Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

High-resolution image and video generation is hitting a wall because attention in DiTs scales quadratically with token count. But does every pixel need to be in full resolution? Introducing Foveated Diffusion: a new approach for efficient diffusion-based generation that allocates compute where it matters most. 1/7🧵

Gordon Wetzstein

5,295 subscribers

163,340 просмотров • 3 месяцев назад •via X (Twitter)

Искусство Здоровье и велнес Наука и технологии

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Selected as a best paper finalist at #CVPR2026: PixelDiT from NVIDIA Research In most image generation models, a pretrained autoencoder compresses the image before any diffusion happens, causing quality loss that accumulates across the entire pipeline. PixelDiT, or Pixel Diffusion Transformers, removes this step entirely. It's a single-stage model that learns the diffusion process directly in pixel space, end-to-end.

Selected as a best paper finalist at #CVPR2026: PixelDiT from NVIDIA Research In most image generation models, a pretrained autoencoder compresses the image before any diffusion happens, causing quality loss that accumulates across the entire pipeline. PixelDiT, or Pixel Diffusion Transformers, removes this step entirely. It's a single-stage model that learns the diffusion process directly in pixel space, end-to-end.

NVIDIA AI

27,833 просмотров • 1 месяц назад

Chop the gradients ✂️! We found that truncating decoder gradients in latent video diffusion to a fixed window allows us to finetune on videos with pixel-wise perceptual losses without running out of memory. Pixel losses have been essential for image generation and reconstruction, but until now, they haven't scaled to long-duration, high-resolution video diffusion due to recursive activation accumulation in causal decoders, leading to OOM during training 💥📉. Project: Video diffusion models can do a lot more 🚀 when you can backprop the decoder! Post-process neural rendered scenes, super-resolve videos, harmonize lighting in controlled synthetic driving scenes, and inpaint videos — all in a single step ⚡ with a quick finetune from a standard diffusion model.

Chop the gradients ✂️! We found that truncating decoder gradients in latent video diffusion to a fixed window allows us to finetune on videos with pixel-wise perceptual losses without running out of memory. Pixel losses have been essential for image generation and reconstruction, but until now, they haven't scaled to long-duration, high-resolution video diffusion due to recursive activation accumulation in causal decoders, leading to OOM during training 💥📉. Project: Video diffusion models can do a lot more 🚀 when you can backprop the decoder! Post-process neural rendered scenes, super-resolve videos, harmonize lighting in controlled synthetic driving scenes, and inpaint videos — all in a single step ⚡ with a quick finetune from a standard diffusion model.

Felix Heide

28,323 просмотров • 3 месяцев назад

NVIDIA just released a very impressive text-to-video paper. Video Latent Diffusion Models (Video LDMs) use a diffusion model in a compressed latent space to generate high-resolution videos. Here's a brief overview of how it works: 1. Pre-train image LDM on a dataset of images. 2. Turn the image LDM into a Video LDM by adding temporal layers to model video frames. 3. Fine-tune the Video LDM on encoded video sequences to create a video generator. 4. Temporally align diffusion model upsamplers to generate high-resolution videos. 5. Validate Video LDM on real driving videos of 512x1024 resolution, achieving state-of-the-art performance. 6. Apply the approach in creative content creation with text-to-video modeling. Paper: Project:

NVIDIA just released a very impressive text-to-video paper. Video Latent Diffusion Models (Video LDMs) use a diffusion model in a compressed latent space to generate high-resolution videos. Here's a brief overview of how it works: 1. Pre-train image LDM on a dataset of images. 2. Turn the image LDM into a Video LDM by adding temporal layers to model video frames. 3. Fine-tune the Video LDM on encoded video sequences to create a video generator. 4. Temporally align diffusion model upsamplers to generate high-resolution videos. 5. Validate Video LDM on real driving videos of 512x1024 resolution, achieving state-of-the-art performance. 6. Apply the approach in creative content creation with text-to-video modeling. Paper: Project:

Lior Alexander

158,553 просмотров • 3 лет назад

DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion TL;DR: Create 3/4DGS from Video Diffusion Note: Some first inference code released (not all yet). Contributions (cited): • We present DimensionX, a novel framework for generating photorealistic 3D and 4D scenes from only a single image using controllable video diffusion. • We propose ST-Director, which decouples the spatial and temporal priors in video diffusion models by learning (spatial and temporal) dimension-aware modules with our curated datasets. We further enhance the hybriddimension control with a training-free composition approach according to the essence of video diffusion denoising process. • To bridge the gap between video diffusion and real-world scenes, we design a trajectory-aware mechanism for 3D generation and an identity-preserving denoising approach for 4D generation, enabling more realistic and controllable scene synthesis. • Extensive experiments manifest that our DimensionX delivers superior performance in video, 3D, and 4D generation compared with baseline methods.

DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion TL;DR: Create 3/4DGS from Video Diffusion Note: Some first inference code released (not all yet). Contributions (cited): • We present DimensionX, a novel framework for generating photorealistic 3D and 4D scenes from only a single image using controllable video diffusion. • We propose ST-Director, which decouples the spatial and temporal priors in video diffusion models by learning (spatial and temporal) dimension-aware modules with our curated datasets. We further enhance the hybriddimension control with a training-free composition approach according to the essence of video diffusion denoising process. • To bridge the gap between video diffusion and real-world scenes, we design a trajectory-aware mechanism for 3D generation and an identity-preserving denoising approach for 4D generation, enabling more realistic and controllable scene synthesis. • Extensive experiments manifest that our DimensionX delivers superior performance in video, 3D, and 4D generation compared with baseline methods.

MrNeRF

17,039 просмотров • 1 год назад

Snap presents MoA Mixture-of-Attention for Subject-Context Disentanglement in Personalized Image Generation We introduce a new architecture for personalization of text-to-image diffusion models, coined Mixture-of-Attention (MoA). Inspired by the Mixture-of-Experts

Snap presents MoA Mixture-of-Attention for Subject-Context Disentanglement in Personalized Image Generation We introduce a new architecture for personalization of text-to-image diffusion models, coined Mixture-of-Attention (MoA). Inspired by the Mixture-of-Experts

AK

47,488 просмотров • 2 лет назад

🆕 Image super-resolution model just dropped! Superior results even with a single sampling step. 🔥InvSR: Arbitrary-steps Image Super-resolution via Diffusion Inversion.

🆕 Image super-resolution model just dropped! Superior results even with a single sampling step. 🔥InvSR: Arbitrary-steps Image Super-resolution via Diffusion Inversion.

Gradio

53,331 просмотров • 1 год назад

The era of ultra-high-resolution imaging has arrived. Modern image sensors exceeding 200 MP resolution are common in smartphones, with over 400 MP sensors under development. However, the large number of pixels poses significant challenges for acquisition and processing, especially on edge devices. Which pixels should be acquired, and when, for bandwidth-efficient imaging and perception? We introduce Policy-based Foveated Imaging and Perception, an on-device, real-time, predictive, and task-aware framework that dynamically allocates sensor resolution to prioritize important regions under specific perception objectives. This paper will be presented at #SIGGRAPH2026! [1/6]

The era of ultra-high-resolution imaging has arrived. Modern image sensors exceeding 200 MP resolution are common in smartphones, with over 400 MP sensors under development. However, the large number of pixels poses significant challenges for acquisition and processing, especially on edge devices. Which pixels should be acquired, and when, for bandwidth-efficient imaging and perception? We introduce Policy-based Foveated Imaging and Perception, an on-device, real-time, predictive, and task-aware framework that dynamically allocates sensor resolution to prioritize important regions under specific perception objectives. This paper will be presented at #SIGGRAPH2026! [1/6]

Gordon Wetzstein

18,310 просмотров • 1 месяц назад

🚨Announcing our #ICLR2025 Oral! 🔥Diffusion LMs are on the rise for parallel text generation! But unlike autoregressive LMs, they struggle with quality, fixed-length constraints & lack of KV caching. 🚀Introducing Block Diffusion—combining autoregressive and diffusion models for the best of both worlds! 👇1/7

🚨Announcing our #ICLR2025 Oral! 🔥Diffusion LMs are on the rise for parallel text generation! But unlike autoregressive LMs, they struggle with quality, fixed-length constraints & lack of KV caching. 🚀Introducing Block Diffusion—combining autoregressive and diffusion models for the best of both worlds! 👇1/7

Marianne Arriola

148,599 просмотров • 1 год назад

🚀 Introducing GenLit – Reformulating Single-Image Relighting as Video Generation! We leverage video diffusion models to perform realistic near-field relighting from just a single image—No explicit 3D reconstruction or ray tracing required! No intermediate graphics buffers, directly in the pixel space! 📄 Dive into the paper: 🎥 Project page & demos: 🛠 Code coming soon! #GenerativeAI #ComputerVision #Relighting #DiffusionModels #Graphics 🧵 1/5

🚀 Introducing GenLit – Reformulating Single-Image Relighting as Video Generation! We leverage video diffusion models to perform realistic near-field relighting from just a single image—No explicit 3D reconstruction or ray tracing required! No intermediate graphics buffers, directly in the pixel space! 📄 Dive into the paper: 🎥 Project page & demos: 🛠 Code coming soon! #GenerativeAI #ComputerVision #Relighting #DiffusionModels #Graphics 🧵 1/5

Haven Feng

22,442 просмотров • 1 год назад

Switti -- a new scale-wise transformer for text-to-image generation 🦾 🔥 Improved generation of fine-grained details. Outperforms existing T2I AR models and competes with state-of-the-art T2I diffusion models while being up to 7x faster.

