Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Introducing FastH3-Omni. The fastest and highest-quality open-source version of realtime H3 by MiniMax (official), post-trained by FastVideo Hao AI Lab with Nuva Lab. Exclusive preview on the Reactor API until 10.20.2026. • First and last frame conditioning • Audio input + strong dialogue • Up to 3 reference images... show more

reactor

9,646 subscribers

61,244 Aufrufe • vor 1 Tag •via X (Twitter)

Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

35 Kommentare

Profilbild von reactor

reactorvor 1 Tag

@haoailab @nuvalab Start building now:

Profilbild von Will Lin

Will Linvor 1 Tag

@MiniMax_AI @haoailab @nuvalab It's amazing to work with you guys and collab on this!

Profilbild von Harvey Michael Pratt

Harvey Michael Prattvor 1 Tag

@MiniMax_AI @haoailab @nuvalab never watching twitch again

Profilbild von Willem Helmet

Willem Helmetvor 1 Tag

@MiniMax_AI @haoailab @nuvalab THIS IS IT!! Amazing job to @haoailab and @nuvalab. Open source video models running faster than realtime are getting better and better every week!!

Profilbild von Alberto

Albertovor 1 Tag

@MiniMax_AI @haoailab @nuvalab

Profilbild von Will (World Model 世界模型)

Will (World Model 世界模型)vor 1 Tag

@MiniMax_AI @haoailab @nuvalab LFG

Profilbild von Cris Lenta

Cris Lentavor 1 Tag

@MiniMax_AI @haoailab @nuvalab crazy model! things are moving so fast soon we'll simulate everything, on every modality

Profilbild von Leanna Ren

Leanna Renvor 1 Tag

@MiniMax_AI @haoailab @nuvalab 🙌🫶

Profilbild von Ross Campbell

Ross Campbellvor 1 Tag

@MiniMax_AI @haoailab @nuvalab It just keeps coming! Big congrats @reactorworld & crew on this latest launch. Insane what we can build with real-time models now.

Profilbild von austin

austinvor 1 Tag

@MiniMax_AI @haoailab @nuvalab 🔥 🔥

Profilbild von Shahbuland

Shahbulandvor 1 Tag

@MiniMax_AI @haoailab @nuvalab no 480p for lower latency? 🥺

Profilbild von Ahmed Ahres

Ahmed Ahresvor 1 Tag

@MiniMax_AI @haoailab @nuvalab I AM SO EXCITED ABOUT THIS MODEL

Profilbild von Zhumazhan Balapanov

Zhumazhan Balapanovvor 1 Tag

@MiniMax_AI @haoailab @nuvalab

Profilbild von Nicholas H

Nicholas Hvor 1 Tag

@MiniMax_AI @haoailab @nuvalab So many cool ideas to be made with this

Profilbild von Bryce Schmidtchen

Bryce Schmidtchenvor 1 Tag

@MiniMax_AI @haoailab @nuvalab let's gooooo!

Profilbild von Abel Dagne

Abel Dagnevor 1 Tag

@MiniMax_AI @haoailab @nuvalab This is great keep killing it!!

Profilbild von lost in latency

lost in latencyvor 1 Tag

@MiniMax_AI @haoailab @nuvalab lets goooo 🔥🔥

Profilbild von Hermes ᯅ

Hermes ᯅvor 1 Tag

@MiniMax_AI @haoailab @nuvalab Wow this looks incredibly realistic. love the hand over the cam at the end. i dont think ive seen that before. Cant wait to try this!

Profilbild von Datz Daito

Datz Daitovor 1 Tag

@MiniMax_AI @haoailab @nuvalab this is huge lots to build with this

Profilbild von Behfar

Behfarvor 1 Tag

@MiniMax_AI @haoailab @nuvalab LFG!

Profilbild von Kevin Fischer

Kevin Fischervor 1 Tag

@MiniMax_AI @haoailab @nuvalab 🔥

Profilbild von Aryan

Aryanvor 1 Tag

@MiniMax_AI @haoailab @nuvalab

Profilbild von Davide Locatelli

Davide Locatellivor 1 Tag

@MiniMax_AI @haoailab @nuvalab Let's go team! The model is incredible

Profilbild von Zico

Zicovor 1 Tag

@MiniMax_AI @haoailab @nuvalab Let’s rock FastH3-Omni with Agora

Profilbild von Anshul Dhawan

Anshul Dhawanvor 1 Tag

@MiniMax_AI @haoailab @nuvalab Damn! This is quite impressive !!

