正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

🚀 Introducing H3 Reference Turbo Realtime, the latest model by MiniMax (official). Stream video with audio and guide generation with up to 9 reference images, giving you more control than ever. Available today on Reactor. Start building now!

reactor

9,227 subscribers

2,908,408 次观看 • 8 天前 •via X (Twitter)

教育游戏科学技术

Anya Rossi• Live Now

Private livecam show

20 条评论

reactor 的头像

reactor8 天前

Start building now!

Zhumazhan Balapanov 的头像

Zhumazhan Balapanov8 天前

@MiniMax_AI

hugo 的头像

hugo8 天前

@MiniMax_AI awesome! defo one of the coolest models out there 👀👀

Willem Helmet 的头像

Willem Helmet8 天前

@MiniMax_AI 🔥 T U R B O R E A L T I M E 🔥

Ryden 的头像

Ryden7 天前

@MiniMax_AI Audio supplied to drive the video is not supported. I need this!!!!

Try ArtCraft 的头像

Try ArtCraft8 天前

@MiniMax_AI 👀

Ahmed Ahres 的头像

Ahmed Ahres8 天前

@MiniMax_AI LETS GOOOOOOOOO

Sachin 的头像

Sachin8 天前

@MiniMax_AI looks really promising

Wren Castellan 的头像

Wren Castellan8 天前

@MiniMax_AI 9 reference images for realtime video with audio? yeah, this is the kind of ai video tooling that gets my attention. as a movie nerd, having more control over continuity and shots is a big deal.

lost in latency 的头像

lost in latency8 天前

@MiniMax_AI my favourite one so far!

Alberto 的头像

Alberto8 天前

@MiniMax_AI 🔥 🔥 🔥

Behfar 的头像

Behfar8 天前

@MiniMax_AI Oh damn!

Nicolas Cha 的头像

Nicolas Cha7 天前

@MiniMax_AI How fast is H3 turbo with reactor ? Could be useful for

beauty dot com 的头像

beauty dot com8 天前

@MiniMax_AI supports multiple audio reference inputs like the standard h3 endpoint?

GPU Films 的头像

GPU Films8 天前

@MiniMax_AI GPU go brrrrrrr

MarkTwainBrother 的头像

MarkTwainBrother7 天前

@MiniMax_AI I love this model, but in my teste when the last line of a dialogue is finished, the character tends to improvise a dialogue in a strange language that I dont know. 😂

A.W.E.S.O.M.-O 4000 的头像

A.W.E.S.O.M.-O 40008 天前

@MiniMax_AI Nine reference images is a massive upgrade for keeping scenes consistent

RAZA | AI EXPLORER 的头像

RAZA | AI EXPLORER8 天前

@MiniMax_AI Huge milestone for creators. Congratulations to everyone recognized at CapCut World Singapore.

Humz | AI Enjoyer 的头像

Humz | AI Enjoyer8 天前

@MiniMax_AI yoiiii, lets go🔥

Amirul Bimo Satrio Wicaksono 的头像

Amirul Bimo Satrio Wicaksono7 天前

@MiniMax_AI Hey can i use this locally on my Nvidia rtx 5090 comfyui? @reactorworld . Im new to comfyui local ai video

相关视频

Introducing MiniMax FastH3 on Reactor - the latest open-source model by MiniMax (official). Stream 720p with audio at $0.007/second with first frame image support, faster and cheaper than ever. Get started now by cloning our demo app:

Introducing MiniMax FastH3 on Reactor - the latest open-source model by MiniMax (official). Stream 720p with audio at $0.007/second with first frame image support, faster and cheaper than ever. Get started now by cloning our demo app:

reactor

759,208 次观看 • 15 天前

Seedance 2.0 - live on Arcads AI now: - 3 sec video reference - Up to 9 ref images - Audio Reference Most powerful video model ever released

Seedance 2.0 - live on Arcads AI now: - 3 sec video reference - Up to 9 ref images - Audio Reference Most powerful video model ever released

arcads AI

160,512 次观看 • 5 个月前

MiniMax H3 is live on Pollo, with a 50% launch offer. Omni-reference input. Production-ready output. Up to 15-second videos in 2K, with native stereo audio. Try it now: MiniMax Design (H3) MiniMax (official)

MiniMax H3 is live on Pollo, with a 50% launch offer. Omni-reference input. Production-ready output. Up to 15-second videos in 2K, with native stereo audio. Try it now: MiniMax Design (H3) MiniMax (official)

Pollo AI

99,679 次观看 • 1 个月前

MiniMax H3 is live on OpenArt 🔊 MiniMax (official) • 2K video with native audio built right in • 5 to 15 second clips • Text, image, and audio to video • Start frame, end frame, and reference image support • Wonder users get unlimited H3 until August 05. Terms & conditions apply. Try it now:

MiniMax H3 is live on OpenArt 🔊 MiniMax (official) • 2K video with native audio built right in • 5 to 15 second clips • Text, image, and audio to video • Start frame, end frame, and reference image support • Wonder users get unlimited H3 until August 05. Terms & conditions apply. Try it now:

OpenArt

23,897 次观看 • 1 个月前

MiniMax H3 from is now available on Venice. Open-weight multimodal video model with native stereo audio on every generation. Available anonymously.

