Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

🆕 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 Aufrufe • vor 1 Jahr •via X (Twitter)

BildungNachrichten & PolitikWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

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 Aufrufe • vor 3 Monaten

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

54,539 Aufrufe • vor 1 Jahr

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

158,595 Aufrufe • vor 3 Jahren

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

164,569 Aufrufe • vor 5 Monaten

😀 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 Aufrufe • vor 2 Jahren

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 🥓👑

457,795 Aufrufe • vor 2 Jahren

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

28,359 Aufrufe • vor 2 Monaten

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 🧩

125,146 Aufrufe • vor 6 Monaten

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

28,399 Aufrufe • vor 4 Monaten

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 Aufrufe • vor 1 Jahr

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 Aufrufe • vor 1 Jahr

I love this image prompt: Super macro photography: a mechanical [concept] made of circuit boards and LED lights, resting on mossy soil in the palm of your hand. Intricate, highly detailed object, captured in high resolution. What would you do with it? 🤔
0:10

I love this image prompt: Super macro photography: a mechanical [concept] made of circuit boards and LED lights, resting on mossy soil in the palm of your hand. Intricate, highly detailed object, captured in high resolution. What would you do with it? 🤔

AlexandrIA

102,877 Aufrufe • vor 11 Monaten

GPT Image 2.0 is now available on Akool 🚀 This isn’t just an upgrade—it’s a major leap in AI image generation. With GPT Image 2.0, you get: • Sharper, high-resolution outputs with improved detail and realism • Much stronger text rendering (finally, text in images that actually looks right) • Better prompt understanding for more accurate and controllable results • Improved consistency across variations and multi-image generations • More precise editing & refinement for iterative creative workflows Whether you're creating marketing visuals, product images, or storytelling assets, GPT Image 2.0 delivers cleaner, more reliable, and production-ready results. Now live on Akool, try the latest in AI image generation today.
0:10

GPT Image 2.0 is now available on Akool 🚀 This isn’t just an upgrade—it’s a major leap in AI image generation. With GPT Image 2.0, you get: • Sharper, high-resolution outputs with improved detail and realism • Much stronger text rendering (finally, text in images that actually looks right) • Better prompt understanding for more accurate and controllable results • Improved consistency across variations and multi-image generations • More precise editing & refinement for iterative creative workflows Whether you're creating marketing visuals, product images, or storytelling assets, GPT Image 2.0 delivers cleaner, more reliable, and production-ready results. Now live on Akool, try the latest in AI image generation today.

Akool Inc

1,541,129 Aufrufe • vor 4 Monaten

🤯 𝐒𝐥𝐢𝐜𝐞𝐝𝐢𝐭 : A revolutionary approach to zero-shot video editing✏️🎥 using text-to-image diffusion models 🎞️Slicedit achieves great temporal consistency by leveraging spatio-temporal "slices"🔀
0:10

🤯 𝐒𝐥𝐢𝐜𝐞𝐝𝐢𝐭 : A revolutionary approach to zero-shot video editing✏️🎥 using text-to-image diffusion models 🎞️Slicedit achieves great temporal consistency by leveraging spatio-temporal "slices"🔀

Gradio

19,586 Aufrufe • vor 2 Jahren

TAA VS FSR 4 VS DLSS 4.5 at a super-low resolution so you can see how each one reconstructs the image better. In this scenario, I've used Assassins Creed: Shadows on two different machines using the same settings and set the following settings for upscaling. In-game resolution at 720p and changed the resolution scaling to 20% (144p) while keeping the sharpness at 30% Which one looks better?
0:16

TAA VS FSR 4 VS DLSS 4.5 at a super-low resolution so you can see how each one reconstructs the image better. In this scenario, I've used Assassins Creed: Shadows on two different machines using the same settings and set the following settings for upscaling. In-game resolution at 720p and changed the resolution scaling to 20% (144p) while keeping the sharpness at 30% Which one looks better?

NikTek

55,738 Aufrufe • vor 7 Monaten

A dream of our lab has been to image the full central dogma from a single endogenous gene, all live and with single molecule resolution. After many years we are happy to unveil a beautiful cell line that makes it possible. Check out our preprint ( (1/n)
0:11

A dream of our lab has been to image the full central dogma from a single endogenous gene, all live and with single molecule resolution. After many years we are happy to unveil a beautiful cell line that makes it possible. Check out our preprint ( (1/n)

Timothy

206,349 Aufrufe • vor 2 Jahren