Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

I've been experimenting with embeddings a lot recently. Here's an interface I created that lets me interpolate between CLIP image embeddings and generate images from the intermediate latents Latent Surfing. it's kinda like a color picker, but for images. (1/n)

aarya

12,650 subscribers

122,731 views • 2 years ago •via X (Twitter)

Education Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Create a 3D model from a single image, set of images or a text prompt in < 1 minute 😮‍💨 This new AI paper called CAT3D shows us that it’ll keep getting easier to produce 3D models from 2D images — whether it’s a sparser real world 3D scan (a few photos instead of hundreds) or your favorite 2D image generator like Midjourney (just an image). How does this magic work? “This architecture is similar to video diffusion models, but with camera pose embeddings for each image instead of time embeddings. The generated views are passed into a robust 3D reconstruction pipeline to create the 3D representation (Zip-NeRF or 3DGS)”

Create a 3D model from a single image, set of images or a text prompt in < 1 minute 😮‍💨 This new AI paper called CAT3D shows us that it’ll keep getting easier to produce 3D models from 2D images — whether it’s a sparser real world 3D scan (a few photos instead of hundreds) or your favorite 2D image generator like Midjourney (just an image). How does this magic work? “This architecture is similar to video diffusion models, but with camera pose embeddings for each image instead of time embeddings. The generated views are passed into a robust 3D reconstruction pipeline to create the 3D representation (Zip-NeRF or 3DGS)”

Bilawal Sidhu

92,760 views • 2 years ago

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

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 views • 23 days ago

Excited to release a research preview of Feature Lab, a playground where you can sculpt images by editing their features. It uses a SAE to extract the sparse features from an image embeddings model, and allows us to finely sculpt and tweak images.

Excited to release a research preview of Feature Lab, a playground where you can sculpt images by editing their features. It uses a SAE to extract the sparse features from an image embeddings model, and allows us to finely sculpt and tweak images.

Gytis Daujotas

73,833 views • 2 years ago

I've recently been experimenting with oklch and I made this little tool that helps generate, explore and preview colors.

I've recently been experimenting with oklch and I made this little tool that helps generate, explore and preview colors.

Jakub Krehel

33,563 views • 1 year ago

wow.. this AI animation platform is mind-blowing! Morphic AI can generate videos from single images and lets you make full animated films. this short clip was generated from just 1 image here's how and more examples:

wow.. this AI animation platform is mind-blowing! Morphic AI can generate videos from single images and lets you make full animated films. this short clip was generated from just 1 image here's how and more examples:

Dhaval Makwana

37,572 views • 1 year ago

Want to generate images from the world's best models like Nano Banana or GPT Image side by side? Now you can with Image Lab 🚀 Run a single prompt across up to 25 models, with up to 20 images from each, and see results in seconds. You've seen our leaderboards. Now generate and evaluate the models yourself. Link in thread 🧵👇

Want to generate images from the world's best models like Nano Banana or GPT Image side by side? Now you can with Image Lab 🚀 Run a single prompt across up to 25 models, with up to 20 images from each, and see results in seconds. You've seen our leaderboards. Now generate and evaluate the models yourself. Link in thread 🧵👇

Artificial Analysis

12,250 views • 3 months ago

Here's an introduction to SeaArt FILM. It can generate images from text, specializing in creating styles that look like movie scenes. And what if you could take those completed images and turn them into videos? #SeaArtAI SeaArt.Ai🐋

Here's an introduction to SeaArt FILM. It can generate images from text, specializing in creating styles that look like movie scenes. And what if you could take those completed images and turn them into videos? #SeaArtAI SeaArt.Ai🐋

Baxtable

15,328 views • 1 year ago

Along with automatic skeletons, another thing I worked on recently was coordinated image loading. You can wrap any group of images with an <ImageCoordinator>, and all the images under it will fade in together rather than popcorning. Makes for a much more pleasant experience! 😀

Along with automatic skeletons, another thing I worked on recently was coordinated image loading. You can wrap any group of images with an <ImageCoordinator>, and all the images under it will fade in together rather than popcorning. Makes for a much more pleasant experience! 😀