Profilbild von Chewy

Chewyvor 1 Tag

@MiniMax_AI @haoailab @nuvalab legends, LFGGGGGGGGGGG 🔥🔥🔥🔥

Profilbild von pedro

pedrovor 1 Tag

@MiniMax_AI @haoailab @nuvalab can't wait to try this out!!

Profilbild von 安叫兽|Bird🕊️ 🔶 BNB

安叫兽|Bird🕊️ 🔶 BNBvor 1 Tag

@MiniMax_AI @haoailab @nuvalab 首尾帧都能控，中间还会乱跑吗？

Profilbild von Noam Naumovsky

Noam Naumovskyvor 1 Tag

@MiniMax_AI @haoailab @nuvalab First and last frame conditioning plus audio input in one model is the combo I've wanted for dialogue scenes. Does the lip sync hold when the last frame forces a different head pose than the audio would naturally lead to?

Profilbild von AJ

AJvor 1 Tag

@MiniMax_AI @haoailab @nuvalab MiniMax H3 keeps getting faster.

Profilbild von Picatrix Picori

Picatrix Picorivor 1 Tag

@MiniMax_AI @haoailab @nuvalab looks amazing, is almost as procedular generation, that ideal is closer than ever, and is amazing, good work

Profilbild von SRS

SRSvor 1 Tag

@MiniMax_AI @haoailab @nuvalab @grok what's the cost of the hosted API for this

Profilbild von DΞV

DΞVvor 1 Tag

@MiniMax_AI @haoailab @nuvalab Awesome!

Profilbild von jie.yao

jie.yaovor 1 Tag

@MiniMax_AI @haoailab @nuvalab @grok 配置需求？

Profilbild von Lady Bee

Lady Beevor 1 Tag

@MiniMax_AI @haoailab @nuvalab Can't wait to try this out

Ähnliche Videos

🚀 FastH3 on Reactor just got an upgrade, thanks to FastVideo Hao AI Lab. Stream 720p with better audio and dialogue, sharper detail in high-motion scenes, and more consistent faces from frame to frame, all at the same speed. Get started now:

🚀 FastH3 on Reactor just got an upgrade, thanks to FastVideo Hao AI Lab. Stream 720p with better audio and dialogue, sharper detail in high-motion scenes, and more consistent faces from frame to frame, all at the same speed. Get started now:

reactor

421,895 Aufrufe • vor 29 Tagen

🚀 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

2,910,113 Aufrufe • vor 1 Monat

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

776,139 Aufrufe • vor 1 Monat

At Reactor we ❤️ open-source. We teamed up with Hao AI Lab to ship an infinite live stream powered by FastVideo’s FastH3: And we’re open-sourcing everything!

At Reactor we ❤️ open-source. We teamed up with Hao AI Lab to ship an infinite live stream powered by FastVideo’s FastH3: And we’re open-sourcing everything!

reactor

171,263 Aufrufe • vor 1 Monat

Trick with Seedance 2 Omni ref on Runway • First clip text to video or your ref images. • Upload the first clip as your reference and prompt "Continue from the last frame of the input video keeping the character and environment consistent" + (extend your story)

Trick with Seedance 2 Omni ref on Runway • First clip text to video or your ref images. • Upload the first clip as your reference and prompt "Continue from the last frame of the input video keeping the character and environment consistent" + (extend your story)

madpencil_

14,312 Aufrufe • vor 4 Monaten

Today, we launch P-Video-2-Pro, based on MiniMax H3: The best quality. The best speed. Text or image in. Video and audio out. • 𝗜𝗻𝗽𝘂𝘁: Text or first-frame image, with optional last-frame conditioning • 𝗦𝗽𝗲𝗲𝗱: ~2.0s for a 5s clip at 480p · ~4.3s at 768p in Speed mode • 𝗣𝗿𝗶𝗰𝗶𝗻𝗴: From $0.02/s Speed · $0.04/s Quality • 𝗠𝗼𝗱𝗲𝘀: Speed or Quality • 𝗖𝗼𝗻𝘁𝗿𝗼𝗹: First and last frame, seed, aspect ratio, and prompt upsampling with Off, Turbo, or Max Available via our inference partners Replicate, Cloudflare, each::labs, Scenario, Tellers, WaveSpeedAI, Wiro AI — Ship AI Faster, Runware, and Together AI Validated by our benchmark partners Datapoint AI, Rapidata, and Design Arena. Benchmarks to be released soon 👀 👉 Free Playground: 📚 Model docs: 🧩 API:

