Introducing P-Video-2-Pro-Reference based on MiniMax (official) H3! 🎬 Combine images, videos, and audio references to guide how your video looks, moves, and sounds. Keep characters consistent, transfer motion, and bring different visual elements together in a single generation. • 𝗜𝗻𝗽𝘂𝘁: Text prompt with image and/or video references, plus optional... audio • 𝗥𝗲𝗳𝗲𝗿𝗲𝗻𝗰𝗲𝘀: Up to 9 images, 3 videos, and 3 audio files • 𝗗𝘂𝗿𝗮𝘁𝗶𝗼𝗻: 5–15s at 480p or 768p • 𝗣𝗿𝗶𝗰𝗶𝗻𝗴: Output starting at $0.015/s in Cost mode, with reference inputs billed separately • 𝗖𝗼𝗻𝘁𝗿𝗼𝗹: First and last frames, seed, aspect ratio, and prompt upsampling Two modes: Speed and Cost. Choose the trade-off that fits your workflow. Available via our inference partners Cloudflare, Scenario, Replicate, Wiro AI — Ship AI Faster, Tellers, each::labs, WaveSpeedAI, inference shell, @_segmind, Together AI, Eden AI, and Runware Validated by our benchmark partners Datapoint AI, Rapidata, and DesignArena 📚 Model docs: 🧩 API:show more

@MiniMax_AI congrats!

@MiniMax_AI Yeah making videos just got easier! Thanks for this

@MiniMax_AI love this keeping characters consistent while transferring motion could make multi scene video creation much easier.

@MiniMax_AI video creation feels so EASY now

@MiniMax_AI finally a way to keep the same character in every shot, that's been my biggest headache with ai video

@MiniMax_AI character consistency has been the biggest pain in ai video up to 9 image refs + motion transfer in one generation is a real fix for that

@MiniMax_AI banger!! congrats team

@MiniMax_AI Mixing video, images and audio in one workflow is actually crazy

@MiniMax_AI this is what i needed!!

@MiniMax_AI 🧑‍🍳🧑‍🍳

@MiniMax_AI the motion transfer part is what i'm most curious about. can you take the movement from one reference clip and apply it to a completely different character?

@MiniMax_AI Multi reference control for look motion and sound wins

@MiniMax_AI thats actually fire

@MiniMax_AI congrats team!!!

@MiniMax_AI The ability to combine visual and audio references while keeping characters consistent is a huge step forward. This gives creators much more control over the final result.

@MiniMax_AI Congrats! Our tests are very impressive

@MiniMax_AI $0.015 per second feels like microtransactions for creativity

@MiniMax_AI how well does character consistency hold up?

@MiniMax_AI now the slop comes with references and citations

@MiniMax_AI @PrunaAI It's wild how one missed element can throw off consistency. We learned the hard way to keep a tight checklist when mixing media for solo projects.

@MiniMax_AI how does the reference image control work - is it frame-level matching or does it extract style/motion separately?

@MiniMax_AI 🚀🚀

Combining image, video, and audio references while keeping characters consistent opens up huge possibilities for AI filmmaking. 🎬🔥 Creators, this is your chance to push beyond basic generations and build cinematic stories with real creative control. Who’s ready to test this and create something that looks straight out of a movie? 👀

@MiniMax_AI Does it handle lip-sync from audio refs?