Switti -- a new scale-wise transformer for text-to-image generation 🦾 🔥 Improved generation of fine-grained details. Outperforms existing T2I AR models and competes with state-of-the-art T2I diffusion models while being up to 7x faster.

Gradio

29,314 просмотров • 1 год назад

Introducing ⇆ Marigold-DC — our training-free zero-shot approach to monocular Depth Completion with guided diffusion! If you have ever wondered how else a long denoising diffusion schedule can be useful, we have an answer for you! Details 🧵

Introducing ⇆ Marigold-DC — our training-free zero-shot approach to monocular Depth Completion with guided diffusion! If you have ever wondered how else a long denoising diffusion schedule can be useful, we have an answer for you! Details 🧵

Anton Obukhov

39,295 просмотров • 1 год назад

Today, we're introducing Muse Image and Muse Video! 🖌️ Muse Image is an agentic image generation model with strong integrations with coding, search, and self-refinement! Muse Video is an early preview of our video generation efforts with strong audio and video generation abilities! Details below! 🧵👇

Today, we're introducing Muse Image and Muse Video! 🖌️ Muse Image is an agentic image generation model with strong integrations with coding, search, and self-refinement! Muse Video is an early preview of our video generation efforts with strong audio and video generation abilities! Details below! 🧵👇

Matt Deitke

51,442 просмотров • 5 дней назад

🎥 Video generation is hitting the memory wall. As videos get longer, the KV cache quietly explodes — and long-horizon consistency starts to break. We built Quant VideoGen: a training-free KV cache compression method for auto-regressive video diffusion. Instead of storing every KV in high precision, QVG exploits video’s spatiotemporal redundancy with semantic-aware smoothing + progressive residual quantization. 🚀 Up to 7× KV memory reduction ⚡ <4% overhead ✅ Strong long-video quality 🕹️ Deploy HYWorldPlay on your own RTX 5090 locally KV compression is becoming a core scaling primitive — not just for LLMs, but for video generation too. Paper: Code: (1/5)

🎥 Video generation is hitting the memory wall. As videos get longer, the KV cache quietly explodes — and long-horizon consistency starts to break. We built Quant VideoGen: a training-free KV cache compression method for auto-regressive video diffusion. Instead of storing every KV in high precision, QVG exploits video’s spatiotemporal redundancy with semantic-aware smoothing + progressive residual quantization. 🚀 Up to 7× KV memory reduction ⚡ <4% overhead ✅ Strong long-video quality 🕹️ Deploy HYWorldPlay on your own RTX 5090 locally KV compression is becoming a core scaling primitive — not just for LLMs, but for video generation too. Paper: Code: (1/5)

Haocheng Xi

64,557 просмотров • 2 месяцев назад

Excited to share our new work "AvatarPopUp"! "Instant 3D Human Avatar Generation using Image Diffusion Models" 💻 📄

Nikos Kolotouros

14,088 просмотров • 2 лет назад

Most recent diffusion language model research (that I’ve seen) seems to be using masking as the noising process. It looks like, however, most closed-source models (Google Gemini Diffusion and possibly Inception Labs’ Mercury) use a different noising process, where instead of masking tokens, they replace them with different tokens (either with a random token or a semantically similar token). I wondered how they were getting such high throughput with the latter noising process, since I believed that optimizing inference with KVCache approximation would be more difficult (for various reasons). I visualized this noising process with tiny-diffusion and compared it to normal unmasking, and was very surprised to see how fast the generation “settles” into a reasonable output, and then only slightly refines afterwards, requiring much fewer steps in total. Unmasking (where tokens are never remasked, the typical implementation) is inherently limited in generation speed by the fact that an increase in tokens decoded per step leads to more errors due to the mismatch between individual and marginal token probability distributions we sample from. The token replacement noising process seems to have a much different set of characteristics. Because we sample each token per step, every token makes “progress” towards the final output each iteration (in addition to *potentially* giving other tokens more information in future steps). Generally, masking has outperformed other noising processes, which is probably why most research focused on it (using smaller models). But the paper referred to in the retweet shows that random replacement as a noising process may scale better as model size increases. Big labs might have noticed these results much earlier (due to having drastically more training resources and being able to test larger models), which may explain the discrepancy in the choice of noising process. I’m gonna test this with larger models, since tiny-diffusion only has 10M parameters.

