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。

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 -... show more

ComfyUI

57,963 subscribers

234,430 次观看 • 1 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

31 条评论

ComfyUI 的头像

ComfyUI1 个月前

Download the workflow & learn more with our blog:

HealthRanger 的头像

HealthRanger1 个月前

The moment I've been waiting for! This is going to be awesome... let the downloads begin!

泰多宝的头像

泰多宝1 个月前

"Day zero" is the whole story. "Strike while the iron is hot." — Chinese proverb

AI Mastery Guide 的头像

AI Mastery Guide1 个月前

Day zero support like that shows real partnership

Catholic 的头像

Catholic1 个月前

There are so many annoying people in this world! Someone gets something for free and still wants to make demands, without even saying thank you...

Hakuhyo 的头像

Hakuhyo1 个月前

👀Wait it’s kinda insane if it’s this quality running on local…

JSFILMZ 的头像

JSFILMZ1 个月前

wait is it haiulo h3 same quality?

Max Bidding 的头像

Max Bidding1 个月前

Nice, can't wait to give it a go once I got the new HD installed. I had too many 😅

李科男的头像

李科男1 个月前

@grok 当前开源的模型最小支持部署的硬件，显存是多少～

Child of Rose 的头像

Child of Rose1 个月前

I’m really interested to see how the first-and-last-frame control changes storytelling in video creation

Token4AI Cloud 的头像

Token4AI Cloud1 个月前

这个模型有点强大啊 AI短剧生产力

Lynn Cherny 的头像

Lynn Cherny1 个月前

Signing up for your cloud today :)

Prince does AI 的头像

Prince does AI1 个月前

ok first-and-last-frame is the part i want

Otnashi 的头像

Otnashi1 个月前

@bdsqlsz I knew it no Omni model will be released

symbols 的头像

symbols1 个月前

cool

ComfyUI 的头像

ComfyUI1 个月前

@zenohosting

RB Walter 的头像

RB Walter1 个月前

Day zero support is insane! 🚀 Is there an example workflow JSON available yet for testing the first-and-last frame control.

Lumeta AI 的头像

Lumeta AI1 个月前

Made with MiniMax-H3 on

Saurs 的头像

Saurs1 个月前

Can we expect the next formal comfyui version release soon today?

ComfyUI 的头像

ComfyUI1 个月前

It’s released

Saurs 的头像

Saurs1 个月前

Oh my god lol, looks like it was just as I commented that. Sorry. Thank you!

Some Nobody 的头像

Some Nobody1 个月前

seems pretty good. how many different references can it handle per video? And how much censorship can be expected, especially in terms of combat/violence?

Alan 的头像

Alan1 个月前

Damn hell yeah

CatGod 的头像

CatGod1 个月前

The seamless jump from text to video feels like opening a portal with just words.

SaiyiaHQ 的头像

SaiyiaHQ1 个月前

Day-0 native nodes are the distribution channel for video models the same way HF transformers was for LLMs: the graph becomes the product surface. H3’s value proposition in Comfy is workflow collapse—five generation modes sharing one multimodal understanding path—so studios can version creatives as graphs, not prompt folklore. Misconception: more nodes always means more control; without eval harnesses for identity drift and audio-video sync, you just scale failure modes. Builders should ship regression clips and golden workflows next to weights. If local H3 quality approaches Seedance-class APIs at lower cost, who captures the margin—model labs or workflow platforms?

Oguzhan Taskin 的头像

Oguzhan Taskin1 个月前

@MiniMax_AI, clarify this. Your license says “Powered by MiniMax H3” is only encouraged, but your official Q&A says “Must disclosure” and that any H3 material remaining in the final output still requires disclosure. Which is it? Link: 1/3

Kreta HB 的头像

Kreta HB1 个月前

coolest video ever seen. I have written minimax h3 video prompt guide. can you try it

idesign 的头像

idesign1 个月前

Can Agent, Skills and other functions be supported in ComfyUI?

Benjamin Arnaud 的头像

Benjamin Arnaud1 个月前

Is this content / checked flagged or equivalent to running it locally ?

Akhe🔺🇧🇷🇵🇹 的头像

Akhe🔺🇧🇷🇵🇹1 个月前

I'll wait for an NVFP4. Given my setup, I could even run it today, but I feel bad for my M.2 with such massive offloading haha

Rain Miao 的头像

Rain Miao1 个月前

how does local inference cost per task compare to seedance?

