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.

Without using any text prompting, we can slice images together in a purely visual language:

Gytis Daujotas

1,775 subscribers

68,609 Aufrufe • vor 2 Jahren •via X (Twitter)

Bildung Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

10 Kommentare

Profilbild von Toad

Toadvor 2 Jahren

oh my god.

Profilbild von Silicon Jungle

Silicon Junglevor 2 Jahren

this is so fun.

Profilbild von Andy Matuschak

Andy Matuschakvor 2 Jahren

Really lovely work!

Profilbild von Gytis Daujotas

Gytis Daujotasvor 2 Jahren

Thank you Andy!

Profilbild von Yondon Fu

Yondon Fuvor 2 Jahren

Some fun visual crafting games to be made with this!

Profilbild von Fiona

Fionavor 2 Jahren

so cool

Profilbild von elvis

elvisvor 2 Jahren

That’s neat

Profilbild von James Hill-Khurana

James Hill-Khuranavor 2 Jahren

This is so great!

Profilbild von Logan Kudlacik

Logan Kudlacikvor 2 Jahren

Awesome. Code?

Profilbild von Lauk Lumba-Lumba

Lauk Lumba-Lumbavor 2 Jahren

Fusing the collage.

Ähnliche Videos

Use voice-to-text when prompting in Visual Studio Code 🎤

Use voice-to-text when prompting in Visual Studio Code 🎤

Visual Studio Code

57,715 Aufrufe • vor 4 Monaten

Creative work often starts before we can describe what we're looking for. What role can generative models play at this stage? 🌱Our new work, Inspiration Seeds, reveals hidden visual connections between images, creating a purely visual exploration space. 🔗

Creative work often starts before we can describe what we're looking for. What role can generative models play at this stage? 🌱Our new work, Inspiration Seeds, reveals hidden visual connections between images, creating a purely visual exploration space. 🔗

Yael Vinker

16,759 Aufrufe • vor 5 Monaten

Prompting Midjourney and Kling without words, to see what they can do with visual direction only.

Prompting Midjourney and Kling without words, to see what they can do with visual direction only.

Tatiana Tsiguleva

142,907 Aufrufe • vor 3 Monaten

We are excited to announce the 1st version of our multimodal assistant, Yasa-1, a language assistant with visual and auditory sensors that can take actions via code execution 🪄. Yasa-1 can understand text, images, videos, sounds & more! 🚀 Check out more details below👇

We are excited to announce the 1st version of our multimodal assistant, Yasa-1, a language assistant with visual and auditory sensors that can take actions via code execution 🪄. Yasa-1 can understand text, images, videos, sounds & more! 🚀 Check out more details below👇

Reka

814,303 Aufrufe • vor 2 Jahren

Today we are launching VE2 — a brand new model for Visual Electric. It can produce hyper realistic photos, accurate text, and generate images 2.5x faster. This is the biggest update ever to Visual Electric. 🔊 SOUND ON

Colin Dunn

41,443 Aufrufe • vor 2 Jahren

I've heard that Netflix is using AI... So I went and tried to redo the Netflix 'Tudum' intro with AI. Text-to-video in Hailuo 02, NO images. Just pure prompting:

I've heard that Netflix is using AI... So I went and tried to redo the Netflix 'Tudum' intro with AI. Text-to-video in Hailuo 02, NO images. Just pure prompting:

Alex Patrascu

112,225 Aufrufe • vor 1 Jahr

An example of how DUSt3R can do "impossible matching": given two images without any shared visual content (my office, obviously never seen at training), it can output an accurate reconstruction (no intrinsics, no poses!) in seconds

An example of how DUSt3R can do "impossible matching": given two images without any shared visual content (my office, obviously never seen at training), it can output an accurate reconstruction (no intrinsics, no poses!) in seconds

Jerome Revaud

68,033 Aufrufe • vor 2 Jahren

Made a simple toy to morph any text with Fourier transforms. Just enter any from/to text in any language and see it morphs: Bonus: Can share link with friends to send the exact message morph to them

Made a simple toy to morph any text with Fourier transforms. Just enter any from/to text in any language and see it morphs: Bonus: Can share link with friends to send the exact message morph to them

Andrei Kashcha

40,301 Aufrufe • vor 4 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

83,657 Aufrufe • vor 3 Jahren

🎙️ Dictate in Multiple Languages in #VSCode Dictation can detect your language and turn your speech into text using a local model. You can use it in Chat, the editor, and the integrated terminal.

