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。

Omegance A Single Parameter for Various Granularities in Diffusion-Based Synthesis

AK

537,079 subscribers

19,379 次观看 • 1 年前 •via X (Twitter)

新闻政治科学技术教育

Anya Rossi• Live Now

Private livecam show

1 条评论

AK 的头像

AK1 年前

discuss:

相关视频

Google presents VLOGGER Multimodal Diffusion for Embodied Avatar Synthesis We propose VLOGGER, a method for audio-driven human video generation from a single input image of a person, which builds on the success of recent generative diffusion models. Our method consists of

AK

66,375 次观看 • 2 年前

'Sup! #PortfolioDay ✌️ I'm a DTM composer that makes music with FM synthesis, sample-based sound chips and various software for music production. #chiptune #ym2151 #furnacetracker #digifu

'Sup! #PortfolioDay ✌️ I'm a DTM composer that makes music with FM synthesis, sample-based sound chips and various software for music production. #chiptune #ym2151 #furnacetracker #digifu

タコス A M 4 N

16,542 次观看 • 1 年前

DiffPortrait360 just dropped on Hugging Face Consistent Portrait Diffusion for 360 View Synthesis

DiffPortrait360 just dropped on Hugging Face Consistent Portrait Diffusion for 360 View Synthesis

AK

58,670 次观看 • 1 年前

Can a language model become SOTA in chemical synthesis? 🧪🔥 We put a 2.6B-parameter Liquid AI model into MMAI Gym. It now sets the state of the art in single-step retrosynthesis. 🚀 #insilicoSOTAFM

Can a language model become SOTA in chemical synthesis? 🧪🔥 We put a 2.6B-parameter Liquid AI model into MMAI Gym. It now sets the state of the art in single-step retrosynthesis. 🚀 #insilicoSOTAFM

Insilico Medicine

39,706 次观看 • 2 个月前

Scaling up GANs for Text-to-Image Synthesis present our 1B-parameter GigaGAN, achieving lower FID than Stable Diffusion v1.5, DALL·E 2, and Parti-750M. It generates 512px outputs at 0.13s, orders of magnitude faster than diffusion and autoregressive models, and inherits the disentangled, continuous, and controllable latent space of GANs abs: project page:

Scaling up GANs for Text-to-Image Synthesis present our 1B-parameter GigaGAN, achieving lower FID than Stable Diffusion v1.5, DALL·E 2, and Parti-750M. It generates 512px outputs at 0.13s, orders of magnitude faster than diffusion and autoregressive models, and inherits the disentangled, continuous, and controllable latent space of GANs abs: project page:

AK

278,220 次观看 • 3 年前

We present Neural Riemannian Motion Fields (NRMF) as a promising paradigm for generative modeling of articulated motion. Unlike various diffusion based models, NRMF is useful both in generation and in deployment as a prior across tasks: #CVPR #AI #CVML👇

We present Neural Riemannian Motion Fields (NRMF) as a promising paradigm for generative modeling of articulated motion. Unlike various diffusion based models, NRMF is useful both in generation and in deployment as a prior across tasks: #CVPR #AI #CVML👇

Tolga Birdal

16,795 次观看 • 1 年前

Presenting MetaVoice-1B, a 1.2B parameter base model for TTS (text-to-speech). * Emotional speech in English * Voice cloning with fine-tuning * Zero-shot cloning for American & British voices * Support for long-form synthesis

Presenting MetaVoice-1B, a 1.2B parameter base model for TTS (text-to-speech). * Emotional speech in English * Voice cloning with fine-tuning * Zero-shot cloning for American & British voices * Support for long-form synthesis

Familiar

111,865 次观看 • 2 年前

Generative Novel View Synthesis with 3D-Aware Diffusion Models abs: project page:

Generative Novel View Synthesis with 3D-Aware Diffusion Models abs: project page:

AK

304,708 次观看 • 3 年前

today, sync. is excited to announce react-1 a ten billion parameter masked video diffusion model built for one purpose: giving you full creative control over performances in post

today, sync. is excited to announce react-1 a ten billion parameter masked video diffusion model built for one purpose: giving you full creative control over performances in post

sync. labs

27,266 次观看 • 11 个月前

Excited to share Norman Müller's DiffRF: Rendering-guided 3D Radiance Field Diffusion #CVPR2023 highlight! 2D diffusion is great, but what about 3D? We show radiance field diffusion with rendering guidance for consistent and editable 3D synthesis. Vid:

Excited to share Norman Müller's DiffRF: Rendering-guided 3D Radiance Field Diffusion #CVPR2023 highlight! 2D diffusion is great, but what about 3D? We show radiance field diffusion with rendering guidance for consistent and editable 3D synthesis. Vid:

Matthias Niessner

118,156 次观看 • 3 年前

📢GaussianGPT: autoregressive 3D Gaussian scene generation. We introduce a GPT-style model that directly generates 3D Gaussian scenes, token by token, in a series of small, discrete decision steps. Generation, completion, and large-scale outpainting in a single pipeline. Unlike diffusion-based approaches, GaussianGPT explicitly models the scene distribution at every step, allowing for quite flexible scene synthesis. 🌐 ▶️ Great work by Nicolas von Lützow, Barbara Roessle, Katharina Schmid

📢GaussianGPT: autoregressive 3D Gaussian scene generation. We introduce a GPT-style model that directly generates 3D Gaussian scenes, token by token, in a series of small, discrete decision steps. Generation, completion, and large-scale outpainting in a single pipeline. Unlike diffusion-based approaches, GaussianGPT explicitly models the scene distribution at every step, allowing for quite flexible scene synthesis. 🌐 ▶️ Great work by Nicolas von Lützow, Barbara Roessle, Katharina Schmid

Matthias Niessner

152,802 次观看 • 7 个月前

VSTAR Generative Temporal Nursing for Longer Dynamic Video Synthesis Despite tremendous progress in the field of text-to-video (T2V) synthesis, open-sourced T2V diffusion models struggle to generate longer videos with dynamically varying and evolving content. They tend to

VSTAR Generative Temporal Nursing for Longer Dynamic Video Synthesis Despite tremendous progress in the field of text-to-video (T2V) synthesis, open-sourced T2V diffusion models struggle to generate longer videos with dynamically varying and evolving content. They tend to

AK

37,003 次观看 • 2 年前

Diffuman4D 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models

Diffuman4D 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models

AK

12,518 次观看 • 1 年前

Congrats to LemonSlice on their $10.5M seed! They built the world's first interactive talking AI video model—a face layer for voice agents. Trained on a custom, 20B-parameter video diffusion transformer, streaming at 20fps on a single GPU. Infinite-length video generation with no error accumulation.

Congrats to LemonSlice on their $10.5M seed! They built the world's first interactive talking AI video model—a face layer for voice agents. Trained on a custom, 20B-parameter video diffusion transformer, streaming at 20fps on a single GPU. Infinite-length video generation with no error accumulation.

Y Combinator

50,969 次观看 • 10 个月前

A new frontier. Project Starlight—the first and only diffusion-based AI model for enhancing video. Launching soon.

A new frontier. Project Starlight—the first and only diffusion-based AI model for enhancing video. Launching soon.

Topaz Labs

22,375 次观看 • 1 年前

Energy-Based Models can now scale better than Diffusion models. Introducing TEM: Transformer Energy-based Models TLDR: • TEM outscales Diffusion without guidance • First scalable contrastive Energy-Based Models • Better generalization, test-time scaling, and OOD detection than Diffusion 🧵

Energy-Based Models can now scale better than Diffusion models. Introducing TEM: Transformer Energy-based Models TLDR: • TEM outscales Diffusion without guidance • First scalable contrastive Energy-Based Models • Better generalization, test-time scaling, and OOD detection than Diffusion 🧵

Alexi Gladstone

88,647 次观看 • 7 天前

ControlMat: Controlled Generative Approach to Material Capture by Giuseppe Vecchio et al. From a single photo to clean, realistics, tileable PBR materials with this diffusion-based matching model.

ControlMat: Controlled Generative Approach to Material Capture by Giuseppe Vecchio et al. From a single photo to clean, realistics, tileable PBR materials with this diffusion-based matching model.

Ben Ferns

120,264 次观看 • 3 年前

More visual based synthesis, this time focusing on bass design.

More visual based synthesis, this time focusing on bass design.

𝐕𝐚𝐫𝐚 𝐎𝐬𝐢𝐫𝐢𝐚 𝐁𝐞𝐥𝐢𝐜𝐡 ༒

13,064 次观看 • 1 年前

StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis significantly improves over previous GANs and outperforms distilled diffusion models in terms of sample quality and speed abs: project page:

StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis significantly improves over previous GANs and outperforms distilled diffusion models in terms of sample quality and speed abs: project page:

AK

425,803 次观看 • 3 年前

Positron AI wants to run 16 trillion parameter models on a single server.

Positron AI wants to run 16 trillion parameter models on a single server.

SemiAnalysis

20,384 次观看 • 6 个月前