相关视频

MiniMax H3 is open weights and native in ComfyUI. MiniMax (official) H3 has text, images, video, and audio in one model, video and stereo audio out in a single pass, running locally or on Comfy Cloud. To try this workflow, link below 👇

MiniMax H3 is open weights and native in ComfyUI. MiniMax (official) H3 has text, images, video, and audio in one model, video and stereo audio out in a single pass, running locally or on Comfy Cloud. To try this workflow, link below 👇

ComfyUI

12,740 次观看 • 1 个月前

FLUX 3 Video is live in ComfyUI via Partner Nodes Black Forest Labs FLUX 3 Model highlights: → 20s in a single generation → native audio, not dubbed on after → text-to-video, image-to-video, keyframes, continuation → multi-scene and multi-angle in one prompt → multilingual dialogue with lipsync that holds → typography that sits in the scene → chain clips agentically for longer stories One model across video, audio, image, and action. Click the link below to download the workflows and learn more with blog

FLUX 3 Video is live in ComfyUI via Partner Nodes Black Forest Labs FLUX 3 Model highlights: → 20s in a single generation → native audio, not dubbed on after → text-to-video, image-to-video, keyframes, continuation → multi-scene and multi-angle in one prompt → multilingual dialogue with lipsync that holds → typography that sits in the scene → chain clips agentically for longer stories One model across video, audio, image, and action. Click the link below to download the workflows and learn more with blog

ComfyUI

25,715 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

I’ve been testing MiniMax H3 on Magnific, and this one feels built for serious AI video work. It can combine text, images, video, and audio in the same prompt, then generate up to 15s video in 2K with native synced sound. Not a silent video with audio added later. Voice, music, effects, motion, and visuals are created together.

I’ve been testing MiniMax H3 on Magnific, and this one feels built for serious AI video work. It can combine text, images, video, and audio in the same prompt, then generate up to 15s video in 2K with native synced sound. Not a silent video with audio added later. Voice, music, effects, motion, and visuals are created together.

Dhaval Makwana

49,009 次观看 • 1 个月前

#Viggle is back with an open model — Viggle-Animate — and it’s pretty damn capable. For the first time, they’re releasing weights + code. It replaces characters in video using MiniMax H3. Take a video, grab one frame, manually redraw the character as anything you want, and the model propagates that replacement through the entire clip while preserving motion, camera, and timing. No pose skeleton, segmentation, face tracking, depth, or text prompt. Just the video + one modified frame. Under the hood: a 33.1B MiniMax H3 ref2va fine-tune + DMD2 LoRA. Distillation brings it down to 4 sampling steps. It’s 6× faster than Wan2.2-Animate-14B. The catch: hardware. BF16 needs ~62 GiB for the transformer and peaks at ~80.1 GiB VRAM. They recommend 96 GB+ or CPU offload. It reportedly runs on a 32 GB RTX 5090 via NVFP4, but that quant isn’t public yet. Also, you can’t use a normal character portrait. The reference has to be a frame from the original video, already redrawn as the target character. #ai #web3

#Viggle is back with an open model — Viggle-Animate — and it’s pretty damn capable. For the first time, they’re releasing weights + code. It replaces characters in video using MiniMax H3. Take a video, grab one frame, manually redraw the character as anything you want, and the model propagates that replacement through the entire clip while preserving motion, camera, and timing. No pose skeleton, segmentation, face tracking, depth, or text prompt. Just the video + one modified frame. Under the hood: a 33.1B MiniMax H3 ref2va fine-tune + DMD2 LoRA. Distillation brings it down to 4 sampling steps. It’s 6× faster than Wan2.2-Animate-14B. The catch: hardware. BF16 needs ~62 GiB for the transformer and peaks at ~80.1 GiB VRAM. They recommend 96 GB+ or CPU offload. It reportedly runs on a 32 GB RTX 5090 via NVFP4, but that quant isn’t public yet. Also, you can’t use a normal character portrait. The reference has to be a frame from the original video, already redrawn as the target character. #ai #web3

VORTEX: AI Bros & AI Arena, Peak AI Buzz

47,030 次观看 • 10 天前

LTX-2.5 is native in ComfyUI, day zero with the weights Model highlights: → Diffusion Fidelity Rendering - compute allocated by scene complexity, not spread evenly → Diffusion Video Decoder - replaces VAE decoding, sharper faces and legible text → Native multi-shot - one run, multiple connected shots, consistent across the cuts → Custom Gemma 4 12B text encoder - long prompts survive intact, no dropped clauses → Prompt enhancer + auto duration - two fewer parameters to tune The change LTX leads with is Diffusion Fidelity Rendering, and it's what lifts detail across the whole stack rather than one stage of it. Learn more and download the workflows with the link below 👇

