MiniMax H3 4-step model lands in Maestro: 14s 720p video in 2.5 minutes on a 4090
cocktailpeanut · x · 2026-09-05
Blizaine integrates MiniMax H3's fused 4-step model into Maestro, supporting text-to-video, image-to-video, references and audio-driven generation plus smooth infinite extension. A 4-step example generates 14.4s of 720p video in 2.5 minutes on a 4090; 8 steps yields more detail.
Related event: MiniMax H3 4-Step Generation Lands in Local Creation Tools(3 posts)→
More from Multimodal
- Voxtral 3 ships a LiveKit-based voice agent SDK streaming listen-think-speak — MistralAI · 2026-10-21
- Voxtral Mini TTS 3 hits SOTA expressiveness in 35+ languages with tag-based control — MistralAI · 2026-10-21
- Mistral launches Voxtral 3 speech models and new Voice Agents API — MistralAI · 2026-10-21
- Open-sourced pixel art normals generator ships as Rust CLI and wasm library — HugoDuprez · 2026-10-20
- Fibo 2.0 is strongest for ecommerce and creator content, weakest at UIUX design — ArtificialAnlys · 2026-10-20
- Fibo 2.0 leads old Fibo on all 9 capabilities, best at reasoning and anatomy — ArtificialAnlys · 2026-10-20