🎙️ Dictate in Multiple Languages in #VSCode Dictation can detect your language and turn your speech into text using a local model. You can use it in Chat, the editor, and the integrated terminal.

Visual Studio Code

27,733 Aufrufe • vor 17 Tagen

StarVector is out on Hugging Face StarVector is a foundation model for generating Scalable Vector Graphics (SVG) code from images and text. It utilizes a Vision-Language Modeling architecture to understand both visual and textual inputs, enabling high-quality vectorization and text-guided SVG creation.

StarVector is out on Hugging Face StarVector is a foundation model for generating Scalable Vector Graphics (SVG) code from images and text. It utilizes a Vision-Language Modeling architecture to understand both visual and textual inputs, enabling high-quality vectorization and text-guided SVG creation.

AK

254,411 Aufrufe • vor 1 Jahr

How can we learn 3D visual grounding with natural supervision—only looking at QA pairs, without ground truth bounding boxes or object classification labels? We inject explicit language priors, e.g., the symmetric property that A near B ⇒ B near A, in structured vision models.

How can we learn 3D visual grounding with natural supervision—only looking at QA pairs, without ground truth bounding boxes or object classification labels? We inject explicit language priors, e.g., the symmetric property that A near B ⇒ B near A, in structured vision models.

Joy Hsu

14,843 Aufrufe • vor 2 Jahren

Multimodality: using #AI to understand & generate content across text, images, & audio. It can break down language barriers, making tech more inclusive. Which multimodal function do you find most impactful? Share your thoughts below 👇

Multimodality: using #AI to understand & generate content across text, images, & audio. It can break down language barriers, making tech more inclusive. Which multimodal function do you find most impactful? Share your thoughts below 👇

Google AI

36,204 Aufrufe • vor 1 Jahr

allright i got you 🫡 you can now auto-generate App Store preview screenshots for your mobile app in 1-click! clone any style you want - just upload some reference images & you're ready to go full control over image & text just by prompting

allright i got you 🫡 you can now auto-generate App Store preview screenshots for your mobile app in 1-click! clone any style you want - just upload some reference images & you're ready to go full control over image & text just by prompting

Fekri

90,874 Aufrufe • vor 7 Monaten

Any language can sound nice when you're purposely talking in a high pitched fake anime voice. Japanese sounds like Nazis of Asia language spoken without being fake & pretentious.

Any language can sound nice when you're purposely talking in a high pitched fake anime voice. Japanese sounds like Nazis of Asia language spoken without being fake & pretentious.

The Genius

4,895,615 Aufrufe • vor 5 Monaten

you can now edit images IN PLACE with a text prompt in only 6 seconds! watch.

you can now edit images IN PLACE with a text prompt in only 6 seconds! watch.

maharshi

30,907 Aufrufe • vor 1 Jahr

Exactly AI Illustrative Training is now on Runware⚙️ - Train a custom model on your brand's visual style - 10–50 images produces a reusable brand-aligned model - Text-to-image + image-to-image with zero style prompting required - Consistent output across campaigns & products

Runware

578,284 Aufrufe • vor 3 Monaten

oh my.. AI is coming for motion graphics you can animate text&graphics by prompting using Claude now.. guide&prompts+crazy examples:

oh my.. AI is coming for motion graphics you can animate text&graphics by prompting using Claude now.. guide&prompts+crazy examples:

el.cine

64,883 Aufrufe • vor 7 Monaten