Today, we launch P-Video-2-Pro, based on MiniMax H3: The best quality. The best speed. Text or image in. Video and audio out. • 𝗜𝗻𝗽𝘂𝘁: Text or first-frame image, with optional last-frame conditioning • 𝗦𝗽𝗲𝗲𝗱: ~2.0s for a 5s clip at 480p · ~4.3s at 768p in Speed mode • 𝗣𝗿𝗶𝗰𝗶𝗻𝗴: From $0.02/s Speed · $0.04/s Quality • 𝗠𝗼𝗱𝗲𝘀: Speed or Quality • 𝗖𝗼𝗻𝘁𝗿𝗼𝗹: First and last frame, seed, aspect ratio, and prompt upsampling with Off, Turbo, or Max Available via our inference partners Replicate, Cloudflare, each::labs, Scenario, Tellers, WaveSpeedAI, Wiro AI — Ship AI Faster, Runware, and Together AI Validated by our benchmark partners Datapoint AI, Rapidata, and Design Arena. Benchmarks to be released soon 👀 👉 Free Playground: 📚 Model docs: 🧩 API:

Pruna AI

103,327 Aufrufe • vor 27 Tagen

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

235,022 Aufrufe • vor 2 Monaten

We are releasing Ultramarine 1 Flash, a frontier-class model built for knowledge work. It is open-source and achieves similar performance to Fable 5, while being 60x cheaper. It was post-trained by a team of 5 for ~$300k all-in. Available on API now, with weights releasing in 2 weeks.

We are releasing Ultramarine 1 Flash, a frontier-class model built for knowledge work. It is open-source and achieves similar performance to Fable 5, while being 60x cheaper. It was post-trained by a team of 5 for ~$300k all-in. Available on API now, with weights releasing in 2 weeks.

Daanish Khazi

1,245,700 Aufrufe • vor 20 Stunden

Today we're announcing Base Labs, a dedicated research organization focused on advancing open-source AI. We believe in a healthy, open frontier model ecosystem. To enable this, we are working on: - Blue-sky research on continual learning, the science of RL, and how models learn across their full lifecycle, with every experiment and recipe shared openly. - The BaseHub Data Foundry: the highest-quality open RL environments, training data, and real-world benchmarks, built for anyone to train and benchmark on. - Post-post training: taking open-source models and making them better, safer, and more aligned through continual post-training, built on our research, and deployed with our frontier safety stack so organizations can use open-source models with confidence. - Making models cheaper and more performant through our model performance research. This is a mission-driven research effort, not a commercial product. We believe the health of the open-source AI ecosystem matters and that the best way to advance it is to do science in the open. We’re hiring engineers, researchers, and research fellows to advance this mission.

Today we're announcing Base Labs, a dedicated research organization focused on advancing open-source AI. We believe in a healthy, open frontier model ecosystem. To enable this, we are working on: - Blue-sky research on continual learning, the science of RL, and how models learn across their full lifecycle, with every experiment and recipe shared openly. - The BaseHub Data Foundry: the highest-quality open RL environments, training data, and real-world benchmarks, built for anyone to train and benchmark on. - Post-post training: taking open-source models and making them better, safer, and more aligned through continual post-training, built on our research, and deployed with our frontier safety stack so organizations can use open-source models with confidence. - Making models cheaper and more performant through our model performance research. This is a mission-driven research effort, not a commercial product. We believe the health of the open-source AI ecosystem matters and that the best way to advance it is to do science in the open. We’re hiring engineers, researchers, and research fellows to advance this mission.