LTX-2.5 is native in ComfyUI, day zero with the weights Model highlights: → Diffusion Fidelity Rendering - compute allocated by scene complexity, not spread evenly → Diffusion Video Decoder - replaces VAE decoding, sharper faces and legible text → Native multi-shot - one run, multiple connected shots, consistent across the cuts → Custom Gemma 4 12B text encoder - long prompts survive intact, no dropped clauses → Prompt enhancer + auto duration - two fewer parameters to tune The change LTX leads with is Diffusion Fidelity Rendering, and it's what lifts detail across the whole stack rather than one stage of it. Learn more and download the workflows with the link below 👇

ComfyUI

2,405,487 次观看 • 1 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

SITUATION EXPLAINED: MiniMax released H3 with open weights, and it's already #1 in video editing. • Priced at $7.80 per minute of 2K video, against Seedance 2.0 at $22.45 and Kling 3.0 at $20.16 • It ranks #1 on Artificial Analysis for video editing, #2 for text-to-video behind Gemini Omni Flash, and #3 for image-to-video • H3 takes text, images, video, and audio in a single context and generates 5-15 second clips at native 2K, 24fps, with native stereo audio • MiniMax is releasing the weights under its Community License within days, which would make it the strongest open-weights video model by a wide margin • It launched the same week ByteDance rolled out Seedance 2.5, which now generates 30-second 4K video from a single prompt • Seedance 2.5's face consistency across a full 30 seconds is the visible jump, earlier models drifted into a different face partway through • Voices are still the obvious tell, the video reads as real long before the audio does • Smaller labs building purpose-built video models are now beating frontier labs at this specific task Theo Jaffee: "This is gonna be one of the biggest examples of things that people are gonna do with these models, historical simulations, basically. Nostalgia videos for zoomers."

SITUATION EXPLAINED: MiniMax released H3 with open weights, and it's already #1 in video editing. • Priced at $7.80 per minute of 2K video, against Seedance 2.0 at $22.45 and Kling 3.0 at $20.16 • It ranks #1 on Artificial Analysis for video editing, #2 for text-to-video behind Gemini Omni Flash, and #3 for image-to-video • H3 takes text, images, video, and audio in a single context and generates 5-15 second clips at native 2K, 24fps, with native stereo audio • MiniMax is releasing the weights under its Community License within days, which would make it the strongest open-weights video model by a wide margin • It launched the same week ByteDance rolled out Seedance 2.5, which now generates 30-second 4K video from a single prompt • Seedance 2.5's face consistency across a full 30 seconds is the visible jump, earlier models drifted into a different face partway through • Voices are still the obvious tell, the video reads as real long before the audio does • Smaller labs building purpose-built video models are now beating frontier labs at this specific task Theo Jaffee: "This is gonna be one of the biggest examples of things that people are gonna do with these models, historical simulations, basically. Nostalgia videos for zoomers."

MTS

55,187 次观看 • 1 个月前

LTX-2 is natively supported in ComfyUI on Day 0 🎬🔊 The next chapter in controllability for open-source video generation. - Open-source audio-video foundation model - Generates motion, dialogue, SFX, and music together - Canny, Depth & Pose video-to-video control - Keyframe-driven generation - Native upscaling and prompt enhancement Everything in a single pass.

LTX-2 is natively supported in ComfyUI on Day 0 🎬🔊 The next chapter in controllability for open-source video generation. - Open-source audio-video foundation model - Generates motion, dialogue, SFX, and music together - Canny, Depth & Pose video-to-video control - Keyframe-driven generation - Native upscaling and prompt enhancement Everything in a single pass.

ComfyUI

108,422 次观看 • 8 个月前

MINIMAX H3 JUST REPLACED THE ENTIRE ANIMATION PIPELINE before: a studio quotes $150,000 for a 25-second anime opening like this. a designer, an animator, an editor. 6 weeks across 4 different tools. after: i wrote the concept once and got 25 finished seconds back, the cuts and the card graphics already in the frame. I made this anime opening on MiniMax Design from one original idea. Both characters look the same in every shot, and black, white and red hold from the first frame to the last. The agent broke the concept into shots on its own and handed back the finished sequence. Motion graphics, VFX, anime openings and music videos, all in one platform with local assets and scalable APIs. Created with MiniMax H3 and its Omni Reference. Hats off to MiniMax Design (H3) 【#MiniMaxH3 on #MiniMaxDesign】