Most recent diffusion language model research (that I’ve seen) seems to be using masking as the noising process. It looks like, however, most closed-source models (Google Gemini Diffusion and possibly Inception Labs’ Mercury) use a different noising process, where instead of masking tokens, they replace them with different tokens (either with a random token or a semantically similar token). I wondered how they were getting such high throughput with the latter noising process, since I believed that optimizing inference with KVCache approximation would be more difficult (for various reasons). I visualized this noising process with tiny-diffusion and compared it to normal unmasking, and was very surprised to see how fast the generation “settles” into a reasonable output, and then only slightly refines afterwards, requiring much fewer steps in total. Unmasking (where tokens are never remasked, the typical implementation) is inherently limited in generation speed by the fact that an increase in tokens decoded per step leads to more errors due to the mismatch between individual and marginal token probability distributions we sample from. The token replacement noising process seems to have a much different set of characteristics. Because we sample each token per step, every token makes “progress” towards the final output each iteration (in addition to potentially giving other tokens more information in future steps). Generally, masking has outperformed other noising processes, which is probably why most research focused on it (using smaller models). But the paper referred to in the retweet shows that random replacement as a noising process may scale better as model size increases. Big labs might have noticed these results much earlier (due to having drastically more training resources and being able to test larger models), which may explain the discrepancy in the choice of noising process. I’m gonna test this with larger models, since tiny-diffusion only has 10M parameters.

nathan (in sf)

40,440 просмотров • 5 месяцев назад

NVidia just released PiD: super resolution in pixel space directly from model latents 🔎 4X resolution for any generated image, FAST! 🏎️💨 FLUX.1, 2 and Z-Image (Qwen Image coming) of course, i built a demo: generate 4K images with Z-Image

NVidia just released PiD: super resolution in pixel space directly from model latents 🔎 4X resolution for any generated image, FAST! 🏎️💨 FLUX.1, 2 and Z-Image (Qwen Image coming) of course, i built a demo: generate 4K images with Z-Image

apolinario (poli)

29,948 просмотров • 1 месяц назад

My first PhD paper!🎉We learn *diffusion* models for code generation that learn to directly *edit* syntax trees of programs. The result is a system that can incrementally write code, see the execution output, and debug it. 🧵1/n

My first PhD paper!🎉We learn diffusion models for code generation that learn to directly edit syntax trees of programs. The result is a system that can incrementally write code, see the execution output, and debug it. 🧵1/n

Shreyas Kapur

742,493 просмотров • 2 лет назад

🚀New paper out - We present Video-MSG (Multimodal Sketch Guidance), a novel planning-based training-free guidance method for T2V models, improving control of spatial layout and object trajectories. 🔧 Key idea: • Generate a Video Sketch — a spatio-temporal plan with background, foreground, and motion in the pixel space. • Encode this structure directly into the latent space of the diffusion model during generation, which does not require fine-tuning or additional memory during inference. 🧵

🚀New paper out - We present Video-MSG (Multimodal Sketch Guidance), a novel planning-based training-free guidance method for T2V models, improving control of spatial layout and object trajectories. 🔧 Key idea: • Generate a Video Sketch — a spatio-temporal plan with background, foreground, and motion in the pixel space. • Encode this structure directly into the latent space of the diffusion model during generation, which does not require fine-tuning or additional memory during inference. 🧵

Jialu Li

35,060 просмотров • 1 год назад

Diffusions are excellent in creating fantastic images and videos 🔎 We cooked a *diffusion* model to synthesize structured data #ICLR2025 🔥 Introducing TabDiff, a mixed-type diffusion model for generating synthetic tabular data, imputing missing values, and beyond! 🧵 1/n

Diffusions are excellent in creating fantastic images and videos 🔎 We cooked a diffusion model to synthesize structured data #ICLR2025 🔥 Introducing TabDiff, a mixed-type diffusion model for generating synthetic tabular data, imputing missing values, and beyond! 🧵 1/n

Minkai Xu

50,434 просмотров • 1 год назад

Diffusion models have amazing image creation abilities. But how well does their generative knowledge transfer to discriminative tasks? We present Diffusion Classifier: strong classification results with pretrained conditional diffusion models, *with no additional training*! 1/9

Diffusion models have amazing image creation abilities. But how well does their generative knowledge transfer to discriminative tasks? We present Diffusion Classifier: strong classification results with pretrained conditional diffusion models, with no additional training! 1/9

Alex Li

95,304 просмотров • 2 лет назад