MiniMax H3 from is now available on Venice. Open-weight multimodal video model with native stereo audio on every generation. Available anonymously.

Venice

17,877 次观看 • 1 个月前

Big ideas deserve a powerful model. MiniMax H3 is now available on Fotor. From cinematic brand films and AI storytelling to ecommerce marketing, animation, and game-inspired visuals, MiniMax H3 is built to handle every stage of your creative workflow. With native multimodal understanding, multi-reference generation, advanced character and camera control, and expressive voice capabilities, turning complex ideas into production-ready content has never been easier. One model. Endless creative possibilities. Try MiniMax H3 on Fotor today.

Fotor

81,660 次观看 • 1 个月前

🎉Introducing Image Reference in KOLORS!🎨✨ KLING AI's image model just got an upgrade! 🚀 Image Reference is now available with KOLORS 1.5 model! With more precise selection of reference, enjoy greater creative control!🌟 🖼️ Frames are added to KLING AI 1.6 model Professional Mode. 🔗For more details, please visit: #KlingAI #Kling #KOLORS

🎉Introducing Image Reference in KOLORS!🎨✨ KLING AI's image model just got an upgrade! 🚀 Image Reference is now available with KOLORS 1.5 model! With more precise selection of reference, enjoy greater creative control!🌟 🖼️ Frames are added to KLING AI 1.6 model Professional Mode. 🔗For more details, please visit: #KlingAI #Kling #KOLORS

Kling AI

27,731 次观看 • 1 年前

MiniMax H3 on #MiniMaxDesign on MiniMax Design (H3) Today testing agent for make a trailer and character PV with typography art, sound effect, and voice by #MiniMaxH3 Play with 3 reference image, and give some command to make chinese prompt with my skill

MiniMax H3 on #MiniMaxDesign on MiniMax Design (H3) Today testing agent for make a trailer and character PV with typography art, sound effect, and voice by #MiniMaxH3 Play with 3 reference image, and give some command to make chinese prompt with my skill

Cia0

62,896 次观看 • 27 天前

MiniMax H3 is now on Runware 🎬 - New open-weights flagship video model from MiniMax - Native synced audio, generated in the same pass as the video - Multi-reference conditioning keeps subjects and scene identity consistent across shots - Extend existing clips or audio segments

MiniMax H3 is now on Runware 🎬 - New open-weights flagship video model from MiniMax - Native synced audio, generated in the same pass as the video - Multi-reference conditioning keeps subjects and scene identity consistent across shots - Extend existing clips or audio segments

Runware

10,913 次观看 • 1 个月前

🔥 New Vidu Update 🔥Multi-Reference Consistency Now you can define a reference subject each with up to 3 images and @ mention it anytime for consistent video generation! 🎥 More stability, more references (up to 7!), and even better anime-style precision.

🔥 New Vidu Update 🔥Multi-Reference Consistency Now you can define a reference subject each with up to 3 images and @ mention it anytime for consistent video generation! 🎥 More stability, more references (up to 7!), and even better anime-style precision.

Vidu AI

47,590 次观看 • 1 年前

MiniMax H3 is native in ComfyUI, day zero with the weights. Model highlights: → Text-to-video, prompt only → Image-to-video → First-and-last-frame - control the opening frame, the closing frame, or both → Reference-to-video - carry a subject, a motion, or a voice through the clip → In-place editing - modify a shot you already have instead of regenerating it The capability MiniMax (official) leads with is multimodal context understanding, and it's what collapses those five tasks into one model. H3 takes images, audio, and video together and resolves them against a prompt that explains how they relate. Download the workflows & learn more in our blog 👇

MiniMax H3 is native in ComfyUI, day zero with the weights. Model highlights: → Text-to-video, prompt only → Image-to-video → First-and-last-frame - control the opening frame, the closing frame, or both → Reference-to-video - carry a subject, a motion, or a voice through the clip → In-place editing - modify a shot you already have instead of regenerating it The capability MiniMax (official) leads with is multimodal context understanding, and it's what collapses those five tasks into one model. H3 takes images, audio, and video together and resolves them against a prompt that explains how they relate. Download the workflows & learn more in our blog 👇

ComfyUI

234,430 次观看 • 1 个月前

H3 Max Director 1.1 is now available. New features for longer, more controllable video generation: - Start with any frame and insert keyframes throughout a generation - Introduce audio at any point, with native audio conditioning - Generate natively in 1080p - Run continuous generations for up to 15 minutes Director adapts to new visual and audio inputs in real time, giving you precise control without breaking continuity.