Base Labs

244,827 Aufrufe • vor 1 Monat

fal head of engineering batuhan the fal guy reveals how reinforcement learning turned H3 Max into a frontier video model that generates 5 seconds of video in under 3 seconds, down from nearly 2 minutes: "It's probably the only frontier video model from a quality and output and adherence perspective that can generate videos in real time." "We took this open source base MiniMax H3 video model, what we wanted to do was not just make it faster, but improve its quality ahead of anything else by implementing reinforcement learning for verifiable concepts like video editing and prompt adherence." "We were able to get the model from 120 seconds for a 5-second video generation, almost 2 minutes, to under 3 seconds for a 5-second video generation. Almost double real time, while improving its quality ahead of the open source version and ahead of many frontier closed source models." fal

fal head of engineering batuhan the fal guy reveals how reinforcement learning turned H3 Max into a frontier video model that generates 5 seconds of video in under 3 seconds, down from nearly 2 minutes: "It's probably the only frontier video model from a quality and output and adherence perspective that can generate videos in real time." "We took this open source base MiniMax H3 video model, what we wanted to do was not just make it faster, but improve its quality ahead of anything else by implementing reinforcement learning for verifiable concepts like video editing and prompt adherence." "We were able to get the model from 120 seconds for a 5-second video generation, almost 2 minutes, to under 3 seconds for a 5-second video generation. Almost double real time, while improving its quality ahead of the open source version and ahead of many frontier closed source models." fal

MTS

31,444 Aufrufe • vor 29 Tagen

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 Aufrufe • vor 2 Monaten

We got attacked by secret unreleased proprietary models and defended ourselves with an open model, more precisely the NVIDIA quantized version of GLM 5.2 coming from Z.ai. Banning any open model would hurt first cyber security defenders, startups, small companies, researchers and everyone who's not a frontier lab and need on-prem affordable controlable models to compete and protect themselves. Let's not do that!

We got attacked by secret unreleased proprietary models and defended ourselves with an open model, more precisely the NVIDIA quantized version of GLM 5.2 coming from Z.ai. Banning any open model would hurt first cyber security defenders, startups, small companies, researchers and everyone who's not a frontier lab and need on-prem affordable controlable models to compete and protect themselves. Let's not do that!

clem 🤗

395,866 Aufrufe • vor 2 Monaten

Last week’s Signal Lab Art Event brought in some outstanding work from the community.🔥 Thank you to everyone who posted, shared, and helped keep ⁠signal-lab active with high-quality OptimAI-focused art. The consistency, creativity, and effort have been genuinely impressive. The event is still running for the next two weeks, so keep creating and keep posting. This week, we’re adding one more way to earn the Signal Conduit role: If your OptimAI art post on X gets liked or commented on by our official OptimAI account, reach out OptimAI Discord - share a screenshot in ⁠signal-lab for verification. Once confirmed, we’ll grant the Signal Conduit role. Keep showing up. Keep building. Keep the signal strong.

Last week’s Signal Lab Art Event brought in some outstanding work from the community.🔥 Thank you to everyone who posted, shared, and helped keep ⁠signal-lab active with high-quality OptimAI-focused art. The consistency, creativity, and effort have been genuinely impressive. The event is still running for the next two weeks, so keep creating and keep posting. This week, we’re adding one more way to earn the Signal Conduit role: If your OptimAI art post on X gets liked or commented on by our official OptimAI account, reach out OptimAI Discord - share a screenshot in ⁠signal-lab for verification. Once confirmed, we’ll grant the Signal Conduit role. Keep showing up. Keep building. Keep the signal strong.

OptimAI Network

12,985 Aufrufe • vor 4 Monaten

Introducing Entelligence AI Model Router, dynamic turn based routing trained on engineering tasks that cuts costs by over 50% Automatically route every coding turn to the model with the best balance of quality, latency, and cost. Escalate to frontier models when they’re actually needed Balanced mode reduces spend by 46% per session Eco mode helps teams save > 76%

Introducing Entelligence AI Model Router, dynamic turn based routing trained on engineering tasks that cuts costs by over 50% Automatically route every coding turn to the model with the best balance of quality, latency, and cost. Escalate to frontier models when they’re actually needed Balanced mode reduces spend by 46% per session Eco mode helps teams save > 76%

Aiswarya Sankar

87,211 Aufrufe • vor 3 Monaten

When will MiniMax have a Fable level model? Olive Song, research lead at MiniMax (official), joins The Bench to answer that question, plus M3, open source models closing the gap on Vibe Code Bench, and the truth about 996 culture. Full episode out now! 7:19 – Inside MiniMax's research culture: AI agents tracking papers since early last year 18:01- The headline of M3: native multimodality and one million tokens of context 21:10- The bottleneck of building models is people, not compute 22:48 – Does MiniMax work 996? 25:47 - Olive's prediction and the 30 point gap on Vibe Code Bench 32:02- Model capabilities Olive is most excited about 32:35- The lab Olive most respects outside of MiniMax 36:24- Will more labs go open source a year from now?