MINIMAX H3 JUST REPLACED THE ENTIRE ANIMATION PIPELINE before: a studio quotes $150,000 for a 25-second anime opening like this. a designer, an animator, an editor. 6 weeks across 4 different tools. after: i wrote the concept once and got 25 finished seconds back, the cuts and the card graphics already in the frame. I made this anime opening on MiniMax Design from one original idea. Both characters look the same in every shot, and black, white and red hold from the first frame to the last. The agent broke the concept into shots on its own and handed back the finished sequence. Motion graphics, VFX, anime openings and music videos, all in one platform with local assets and scalable APIs. Created with MiniMax H3 and its Omni Reference. Hats off to MiniMax Design (H3) 【#MiniMaxH3 on #MiniMaxDesign】

Fokki

80,007 次观看 • 29 天前

Today, we're announcing that Comfy is the first and only commercial license distributor for MiniMax (official)'s generative media models. MiniMax open weight models have been downloaded through Comfy close to 20M times. Now you can license them for commercial work. → Full commercial rights to your outputs → Fine-tuning and LoRA training, fully allowed → Client and agency projects covered → MiniMax Audio & Music, not just video Professional and Enterprise plans, with Enterprise covering every H3 model version. Request a license with the link below today ⬇️

Today, we're announcing that Comfy is the first and only commercial license distributor for MiniMax (official)'s generative media models. MiniMax open weight models have been downloaded through Comfy close to 20M times. Now you can license them for commercial work. → Full commercial rights to your outputs → Fine-tuning and LoRA training, fully allowed → Client and agency projects covered → MiniMax Audio & Music, not just video Professional and Enterprise plans, with Enterprise covering every H3 model version. Request a license with the link below today ⬇️

ComfyUI

144,394 次观看 • 21 天前

MiniMax (official) H3 is live in SGLang Diffusion, with day-0 serving support 🎬 This open model matches Seedance 2.0 at 1/3 the cost, or $0 if you run it locally on 2x 5090 or 1 RTX 6000. With SGLang Diffusion, you can build visual concepts, motion design, e-commerce creatives, precise video edits, animation and stylized visuals, all locally on your own machine. No API bill, no waitlist. H3 takes text, image, video and audio in a single context, and generates 5-15s clips at native 2K, 24fps with native stereo audio. SGLang Diffusion also runs on NVIDIA AI Blackwell and Hopper, and AMD MI355X / MI300X. Let's create something with MiniMax H3 👇

MiniMax (official) H3 is live in SGLang Diffusion, with day-0 serving support 🎬 This open model matches Seedance 2.0 at 1/3 the cost, or $0 if you run it locally on 2x 5090 or 1 RTX 6000. With SGLang Diffusion, you can build visual concepts, motion design, e-commerce creatives, precise video edits, animation and stylized visuals, all locally on your own machine. No API bill, no waitlist. H3 takes text, image, video and audio in a single context, and generates 5-15s clips at native 2K, 24fps with native stereo audio. SGLang Diffusion also runs on NVIDIA AI Blackwell and Hopper, and AMD MI355X / MI300X. Let's create something with MiniMax H3 👇

LMSYS Org

100,189 次观看 • 1 个月前

In May, we integrated 11 new models spanning image, 3D, audio, video, and multimodal. The highlights: → Krea 2 — style-first image generation, live as a Partner Node on day one. Competes on how the frame looks, not just what's in it → VOID (Netflix) — removes objects and everything they caused: shadows, reflections, physical interactions. Apache 2.0, natively supported → Tripo 3.1 + TripoSplat — one image to a full 3D Gaussian asset, end to end Also live in May: Gemma 4, HidDream-O1-Image, Stable Audio 3, BiRefNet, MoGe, Claude, OpenRouter, Luma UNI-1 Learn more with our blog 👇

In May, we integrated 11 new models spanning image, 3D, audio, video, and multimodal. The highlights: → Krea 2 — style-first image generation, live as a Partner Node on day one. Competes on how the frame looks, not just what's in it → VOID (Netflix) — removes objects and everything they caused: shadows, reflections, physical interactions. Apache 2.0, natively supported → Tripo 3.1 + TripoSplat — one image to a full 3D Gaussian asset, end to end Also live in May: Gemma 4, HidDream-O1-Image, Stable Audio 3, BiRefNet, MoGe, Claude, OpenRouter, Luma UNI-1 Learn more with our blog 👇

ComfyUI

20,550 次观看 • 3 个月前

🚀 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!