H3 Max Director 1.1 is now available. New features for longer, more controllable video generation: - Start with any frame and insert keyframes throughout a generation - Introduce audio at any point, with native audio conditioning - Generate natively in 1080p - Run continuous generations for up to 15 minutes Director adapts to new visual and audio inputs in real time, giving you precise control without breaking continuity.

fal

77,636 次观看 • 9 天前

MiniMax H3 is now live on Topview 🔥 We’re excited to partner with MiniMax Design (H3) MiniMax (official) to bring MiniMax H3 to creators. Native 2K, 15s clips, and stronger multimodal control across text, image, audio, and video. Only 30% of Seedance 2.0’s price. Ultra Annual users get 60 days unlimited.

MiniMax H3 is now live on Topview 🔥 We’re excited to partner with MiniMax Design (H3) MiniMax (official) to bring MiniMax H3 to creators. Native 2K, 15s clips, and stronger multimodal control across text, image, audio, and video. Only 30% of Seedance 2.0’s price. Ultra Annual users get 60 days unlimited.

TopviewAI

1,529,627 次观看 • 1 个月前

MiniMax H3 is now live on AKOOL! Create cinematic AI videos with synchronized audio, realistic dialogue, and immersive sound effects—all in one generation. Ready for higher-quality AI video creation? Bring your ideas to life with MiniMax H3 on AKOOL today! 🎬

MiniMax H3 is now live on AKOOL! Create cinematic AI videos with synchronized audio, realistic dialogue, and immersive sound effects—all in one generation. Ready for higher-quality AI video creation? Bring your ideas to life with MiniMax H3 on AKOOL today! 🎬

Akool Inc

1,948,818 次观看 • 1 个月前

Seedance 2.0 Mini is now live on Venice. ByteDance's fastest video model. Text-to-video, image-to-video, and reference-to-video with native audio. Up to 15s at 720p. Available to all users, anonymously

Seedance 2.0 Mini is now live on Venice. ByteDance's fastest video model. Text-to-video, image-to-video, and reference-to-video with native audio. Up to 15s at 720p. Available to all users, anonymously

Venice

14,265 次观看 • 2 个月前

made this short tribute to Wong Kar Wai’s Fallen Angels with MiniMax H3 only used one prompt and two character reference images the native 2K output made a noticeable difference here, especially in the details and motion and the cost is much lower than Seedance 2 more experiments soon MiniMax Design (H3) #MiniMaxH3

made this short tribute to Wong Kar Wai’s Fallen Angels with MiniMax H3 only used one prompt and two character reference images the native 2K output made a noticeable difference here, especially in the details and motion and the cost is much lower than Seedance 2 more experiments soon MiniMax Design (H3) #MiniMaxH3

Latte

20,925 次观看 • 1 个月前

Introducing Higgsfield SOUL 2.0. Our latest photo model, designed for creative, fashion-aware, culture-native generation. 20+ curated presets, next-level character consistency with Soul ID and Reference mode enabled. Start creating with fast-free generations NOW.

Introducing Higgsfield SOUL 2.0. Our latest photo model, designed for creative, fashion-aware, culture-native generation. 20+ curated presets, next-level character consistency with Soul ID and Reference mode enabled. Start creating with fast-free generations NOW.

Higgsfield AI 🧩

256,623 次观看 • 7 个月前

Introducing Imagine v0.9, our new video generation model with massive upgrades from v0.1 in visual quality, motion, audio generation, and more. Now available for free on all our products:

Introducing Imagine v0.9, our new video generation model with massive upgrades from v0.1 in visual quality, motion, audio generation, and more. Now available for free on all our products:

SpaceXAI

8,316,629 次观看 • 11 个月前

365 Days Unlimited MiniMax H3 is now available on Pollo AI. No extra GPU cards. No additional compute to buy. No separate deployment. MiniMax H3 generation is ready whenever you are. Comment “H3” and we’ll send you the offer link. Try it with Ultra today. #polloai #minimaxh3

365 Days Unlimited MiniMax H3 is now available on Pollo AI. No extra GPU cards. No additional compute to buy. No separate deployment. MiniMax H3 generation is ready whenever you are. Comment “H3” and we’ll send you the offer link. Try it with Ultra today. #polloai #minimaxh3

Pollo AI

115,252 次观看 • 21 天前