When will MiniMax have a Fable level model? Olive Song, research lead at MiniMax (official), joins The Bench to answer that question, plus M3, open source models closing the gap on Vibe Code Bench, and the truth about 996 culture. Full episode out now! 7:19 – Inside MiniMax's research culture: AI agents tracking papers since early last year 18:01- The headline of M3: native multimodality and one million tokens of context 21:10- The bottleneck of building models is people, not compute 22:48 – Does MiniMax work 996? 25:47 - Olive's prediction and the 30 point gap on Vibe Code Bench 32:02- Model capabilities Olive is most excited about 32:35- The lab Olive most respects outside of MiniMax 36:24- Will more labs go open source a year from now?

Vals AI

49,462 Aufrufe • vor 2 Monaten

P-Video-2-Pro now has a Cost mode! Get the same output quality as Speed mode, now starting from just $0.01/s. Optimised for cost when generation time matters less. And for launch, it’s 50% off until October 13! • 𝗜𝗻𝗽𝘂𝘁: Text or first-frame image, with optional last-frame conditioning • 𝗗𝘂𝗿𝗮𝘁𝗶𝗼𝗻: 5–15s with generated audio • 𝗣𝗿𝗶𝗰𝗶𝗻𝗴: $0.01/s at 480p · $0.025/s at 768p • 𝗖𝗼𝗻𝘁𝗿𝗼𝗹: First + last frame, seed, aspect ratio, and prompt upsampling Three modes: Cost, Speed, Quality. Pick the tradeoff that fits your workflow. Available via our inference partners Cloudflare, Scenario, Replicate, Wiro AI — Ship AI Faster, Tellers, each::labs, Eden AI, Runware, WaveSpeedAI, inference shell, Together AI, and Prodia. Validated by our benchmark partners Datapoint AI, Rapidata, and Design Arena. 📚 Model docs: 🧩 API:

P-Video-2-Pro now has a Cost mode! Get the same output quality as Speed mode, now starting from just $0.01/s. Optimised for cost when generation time matters less. And for launch, it’s 50% off until October 13! • 𝗜𝗻𝗽𝘂𝘁: Text or first-frame image, with optional last-frame conditioning • 𝗗𝘂𝗿𝗮𝘁𝗶𝗼𝗻: 5–15s with generated audio • 𝗣𝗿𝗶𝗰𝗶𝗻𝗴: $0.01/s at 480p · $0.025/s at 768p • 𝗖𝗼𝗻𝘁𝗿𝗼𝗹: First + last frame, seed, aspect ratio, and prompt upsampling Three modes: Cost, Speed, Quality. Pick the tradeoff that fits your workflow. Available via our inference partners Cloudflare, Scenario, Replicate, Wiro AI — Ship AI Faster, Tellers, each::labs, Eden AI, Runware, WaveSpeedAI, inference shell, Together AI, and Prodia. Validated by our benchmark partners Datapoint AI, Rapidata, and Design Arena. 📚 Model docs: 🧩 API:

Pruna AI

26,955 Aufrufe • vor 15 Tagen

I'm thrilled to announce the launch of ⚡️Flash Diffusion from Jasper! Earlier this year, with our acquisition of Clipdrop, we launched the Jasper AI Research Lab in Paris. Today, we are excited to release our first piece of groundbreaking research: the open-source distillation method, "Flash Diffusion". Flash Diffusion accelerates inference by 500%, reduces computing costs, and produces higher-quality image outputs. Dive into the details and discover how Flash Diffusion is set to revolutionize the field of AI and image synthesis. Read all about it here: Try a demo on Hugging Face:

