Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models turn the publicly available, state-of-the-art text-to-image LDM Stable Diffusion into an efficient and expressive text-to-video model with resolution up to 1280 x 2048 abs: project page:

AK

535,578 subscribers

718,894 Aufrufe • vor 3 Jahren •via X (Twitter)

Wissenschaft & Technologie Bildung

Anya Rossi• Live Now

Private livecam show

22 Kommentare

Profilbild von Yackadaisical

Yackadaisicalvor 3 Jahren

"Andreas, Robin and Tim did the work during internships at NVIDIA." interns these days...

Profilbild von VRonny

VRonnyvor 3 Jahren

I want Will Smith eating spaghetti to be the official text to video benchmark

Profilbild von Miguel | AP

Miguel | APvor 3 Jahren

This is actually crazy. If this came out in mid-2022 everyone would be floored. Wild times

Profilbild von Thomas Willberger

Thomas Willbergervor 3 Jahren

Awesome! We're working on video diffusion models at @ParamaxAi for AI movie generation, based in Germany but hiring globally. Let us know if you want to contribute!

Profilbild von Alessandro Flaborea

Alessandro Flaboreavor 3 Jahren

just waiting for the open source version of this 👀

Profilbild von even constant

even constantvor 3 Jahren

We’re entering Dreamtime

Profilbild von Adhik Joshi

Adhik Joshivor 3 Jahren

This is nuts, any plans for releasing code? Maybe someone can do implementation of this paper ? @mk1stats

Profilbild von Jesse Wood

Jesse Woodvor 3 Jahren

Called it 💯🎯

Profilbild von The Guy

The Guyvor 3 Jahren

Are ANY of these text-to-video methods available in an open source or other accessible form that we can tinker with? Or are they all behind a website wall at best? I've got video generating code on my github that is comparable in quality that just uses straight up CLIP & SD.

Profilbild von .

.vor 3 Jahren

another text-to-video model the public isn't allowed to use. this is the wrong way to go, because the alternative is the public one day suddenly having access to text-to-video that is indistinguishable from reality out of nowhere, and you can imagine how that will affect things

Profilbild von iandanforth 🦋 @iandanforth.bsky.social

iandanforth 🦋 @iandanforth.bsky.socialvor 3 Jahren

Amazing! I hope this method is compatible with control-net style inputs for even better control.

Profilbild von AgiDoomerAnon

AgiDoomerAnonvor 3 Jahren

but can it do anime

Profilbild von B. Elliott Baker

B. Elliott Bakervor 3 Jahren

wild!

Profilbild von Emily

Emilyvor 3 Jahren

Great start.

Profilbild von Woje

Wojevor 3 Jahren

@sanskar_mk2

Profilbild von Ruoyu Feng

Ruoyu Fengvor 3 Jahren

amazing

Profilbild von alber 🌊

alber 🌊vor 3 Jahren

@SaveToNotion #thread #stable_diffusion

Profilbild von Grammz10

Grammz10vor 3 Jahren

@NotionAddon

Profilbild von mazing A

mazing Avor 3 Jahren

@SaveToNotion #thread

Profilbild von Dautel

Dautelvor 3 Jahren

@en_klem @neuralframes

Profilbild von Function

Functionvor 3 Jahren

Okay, now create me a universe in real-time that I can oversee. I may send in my son's avatar from time to time to make sure everyone is playing by the rules.

Profilbild von Anxo(a)

Anxo(a)vor 3 Jahren

Asistimos al inicio de una nueva era, como cuando las primeras imágenes cinematográficas!

