🔥 SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer

💡 The paper introduces SANA-Video, a small diffusion model designed for efficient video generation. The problem addressed is the high cost and slow speed of existing video generation models. To solve this, the authors propose two core designs: Linear DiT, which leverages linear attention as the core operation, and a constant-memory KV cache for block linear attention. This cache provides global context at a fixed memory cost, eliminating the need for a traditional KV cache and enabling efficient long video generation.

The method used is a block-wise autoregressive approach for long video generation, which employs a constant-memory state derived from the cumulative properties of linear attention. The authors also explore effective data filters and model training strategies, which narrow the training cost to 12 days on 64 H100 GPUs, a significant reduction compared to other models.

The results show that SANA-Video achieves competitive performance compared to modern state-of-the-art small diffusion models, while being 16 times faster in measured latency. The model can generate high-resolution, high-quality videos up to 720x1280 resolution and minute-length duration at a remarkably fast speed. Additionally, SANA-Video can be deployed on RTX 5090 GPUs, accelerating the inference speed of generating a 5-second 720p video from 71 seconds to 29 seconds, a 2.4 times speedup. Overall, SANA-Video enables low-cost, high-quality video generation, making it a significant contribution to the field of video generation.

📅 Published on Sep 29, 2025

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2509.24695
• PDF: https://arxiv.org/pdf/2509.24695
• Project Page: https://nvlabs.github.io/Sana/Video

🤖 Models citing this paper:
• https://huggingface.co/Efficient-Large-Model/SANA-Video_2B_720p
• https://huggingface.co/Efficient-Large-Model/SANA-Video_2B_480p
• https://huggingface.co/Efficient-Large-Model/SANA-Video_2B_480p_diffusers

🚀 Spaces citing this paper:
• https://huggingface.co/spaces/helenai/check-optimum-intel-support

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://xn--r1a.website/PaperNexus

#VideoGenerationModels #DiffusionTransformer #BlockLinearAttention #EfficientVideoProcessing #AutoregressiveVideoGeneration

🔥 LongCat-Video Technical Report

💡 The paper introduces LongCat-Video, a 13.6 billion parameter video generation model based on the Diffusion Transformer framework. The model is designed to generate high-quality long videos efficiently, which is a crucial step towards creating world models. LongCat-Video has a unified architecture that can perform multiple tasks, including text-to-video, image-to-video, and video continuation, using a single model.

The model achieves efficient long video generation through a coarse-to-fine generation strategy and block sparse attention, allowing it to generate 720p, 30fps videos within minutes. The coarse-to-fine generation strategy works by gradually increasing the resolution and detail of the video, both in terms of time and space. Block sparse attention is a technique that reduces the computational cost of the model by only attending to certain parts of the input data.

The model was trained using a multi-reward reinforcement learning from human feedback approach, which enables it to achieve performance comparable to state-of-the-art models. The use of multi-reward reinforcement learning from human feedback allows the model to learn from human evaluators and improve its performance over time.

The results show that LongCat-Video excels in generating high-quality long videos, maintaining temporal coherence and quality even in videos that are several minutes long. The model's efficiency and performance make it a significant contribution to the field of video generation, and the fact that the code and model weights are publicly available will accelerate progress in this area. Overall, LongCat-Video is a foundational model that takes an important step towards creating world models, which are complex models that can simulate and generate realistic videos and other types of data.

📅 Published on Oct 25, 2025

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2510.22200
• PDF: https://arxiv.org/pdf/2510.22200

🤖 Models citing this paper:
• https://huggingface.co/meituan-longcat/LongCat-Video
• https://huggingface.co/Nishant2414/LongCat-Video
• https://huggingface.co/fjkane/LongCat-Video-bf16

🚀 Spaces citing this paper:
• https://huggingface.co/spaces/cpuai/LongCat-Video-Avatar
• https://huggingface.co/spaces/multimodalart/LongCat-Video
• https://huggingface.co/spaces/armaishere/meituan-longcat-LongCat-Video

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://xn--r1a.website/PaperNexus

#VideoGenerationModels #DiffusionTransformer #LongVideoSynthesis #TextToVideoSynthesis #ImageToVideoGeneration

🔥 WavTTS: Towards High-Quality Zero-Shot TTS via Direct Raw Waveform Modeling

💡 The paper introduces WavTTS, a novel text-to-speech model that directly generates raw waveforms, addressing the limitations of existing latent-space diffusion models. Current state-of-the-art models operate on compressed representations such as mel-spectrograms or VAE latents, which leads to information loss and non-end-to-end training. Directly modeling raw waveforms is theoretically beneficial but has been underexplored due to the long sequence length of audio signals.

To overcome this challenge, WavTTS employs a flow matching approach with a Diffusion Transformer architecture and a simple patchification strategy to directly model speech waveforms. The model also incorporates multi-scale mel-spectrogram supervision to provide perceptual guidance during training. Additionally, the authors investigate the impact of prediction targets and noise scheduling in waveform diffusion and develop an effective schedule design to improve generation quality.

The results show that WavTTS significantly narrows the performance gap with latent-space generative models and outperforms previous end-to-end speech generation models. Evaluations on open-source benchmarks demonstrate that WavTTS closely approaches the performance of current state-of-the-art latent generative zero-shot text-to-speech models. The findings of this paper demonstrate the feasibility of scaling diffusion-based text-to-speech models directly in the waveform space, opening a new direction for end-to-end speech generation.

📅 Published on Jun 2

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2606.03455
• PDF: https://arxiv.org/pdf/2606.03455
• Project Page: https://wavtts.github.io/

🤖 Models citing this paper:
• https://huggingface.co/worstchan/WavTTS
• https://huggingface.co/drbaph/WavTTS

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://xn--r1a.website/PaperNexus

#TextToSpeechSynthesis #RawWaveformModeling #DiffusionTransformer #ZeroShotTTS #SpeechSynthesisTechniques