I'm thrilled to announce the launch of ⚡️Flash Diffusion from Jasper! Earlier this year, with our acquisition of Clipdrop, we launched the Jasper AI Research Lab in Paris. Today, we are excited to release our first piece of groundbreaking research: the open-source distillation method, "Flash Diffusion". Flash Diffusion accelerates inference by 500%, reduces computing costs, and produces higher-quality image outputs. Dive into the details and discover how Flash Diffusion is set to revolutionize the field of AI and image synthesis. Read all about it here: Try a demo on Hugging Face:

Timothy Young

10,180 Aufrufe • vor 2 Jahren

🤝 Arcee.ai, an American AI lab, built its frontier open model family on NVIDIA Blackwell Ultra. Its flagship MoE model, Trinity-Large-Thinking, was RL post-trained using NVIDIA NeMo open libraries. Arcee optimized agentic model inference with NVIDIA Dynamo and vLLM, along with NVIDIA accelerated networking, to deliver low token cost, achieving: ✅ 3T+ tokens served on OpenRouter in its first two months ✅ $0.90 per 1M output tokens ✅ 2nd on PinchBench for open agentic models Explore Arcee's open models, powered by NVIDIA ➡️

🤝 Arcee.ai, an American AI lab, built its frontier open model family on NVIDIA Blackwell Ultra. Its flagship MoE model, Trinity-Large-Thinking, was RL post-trained using NVIDIA NeMo open libraries. Arcee optimized agentic model inference with NVIDIA Dynamo and vLLM, along with NVIDIA accelerated networking, to deliver low token cost, achieving: ✅ 3T+ tokens served on OpenRouter in its first two months ✅ $0.90 per 1M output tokens ✅ 2nd on PinchBench for open agentic models Explore Arcee's open models, powered by NVIDIA ➡️

NVIDIA AI Infrastructure

27,377 Aufrufe • vor 3 Monaten

Wendy's Wonderful Dreamworld, Episode 3: Previously Wendy learned that her friend Kavi is being held prisoner by his mother Queen Aramati in the Black Rose Maze for the crime of bringing Wendy into the Dreamworld. Now Wendy is wandering the surreal landscape beyond the mansion to rescue Kavi from his punishment...but Queen Arimati is determined to never let her reach the maze! Made with Midjourney, Seedream, Nano Banana Pro, GPT images + Seedance (on Dreamina AI #dreaminacpp) and MiniMax H3 ( MiniMax Design (H3) ) videos + Seed Audio + Elevenlabs and Udio and Suno music/sound effects/voices.

Wendy's Wonderful Dreamworld, Episode 3: Previously Wendy learned that her friend Kavi is being held prisoner by his mother Queen Aramati in the Black Rose Maze for the crime of bringing Wendy into the Dreamworld. Now Wendy is wandering the surreal landscape beyond the mansion to rescue Kavi from his punishment...but Queen Arimati is determined to never let her reach the maze! Made with Midjourney, Seedream, Nano Banana Pro, GPT images + Seedance (on Dreamina AI #dreaminacpp) and MiniMax H3 ( MiniMax Design (H3) ) videos + Seed Audio + Elevenlabs and Udio and Suno music/sound effects/voices.

Christopher Gwinn | Grindhouse Glitch

20,128 Aufrufe • vor 11 Tagen

Local Reachy Mini conversations wireless looks like magic! You can bring your friend around the house and get WOW effect from anyone! 🔥 Thanks Andi Marafioti for the blog post on how to set this up: Open-source Realtime API powered by llama.cpp: Parakeet -> Gemma 4 E4B -> Qwen3TTS. Just perfect on M5! Pictures, audio and content remain local and private! Next step adding some tools to search on the web or even better interfacing with my Hermes Agent! 🔥

Local Reachy Mini conversations wireless looks like magic! You can bring your friend around the house and get WOW effect from anyone! 🔥 Thanks Andi Marafioti for the blog post on how to set this up: Open-source Realtime API powered by llama.cpp: Parakeet -> Gemma 4 E4B -> Qwen3TTS. Just perfect on M5! Pictures, audio and content remain local and private! Next step adding some tools to search on the web or even better interfacing with my Hermes Agent! 🔥

Ivan Fioravanti ᯅ

22,458 Aufrufe • vor 4 Monaten