Ähnliche Videos

Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Models abs: project page:

Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Models abs: project page:

AK

121,020 Aufrufe • vor 3 Jahren

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 Aufrufe • vor 3 Jahren

Expressive Text-to-Image Generation with Rich Text abs: project page:

Expressive Text-to-Image Generation with Rich Text abs: project page:

AK

209,410 Aufrufe • vor 3 Jahren

Dreamix: Video Diffusion Models are General Video Editors abs: project page: present diffusion-based method that is able to perform text-based motion and appearance editing of general videos

Dreamix: Video Diffusion Models are General Video Editors abs: project page: present diffusion-based method that is able to perform text-based motion and appearance editing of general videos

AK

398,258 Aufrufe • vor 3 Jahren

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 Aufrufe • vor 3 Jahren

🤯DiffIR2VR-Zero: Zero-shot video restoration to high-resolution using pre-trained image restoration diffusion models. - Framework can handle video denoising and up to 8x super-resolution - outperforms trained models in generalizing across diverse datasets and extreme degradations - Compatible with every 2D restoration model

🤯DiffIR2VR-Zero: Zero-shot video restoration to high-resolution using pre-trained image restoration diffusion models. - Framework can handle video denoising and up to 8x super-resolution - outperforms trained models in generalizing across diverse datasets and extreme degradations - Compatible with every 2D restoration model

Gradio

20,368 Aufrufe • vor 2 Jahren

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 Aufrufe • vor 3 Jahren

Designing an Encoder for Fast Personalization of Text-to-Image Models TL;DR: use an encoder to personalize a text-to-image model to new concepts with a single image and 5-15 tuning steps abs: project page:

Designing an Encoder for Fast Personalization of Text-to-Image Models TL;DR: use an encoder to personalize a text-to-image model to new concepts with a single image and 5-15 tuning steps abs: project page:

AK

165,179 Aufrufe • vor 3 Jahren

TokenFlow: Consistent Diffusion Features for Consistent Video Editing paper page: The generative AI revolution has recently expanded to videos. Nevertheless, current state-of-the-art video models are still lagging behind image models in terms of visual quality and user control over the generated content. In this work, we present a framework that harnesses the power of a text-to-image diffusion model for the task of text-driven video editing. Specifically, given a source video and a target text-prompt, our method generates a high-quality video that adheres to the target text, while preserving the spatial layout and motion of the input video. Our method is based on a key observation that consistency in the edited video can be obtained by enforcing consistency in the diffusion feature space. We achieve this by explicitly propagating diffusion features based on inter-frame correspondences, readily available in the model. Thus, our framework does not require any training or fine-tuning, and can work in conjunction with any off-the-shelf text-to-image editing method. We demonstrate state-of-the-art editing results on a variety of real-world videos.

TokenFlow: Consistent Diffusion Features for Consistent Video Editing paper page: The generative AI revolution has recently expanded to videos. Nevertheless, current state-of-the-art video models are still lagging behind image models in terms of visual quality and user control over the generated content. In this work, we present a framework that harnesses the power of a text-to-image diffusion model for the task of text-driven video editing. Specifically, given a source video and a target text-prompt, our method generates a high-quality video that adheres to the target text, while preserving the spatial layout and motion of the input video. Our method is based on a key observation that consistency in the edited video can be obtained by enforcing consistency in the diffusion feature space. We achieve this by explicitly propagating diffusion features based on inter-frame correspondences, readily available in the model. Thus, our framework does not require any training or fine-tuning, and can work in conjunction with any off-the-shelf text-to-image editing method. We demonstrate state-of-the-art editing results on a variety of real-world videos.

AK

143,557 Aufrufe • vor 3 Jahren

Google just released Muse: a text to image model achieving state of the art performance. It is significantly more efficient than diffusion models. Muse also allows for inpainting, outpainting, and mask-free editing without finetuning or inverting the model.

