Загрузка видео...

Не удалось загрузить видео

На главную

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

Gradio's profile picture

Gradio

55,683 subscribers

53,331 просмотров • 1 год назад •via X (Twitter)

ОбразованиеНовости и политикаНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

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
0:12

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

🔥 KEEP - New sota for video face super-resolution
0:13

🔥 KEEP - New sota for video face super-resolution

Gradio

53,631 просмотров • 1 год назад

ByteDance Seed is back with SeedVR2, now on Hugging Face! This one-step video restoration model leverages diffusion adversarial post-training for impressive results, even on high-resolution videos.
0:19

ByteDance Seed is back with SeedVR2, now on Hugging Face! This one-step video restoration model leverages diffusion adversarial post-training for impressive results, even on high-resolution videos.

DailyPapers

54,511 просмотров • 1 год назад

new image-to-svg model just dropped 🔥
0:12

new image-to-svg model just dropped 🔥

Dreaming Tulpa 🥓👑

20,934 просмотров • 1 год назад

Relightify: Relightable 3D Faces from a Single Image via Diffusion Models abs: paper page:
0:10

Relightify: Relightable 3D Faces from a Single Image via Diffusion Models abs: paper page:

AK

85,893 просмотров • 3 лет 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:
0:14

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

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🧵
0:17

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

163,340 просмотров • 3 месяцев назад

😀 ToonCrafter: Generative Cartoon Interpolation 🔆 Can interpolate two cartoon images by leveraging the pre-trained image-to-video diffusion priors. Model on 🤗👇
0:10

😀 ToonCrafter: Generative Cartoon Interpolation 🔆 Can interpolate two cartoon images by leveraging the pre-trained image-to-video diffusion priors. Model on 🤗👇

Gradio

93,074 просмотров • 2 лет назад

The Stable Video Diffusion model just dropped 🔥 The new model supports: – Text-to-Video – Image-to-Video – 14 or 25 frames at 576 x 1024 – Multi-View Generation – Frame Interpolation – 3D Scene Understanding – Camera Control via LoRA Paper: Code: SVD model: SVD-XT model:
0:10

The Stable Video Diffusion model just dropped 🔥 The new model supports: – Text-to-Video – Image-to-Video – 14 or 25 frames at 576 x 1024 – Multi-View Generation – Frame Interpolation – 3D Scene Understanding – Camera Control via LoRA Paper: Code: SVD model: SVD-XT model:

Dreaming Tulpa 🥓👑

457,724 просмотров • 2 лет назад

Going educational! Heres a visual example of how #resolution is affected when the image resolution is to small for the #display #themoreyouknow
0:15

Going educational! Heres a visual example of how #resolution is affected when the image resolution is to small for the #display #themoreyouknow

Demora Avarice

114,055 просмотров • 1 год назад

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.
0:18

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

Hi3DGen 🔥 High-fidelity 3D geometry generation from a single image by leveraging normal maps as an intermediate representation
0:15

Hi3DGen 🔥 High-fidelity 3D geometry generation from a single image by leveraging normal maps as an intermediate representation

Gradio

50,996 просмотров • 1 год назад

Yesss Jasper introduces LBM: Latent Bridge Matching for Fast Image-to-Image Translation💡 and drops an amazing ✨image relighting✨ demo that runs with a single(!) inference step 🔥
0:14

Yesss Jasper introduces LBM: Latent Bridge Matching for Fast Image-to-Image Translation💡 and drops an amazing ✨image relighting✨ demo that runs with a single(!) inference step 🔥

Linoy Tsaban

14,426 просмотров • 1 год назад

Seedream 5.0 lite LIVE on Higgsfield at Day-0! 💥 UNLIMITED FOR 7 DAYS on Pro, Ultimate & Creator plans. Seedream 5.0 Lite brings stunning multi-image blending, instant outfit swaps & batch image creation with perfect subject consistency across EVERY frame. Up to 14 reference images with up to 3K resolution on every single output. Powered by ByteDance's most advanced image model yet.
0:20

Seedream 5.0 lite LIVE on Higgsfield at Day-0! 💥 UNLIMITED FOR 7 DAYS on Pro, Ultimate & Creator plans. Seedream 5.0 Lite brings stunning multi-image blending, instant outfit swaps & batch image creation with perfect subject consistency across EVERY frame. Up to 14 reference images with up to 3K resolution on every single output. Powered by ByteDance's most advanced image model yet.

Higgsfield AI 🧩

120,870 просмотров • 4 месяцев 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.
0:19

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 • 2 месяцев 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.
0:16

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

Meta just dropped a new paper. "A Recipe for Generating 3D Worlds From a Single Image" Turn a single image into a high-quality 3D world ready for VR. 10 wild examples:
0:16

Meta just dropped a new paper. "A Recipe for Generating 3D Worlds From a Single Image" Turn a single image into a high-quality 3D world ready for VR. 10 wild examples:

Angry Tom

214,406 просмотров • 1 год назад

Step 1: Generate the base image with GPT-2 Step 2: Serve the image you just generated back to GPT-2 with this prompt: "Convert this scene into a 360 equirectangular image"
0:19

Step 1: Generate the base image with GPT-2 Step 2: Serve the image you just generated back to GPT-2 with this prompt: "Convert this scene into a 360 equirectangular image"

A.I.Warper

77,151 просмотров • 2 месяцев назад

(1/2) Intrinsic Image Diffusion for Single-view Material Estimation! We propose a probabilistic diffusion model to handle material & lighting ambiguities. We obtain sharp material estimates and facilitate high-fidelity relighting.
0:19

(1/2) Intrinsic Image Diffusion for Single-view Material Estimation! We propose a probabilistic diffusion model to handle material & lighting ambiguities. We obtain sharp material estimates and facilitate high-fidelity relighting.

Matthias Niessner

69,400 просмотров • 2 лет назад