Loading video...

Video Failed to Load

Go Home

NVIDIA just released AnyFlow on Hugging Face The first any-step video diffusion model that generates high-quality text-to-video with any inference budget - 4 steps or 50, quality scales smoothly without degradation.

HuggingPapers's profile picture

DailyPapers

21,053 subscribers

41,764 views • 4 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

4 Comments

DailyPapers's profile picture
DailyPapers4 months ago

Model: Project page:

Mian Khan's profile picture
Mian Khan4 months ago

@_akhaliq Thanks for the update

Shantun Singh Parmar's profile picture
Shantun Singh Parmar4 months ago

Nvidia is literally changing the game for video generation speed now.

Kekko D’Amato's profile picture
Kekko D’Amato4 months ago

The flexibility on inference steps is what makes this genuinely useful in production — you can tune speed vs quality at runtime rather than committing at architecture design time. Curious if anyone's benchmarked wall-clock diff between 4 and 50 steps on consumer hardware yet.

Related Videos

Self-Forcing++ for minute-scale video generation ByteDance's new method generates high-quality videos up to 4 min 15 sec! It scales diffusion models without long-video teachers or retraining, preserving fidelity and consistency.
1:40

Self-Forcing++ for minute-scale video generation ByteDance's new method generates high-quality videos up to 4 min 15 sec! It scales diffusion models without long-video teachers or retraining, preserving fidelity and consistency.

DailyPapers

17,744 views • 11 months ago

LTX-Video new text-to-video model generates stunning, high-quality videos faster than real-time—5 seconds of 24fps video at 768x512 in just 4 seconds on an Nvidia H100 open code & weights
0:26

LTX-Video new text-to-video model generates stunning, high-quality videos faster than real-time—5 seconds of 24fps video at 768x512 in just 4 seconds on an Nvidia H100 open code & weights

AK

51,498 views • 1 year ago

LFM2-Audio just dropped! It's a 1.5B model that understands and generates both text and audio Inference 10x faster + quality on par with models 10x larger Available today on Hugging Face and our playground 🥳
2:00

LFM2-Audio just dropped! It's a 1.5B model that understands and generates both text and audio Inference 10x faster + quality on par with models 10x larger Available today on Hugging Face and our playground 🥳

Maxime Labonne

85,053 views • 11 months ago

Excited to announce LTX-Video! Our new text-to-video model generates stunning, high-quality videos faster than real-time—5 seconds of 24fps video at 768x512 in just 4 seconds on an Nvidia H100! ⚡ We’re open-sourcing the code & weights. Check out the results 🎥👇
0:26

Excited to announce LTX-Video! Our new text-to-video model generates stunning, high-quality videos faster than real-time—5 seconds of 24fps video at 768x512 in just 4 seconds on an Nvidia H100! ⚡ We’re open-sourcing the code & weights. Check out the results 🎥👇

Yoav HaCohen

50,374 views • 1 year ago

Announcing Diffusion Forcing Transformer (DFoT), our new video diffusion algorithm that generates ultra-long videos of 800+ frames. DFoT enables History Guidance, a simple add-on to any existing video diffusion models for a quality boost. Website: (1/7)
0:36

Announcing Diffusion Forcing Transformer (DFoT), our new video diffusion algorithm that generates ultra-long videos of 800+ frames. DFoT enables History Guidance, a simple add-on to any existing video diffusion models for a quality boost. Website: (1/7)

Boyuan Chen

175,996 views • 1 year ago

This new AI model for anime is insane! It stylizes any video in minutes with high quality. Step-by-step tutorial right here 🧵👇
0:41

This new AI model for anime is insane! It stylizes any video in minutes with high quality. Step-by-step tutorial right here 🧵👇

TechHalla

41,339 views • 1 year ago

Collaborative Video Diffusion Consistent Multi-video Generation with Camera Control Research on video generation has recently made tremendous progress, enabling high-quality videos to be generated from text prompts or images. Adding control to the video generation
2:16

Collaborative Video Diffusion Consistent Multi-video Generation with Camera Control Research on video generation has recently made tremendous progress, enabling high-quality videos to be generated from text prompts or images. Adding control to the video generation

