
6:15 PM — Fireside Chat: MiniMax × Magnific
Victor Su-Ortiz and Enrique Lopez discuss what’s new with H3, the state of AI video, and how MiniMax and Magnific are approaching the future of creative workflows.
6:30 PM — Live H3 Workflow Demo
A live creative workflow using H3 in Magnific, showcasing cinematic generation, native audio, dialogue, editing, and more.
7:00 PM — Networking + Open Showcase
Continue the conversation, explore the projects, and connect with the Magnific and MiniMax teams.
Come curious. Leave with new tricks for your creative workflow.
📍 Magnific San Francisco Office
About MiniMax
MiniMax is a global AI company developing multimodal foundation models and AI-native products. Founded in 2022, our models—including MiniMax M3, H3, Speech 2.6 and Music 3.0—support advanced coding, agentic performance and long-context processing across text, audio, images, video and music. They power MiniMax Code, MiniMax Hub, MiniMax Audio, Talkie and our Open API Platform, serving 300M+ users in 200+ countries and 1M+ enterprises and developers in 100+ countries.
The Fine Print:
📸 This event might be photographed and/or filmed. By attending, you consent to your image being used by Freepik for marketing and communications purposes.
🚗 Parking is limited. We recommend public transportation. If driving, the best streets for parking are Howard, Natoma, and Rausch St.
♿ Please note this venue is not ADA compliant.
💬 Questions? DM us directly.