Devon Govett

122,970 views • 1 year ago

Lovable now handles images a lot better 1. Upload image to chat 2. Ask Lovable to use that image in your app

Lovable now handles images a lot better 1. Upload image to chat 2. Ask Lovable to use that image in your app

Lovable

28,984 views • 1 year ago

You can now Remix your images 🎨 Click the Remix icon below your generated image and Venice will generate a similar image with some details and characteristics "remixed"

You can now Remix your images 🎨 Click the Remix icon below your generated image and Venice will generate a similar image with some details and characteristics "remixed"

Venice

14,923 views • 9 months ago

Finally I tried Seedance 2.0. However there is limitation: It seems that they don't allow for uploading images with human faces. So it's hard for me as I usually create image of characters first. This video is created from just prompt on Seedance.

Finally I tried Seedance 2.0. However there is limitation: It seems that they don't allow for uploading images with human faces. So it's hard for me as I usually create image of characters first. This video is created from just prompt on Seedance.

Cape Obsession

12,535 views • 2 months ago

you can now generate prompts from images in Krea drag & drop any image into the prompt box -> get a prompt for it

you can now generate prompts from images in Krea drag & drop any image into the prompt box -> get a prompt for it

titus

16,807 views • 3 months ago

Yesterday someone suggested I create a fight between Alucard and Drolta Tzuentes using Kling AI 2.6. I usually work with Text to Video, but in this case I had to use Image to Video. The base image is a fusion of two images created in Niji and combined with GPT Image 1.5. Then I added the right prompt to give the fight speed and dynamism. The result isn’t perfect, but it’s pretty cool.

Yesterday someone suggested I create a fight between Alucard and Drolta Tzuentes using Kling AI 2.6. I usually work with Text to Video, but in this case I had to use Image to Video. The base image is a fusion of two images created in Niji and combined with GPT Image 1.5. Then I added the right prompt to give the fight speed and dynamism. The result isn’t perfect, but it’s pretty cool.

OscarAI

18,533 views • 6 months ago

so they definitely trained 3.7 on landing pages right? probably the best UI I've seen an LLM generate from a single prompt (no images) bonkers

so they definitely trained 3.7 on landing pages right? probably the best UI I've seen an LLM generate from a single prompt (no images) bonkers

Sully

590,041 views • 1 year ago

made an app that guesses where you are in the world with just a picture using image embeddings trained on street view data first time using swiftui, consumer apps in general, TestFlight below

made an app that guesses where you are in the world with just a picture using image embeddings trained on street view data first time using swiftui, consumer apps in general, TestFlight below

Surya

9,599,974 views • 1 year ago

I like my Laravel seeders fast. I use recycle() to dodge N+1 model creations. Another trick: when a model needs an image saved on disk, generating a unique one for each record is painfully slow. And honestly, images aren’t immediately essential. So I dispatch that work to a job. My local projects always run Horizon, so images get generated in the background while I keep coding. A local environment you can reset instantly with random data is a game-changer.

I like my Laravel seeders fast. I use recycle() to dodge N+1 model creations. Another trick: when a model needs an image saved on disk, generating a unique one for each record is painfully slow. And honestly, images aren’t immediately essential. So I dispatch that work to a job. My local projects always run Horizon, so images get generated in the background while I keep coding. A local environment you can reset instantly with random data is a game-changer.

Benjamin Crozat

10,488 views • 10 months ago

This is the most insane magical model I've ever used I just provided some AI generated images and fed it into the chat and told me to generate a game It used the image as a billboard and gave it some actions And it did this Really great

This is the most insane magical model I've ever used I just provided some AI generated images and fed it into the chat and told me to generate a game It used the image as a billboard and gave it some actions And it did this Really great

Tornado guy

36,154 views • 2 months ago

I finally built my dream interface where I can inspect the vibes of any word in our collective consciousness (using semantic embeddings)

I finally built my dream interface where I can inspect the vibes of any word in our collective consciousness (using semantic embeddings)

Defender

66,996 views • 1 year ago

colour constellations according to CLIP text embeddings—

colour constellations according to CLIP text embeddings—

Matt DesLauriers

11,940 views • 2 months ago