AK

29,278 views • 2 years ago

TokenFlow: Consistent Diffusion Features for Consistent Video Editing paper page: The generative AI revolution has recently expanded to videos. Nevertheless, current state-of-the-art video models are still lagging behind image models in terms of visual quality and user control over the generated content. In this work, we present a framework that harnesses the power of a text-to-image diffusion model for the task of text-driven video editing. Specifically, given a source video and a target text-prompt, our method generates a high-quality video that adheres to the target text, while preserving the spatial layout and motion of the input video. Our method is based on a key observation that consistency in the edited video can be obtained by enforcing consistency in the diffusion feature space. We achieve this by explicitly propagating diffusion features based on inter-frame correspondences, readily available in the model. Thus, our framework does not require any training or fine-tuning, and can work in conjunction with any off-the-shelf text-to-image editing method. We demonstrate state-of-the-art editing results on a variety of real-world videos.
0:36

TokenFlow: Consistent Diffusion Features for Consistent Video Editing paper page: The generative AI revolution has recently expanded to videos. Nevertheless, current state-of-the-art video models are still lagging behind image models in terms of visual quality and user control over the generated content. In this work, we present a framework that harnesses the power of a text-to-image diffusion model for the task of text-driven video editing. Specifically, given a source video and a target text-prompt, our method generates a high-quality video that adheres to the target text, while preserving the spatial layout and motion of the input video. Our method is based on a key observation that consistency in the edited video can be obtained by enforcing consistency in the diffusion feature space. We achieve this by explicitly propagating diffusion features based on inter-frame correspondences, readily available in the model. Thus, our framework does not require any training or fine-tuning, and can work in conjunction with any off-the-shelf text-to-image editing method. We demonstrate state-of-the-art editing results on a variety of real-world videos.

AK

143,469 views • 3 years ago

Stability AI just dropped Stable Virtual Camera on Hugging Face a generalist diffusion model designed to address the exciting challenge of Novel View Synthesis (NVS). With just one or a few images, it allows you to create a smooth trajectory video from any viewpoint you desire.
1:00

Stability AI just dropped Stable Virtual Camera on Hugging Face a generalist diffusion model designed to address the exciting challenge of Novel View Synthesis (NVS). With just one or a few images, it allows you to create a smooth trajectory video from any viewpoint you desire.

AK

133,667 views • 1 year ago

ComfyUI MiniMax-H3 Audio Refine audio-only refinement. Makes high-quality audio on 4-step Turbo video by running extra denoising steps on the audio stream only - preserves video
0:30

ComfyUI MiniMax-H3 Audio Refine audio-only refinement. Makes high-quality audio on 4-step Turbo video by running extra denoising steps on the audio stream only - preserves video

Wildminder

15,139 views • 23 days ago

4x cost reduction in TTS inference with Tenstorrent! 11 NVIDIA L40S ran 550 simultaneous audio-stream at ~$100K. Now, 27 Tenstorrent P100 chips do the same at ~$27k. First production-grade TTS to match the cost of text tokens without degradation in audio quality. Hear it straight from the team that built it: Akshat Mandloi and Ranjith M S in the video below.
4:17

4x cost reduction in TTS inference with Tenstorrent! 11 NVIDIA L40S ran 550 simultaneous audio-stream at ~$100K. Now, 27 Tenstorrent P100 chips do the same at ~$27k. First production-grade TTS to match the cost of text tokens without degradation in audio quality. Hear it straight from the team that built it: Akshat Mandloi and Ranjith M S in the video below.

smallest.ai

22,584 views • 4 months ago

🚀 LongCat-Video Now Open-Source: Text/Image-to-Video + Video Continuation in One Model 🏆 Text/Image-to-Video Performance Hits Open-Source SOTA 🎬 Minutes-Long High-Quality Videos: No Color Drift/Quality Loss (Industry-Standout) ⚙ 13.6B Params | Strong Open-Source DiT-Based Unified Multitask Video Base Model ⚡ C2F Pipeline + Block Sparse Attention: 720p/30fps Video in Minutes 🤗 Open-Source Links: GitHub： Hugging Face： Project Page：
0:06