Google just released Muse: a text to image model achieving state of the art performance. It is significantly more efficient than diffusion models. Muse also allows for inpainting, outpainting, and mask-free editing without finetuning or inverting the model.

bleedingedge.ai

183,766 Aufrufe • vor 3 Jahren

Nvidia just announced Align Your Gaussians Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models

Nvidia just announced Align Your Gaussians Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models

AK

131,358 Aufrufe • vor 2 Jahren

Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution paper page: Text-based diffusion models have exhibited remarkable success in generation and editing, showing great promise for enhancing visual content with their generative prior. However, applying these models to video super-resolution remains challenging due to the high demands for output fidelity and temporal consistency, which is complicated by the inherent randomness in diffusion models. Our study introduces Upscale-A-Video, a text-guided latent diffusion framework for video upscaling. This framework ensures temporal coherence through two key mechanisms: locally, it integrates temporal layers into U-Net and VAE-Decoder, maintaining consistency within short sequences; globally, without training, a flow-guided recurrent latent propagation module is introduced to enhance overall video stability by propagating and fusing latent across the entire sequences. Thanks to the diffusion paradigm, our model also offers greater flexibility by allowing text prompts to guide texture creation and adjustable noise levels to balance restoration and generation, enabling a trade-off between fidelity and quality. Extensive experiments show that Upscale-A-Video surpasses existing methods in both synthetic and real-world benchmarks, as well as in AI-generated videos, showcasing impressive visual realism and temporal consistency.

Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution paper page: Text-based diffusion models have exhibited remarkable success in generation and editing, showing great promise for enhancing visual content with their generative prior. However, applying these models to video super-resolution remains challenging due to the high demands for output fidelity and temporal consistency, which is complicated by the inherent randomness in diffusion models. Our study introduces Upscale-A-Video, a text-guided latent diffusion framework for video upscaling. This framework ensures temporal coherence through two key mechanisms: locally, it integrates temporal layers into U-Net and VAE-Decoder, maintaining consistency within short sequences; globally, without training, a flow-guided recurrent latent propagation module is introduced to enhance overall video stability by propagating and fusing latent across the entire sequences. Thanks to the diffusion paradigm, our model also offers greater flexibility by allowing text prompts to guide texture creation and adjustable noise levels to balance restoration and generation, enabling a trade-off between fidelity and quality. Extensive experiments show that Upscale-A-Video surpasses existing methods in both synthetic and real-world benchmarks, as well as in AI-generated videos, showcasing impressive visual realism and temporal consistency.

AK

32,849 Aufrufe • vor 2 Jahren

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 Aufrufe • vor 2 Jahren

ByteDance just announced MagicVideo-V2 Multi-Stage High-Aesthetic Video Generation paper page: The growing demand for high-fidelity video generation from textual descriptions has catalyzed significant research in this field. In this work, we introduce MagicVideo-V2 that integrates the text-to-image model, video motion generator, reference image embedding module and frame interpolation module into an end-to-end video generation pipeline. Benefiting from these architecture designs, MagicVideo-V2 can generate an aesthetically pleasing, high-resolution video with remarkable fidelity and smoothness. It demonstrates superior performance over leading Text-to-Video systems such as Runway, Pika 1.0, Morph, Moon Valley and Stable Video Diffusion model via user evaluation at large scale

ByteDance just announced MagicVideo-V2 Multi-Stage High-Aesthetic Video Generation paper page: The growing demand for high-fidelity video generation from textual descriptions has catalyzed significant research in this field. In this work, we introduce MagicVideo-V2 that integrates the text-to-image model, video motion generator, reference image embedding module and frame interpolation module into an end-to-end video generation pipeline. Benefiting from these architecture designs, MagicVideo-V2 can generate an aesthetically pleasing, high-resolution video with remarkable fidelity and smoothness. It demonstrates superior performance over leading Text-to-Video systems such as Runway, Pika 1.0, Morph, Moon Valley and Stable Video Diffusion model via user evaluation at large scale

AK

181,049 Aufrufe • vor 2 Jahren

Today, we are releasing Stable Video Diffusion, our first foundation model for generative AI video based on the image model, Stable Diffusion. As part of this research preview, the code, weights, and research paper are now available. Additionally, today you can sign up for our waitlist to access a new upcoming web experience featuring a Text-To-Video interface. To access the model & sign up for our waitlist, visit our website here:

Today, we are releasing Stable Video Diffusion, our first foundation model for generative AI video based on the image model, Stable Diffusion. As part of this research preview, the code, weights, and research paper are now available. Additionally, today you can sign up for our waitlist to access a new upcoming web experience featuring a Text-To-Video interface. To access the model & sign up for our waitlist, visit our website here:

Stability AI

1,024,917 Aufrufe • vor 2 Jahren

try out the Gradio Demo for AudioLDM: Text-to-Audio Generation with Latent Diffusion Models on Hugging Face demo:

try out the Gradio Demo for AudioLDM: Text-to-Audio Generation with Latent Diffusion Models on Hugging Face demo:

AK

82,138 Aufrufe • vor 3 Jahren

Struggling with slow inference of diffusion and flow models? Check out the video below—I’ve been using our new FastGen library to achieve 7-28x acceleration for text-2-image and {text,image,video}-2-video generation without sacrificing visual fidelity!

Struggling with slow inference of diffusion and flow models? Check out the video below—I’ve been using our new FastGen library to achieve 7-28x acceleration for text-2-image and {text,image,video}-2-video generation without sacrificing visual fidelity!

Julius Berner

13,788 Aufrufe • vor 8 Monaten

LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models paper page: github: Recent advancements in text-to-image generation with diffusion models have yielded remarkable results synthesizing highly realistic and diverse images. However, these models still encounter difficulties when generating images from prompts that demand spatial or common sense reasoning. We propose to equip diffusion models with enhanced reasoning capabilities by using off-the-shelf pretrained large language models (LLMs) in a novel two-stage generation process. First, we adapt an LLM to be a text-guided layout generator through in-context learning. When provided with an image prompt, an LLM outputs a scene layout in the form of bounding boxes along with corresponding individual descriptions. Second, we steer a diffusion model with a novel controller to generate images conditioned on the layout. Both stages utilize frozen pretrained models without any LLM or diffusion model parameter optimization. We validate the superiority of our design by demonstrating its ability to outperform the base diffusion model in accurately generating images according to prompts that necessitate both language and spatial reasoning. Additionally, our method naturally allows dialog-based scene specification and is able to handle prompts in a language that is not well-supported by the underlying diffusion model.

LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models paper page: github: Recent advancements in text-to-image generation with diffusion models have yielded remarkable results synthesizing highly realistic and diverse images. However, these models still encounter difficulties when generating images from prompts that demand spatial or common sense reasoning. We propose to equip diffusion models with enhanced reasoning capabilities by using off-the-shelf pretrained large language models (LLMs) in a novel two-stage generation process. First, we adapt an LLM to be a text-guided layout generator through in-context learning. When provided with an image prompt, an LLM outputs a scene layout in the form of bounding boxes along with corresponding individual descriptions. Second, we steer a diffusion model with a novel controller to generate images conditioned on the layout. Both stages utilize frozen pretrained models without any LLM or diffusion model parameter optimization. We validate the superiority of our design by demonstrating its ability to outperform the base diffusion model in accurately generating images according to prompts that necessitate both language and spatial reasoning. Additionally, our method naturally allows dialog-based scene specification and is able to handle prompts in a language that is not well-supported by the underlying diffusion model.

AK

83,681 Aufrufe • vor 3 Jahren

Introducing 🔥BLIP-Diffusion🔥, a novel method for enabling Text-to-image Diffusion models with multimodal controllable generation/editing, powered by BLIP-2 pre-trained text-aligned subject representation. Paper: Project: (1/n)

Introducing 🔥BLIP-Diffusion🔥, a novel method for enabling Text-to-image Diffusion models with multimodal controllable generation/editing, powered by BLIP-2 pre-trained text-aligned subject representation. Paper: Project: (1/n)

Steven Hoi

40,615 Aufrufe • vor 3 Jahren