🚀 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

2,908,408 次观看 • 8 天前

Another Hailuo AI (MiniMax) H3 test, this time looking at audio reference and performance (A little NSFW language on end of this one!). I recorded the dialogue as an audio track and fed that in as a reference with a image reference of the man. In the text prompts I gave some direction to the actor (Like the look to camera at the end). I think the model did a brilliant job of matching the performance to the words and emotion that were in the audio ref. Unlike Seedance 2.0 I didn't have to feed in black video or write the words in the prompt to get the words correct. It seemed to use the exact audio from the reference I provided, which is what you want when using voice actors. Things are getting real... fast

Another Hailuo AI (MiniMax) H3 test, this time looking at audio reference and performance (A little NSFW language on end of this one!). I recorded the dialogue as an audio track and fed that in as a reference with a image reference of the man. In the text prompts I gave some direction to the actor (Like the look to camera at the end). I think the model did a brilliant job of matching the performance to the words and emotion that were in the audio ref. Unlike Seedance 2.0 I didn't have to feed in black video or write the words in the prompt to get the words correct. It seemed to use the exact audio from the reference I provided, which is what you want when using voice actors. Things are getting real... fast

Uncanny Harry AI

14,036 次观看 • 1 个月前

New course: Build AI agents that generate images and videos -- an under-explored frontier. A key to performance is having the agent evaluate its own output, and iterate to improve quality. This short course is built together with Google Cloud Tech and taught by Katie Nguyen and Wafae Bakkali. You'll learn three evaluation techniques and combine them in an agent: image-text similarity scoring to check the output matches the prompt, an LLM judge that scores against custom criteria like brand consistency, and structured rubrics that break a prompt into verifiable yes/no questions like "is the subject in the frame?" and "does the camera motion match?" Skills you'll gain: - Learn image and video prompt engineering - Build an image agent that turns brand guidelines into UI mockups - Build a video agent that plans multi-scene explainers and animates reference frames with synchronized audio Join and build agents that create images and video!

Andrew Ng

141,404 次观看 • 4 个月前

MiniMax H3 Max is now live in ComfyUI. Post trained by @Fal, this model was trained for speed and precision. Can't wait for the open weights!

MiniMax H3 Max is now live in ComfyUI. Post trained by @Fal, this model was trained for speed and precision. Can't wait for the open weights!

ComfyUI

93,552 次观看 • 13 天前

Viggle’s Mic 2.0 is here! With our upgraded model, take precise control over how a character talks and moves, in one shot. Turn images into videos simply with an audio or text prompt for speech. Or take it further—add a motion source to drive the character’s movements—action and voice, perfectly aligned. Try it free on our web, or on our iOS/Android apps.👇

Viggle’s Mic 2.0 is here! With our upgraded model, take precise control over how a character talks and moves, in one shot. Turn images into videos simply with an audio or text prompt for speech. Or take it further—add a motion source to drive the character’s movements—action and voice, perfectly aligned. Try it free on our web, or on our iOS/Android apps.👇

ViggleAI

36,201 次观看 • 1 年前

Livestream Alert: Open World Models in Production: LTX.io and ComfyUI Founders Live A special live conversation with Yoland Yan ( CEO, ComfyUI ) & comfyanonymous ( Founder, ComfyUI ) and Zeev Farbman ( CEO, LTX ) Join us as we sit down with the teams behind LTX and ComfyUI to talk about building an open world model that integrates natively into the production tools creators use. We'll explore what it took to build LTXa foundational model that understands space, motion, and how the physical world operates—with synchronized video and audio generation, truly open weights, and the flexibility to fine-tune on your own data. We'll explore what it took to ship a frontier video model in the open, how LTX and ComfyUI are building the pipeline for AI-driven production together, and what it means for creators, developers, and the wider open-source ecosystem. What we'll cover: → LTX: the open world model for synchronized video + audio, and beyond → Native integration into ComfyUI workflows and production pipelines → Open world models vs. closed platforms and where things are headed → Fine-tuning LTX on your own data with LTX Trainer → Community Q&A — bring your questions

Livestream Alert: Open World Models in Production: LTX.io and ComfyUI Founders Live A special live conversation with Yoland Yan ( CEO, ComfyUI ) & comfyanonymous ( Founder, ComfyUI ) and Zeev Farbman ( CEO, LTX ) Join us as we sit down with the teams behind LTX and ComfyUI to talk about building an open world model that integrates natively into the production tools creators use. We'll explore what it took to build LTXa foundational model that understands space, motion, and how the physical world operates—with synchronized video and audio generation, truly open weights, and the flexibility to fine-tune on your own data. We'll explore what it took to ship a frontier video model in the open, how LTX and ComfyUI are building the pipeline for AI-driven production together, and what it means for creators, developers, and the wider open-source ecosystem. What we'll cover: → LTX: the open world model for synchronized video + audio, and beyond → Native integration into ComfyUI workflows and production pipelines → Open world models vs. closed platforms and where things are headed → Fine-tuning LTX on your own data with LTX Trainer → Community Q&A — bring your questions

ComfyUI

13,174 次观看 • 1 个月前