🚀 LongCat-Video Now Open-Source: Text/Image-to-Video + Video Continuation in One Model 🏆 Text/Image-to-Video Performance Hits Open-Source SOTA 🎬 Minutes-Long High-Quality Videos: No Color Drift/Quality Loss (Industry-Standout) ⚙ 13.6B Params | Strong Open-Source DiT-Based Unified Multitask Video Base Model ⚡ C2F Pipeline + Block Sparse Attention: 720p/30fps Video in Minutes 🤗 Open-Source Links: GitHub： Hugging Face： Project Page：

Meituan LongCat

43,828 views • 10 months ago

Open-source video generation is now faster than playback without compromising quality. Introducing Video Delta Net (VDN): hybrid attention for live text-to-video with near-lossless quality. VDN accelerates Minimax-H3 by 75 - 90 x, generating 14 seconds of 768p video in 11 seconds on 8× NVIDIA B200 GPUs. Checkpoints + training/inference code + Technical Blog ⬇️ (1/6)
1:09

Open-source video generation is now faster than playback without compromising quality. Introducing Video Delta Net (VDN): hybrid attention for live text-to-video with near-lossless quality. VDN accelerates Minimax-H3 by 75 - 90 x, generating 14 seconds of 768p video in 11 seconds on 8× NVIDIA B200 GPUs. Checkpoints + training/inference code + Technical Blog ⬇️ (1/6)

Haocheng Xi

436,348 views • 12 days ago

Topaz Labs - "We're launching Project Starlight: the first-ever diffusion model for video restoration. Enhance old, low-quality videos to stunning high-resolution. This is our biggest leap since Video AI was first launched."
0:46

Topaz Labs - "We're launching Project Starlight: the first-ever diffusion model for video restoration. Enhance old, low-quality videos to stunning high-resolution. This is our biggest leap since Video AI was first launched."

Chubby♨️

67,022 views • 1 year ago

MiniMax H3 Just Dropped on Lovart! 🔥 The world's #2 video model just landed on Lovart. Production-quality AI video at less than half the cost. •15s cinematic output with fluid, high-fidelity motion •15multimodal references: text, image, video & audio •Consistent characters, products, scenes & styles From Ads to MV to TVC, no more choosing between quality and cost.
0:21

MiniMax H3 Just Dropped on Lovart! 🔥 The world's #2 video model just landed on Lovart. Production-quality AI video at less than half the cost. •15s cinematic output with fluid, high-fidelity motion •15multimodal references: text, image, video & audio •Consistent characters, products, scenes & styles From Ads to MV to TVC, no more choosing between quality and cost.

LovartAI

241,649 views • 1 month ago

World meet #emuvideo For the past year, our team has been pushing on video generation. The result? Emu Video that generates high quality videos from text or images. SOTA performance vs. commercial products and academic papers. Check it out
1:29

World meet #emuvideo For the past year, our team has been pushing on video generation. The result? Emu Video that generates high quality videos from text or images. SOTA performance vs. commercial products and academic papers. Check it out

Ishan Misra

132,141 views • 2 years ago

Veo: our most capable video generation model is now available on Vertex AI in private preview! Developed by Google DeepMind, Veo generates high-quality videos based on text or image prompts in a range of cinematic & visual styles with exceptional speed →
0:25

Veo: our most capable video generation model is now available on Vertex AI in private preview! Developed by Google DeepMind, Veo generates high-quality videos based on text or image prompts in a range of cinematic & visual styles with exceptional speed →

Google Cloud

190,874 views • 1 year ago

Meet Gemini Omni, our new model that can create anything from any input, starting with video. With Gemini Omni, you can combine images, videos and text as inputs and generate high-quality videos grounded in Gemini's real-world knowledge. #GoogleIO
0:50

Meet Gemini Omni, our new model that can create anything from any input, starting with video. With Gemini Omni, you can combine images, videos and text as inputs and generate high-quality videos grounded in Gemini's real-world knowledge. #GoogleIO

Google Gemini

89,578 views • 3 months ago