“The New CLIP Adversarial Examples Are Partially from the Use-mention Distinction. CLIP Was Trained to Predict Which Caption from a List Matches an Image. It Makes Sense That a Picture of an Apple With a Large IPod’ Label Would Be Captioned With ’iPod”

“Here Are Some GLIDE Demo Prompts That I Ran With the New 1.45B Parameter Latent Diffusion Model from CompVis (https:/​/​github.com/​CompVis/​latent-diffusion):”A Hedgehog Using a Calculator” · “A Corgi Wearing a Red Bowtie and a Purple Party Hat” · “Robots Meditating in a Vipassana Retreat” · “A Fall Landscape With a Small Cottage next to a Lake” ”

“This Is Great! Now That the Model Can Be Used in PyTorch, I’ve Starting Playing With @AydaoAI’s Anime StyleGAN Directly Guided by CLIP. Starting Slow by Searching for Asuka by Name in the Latent Space.”

“Here’s a Link to My Colab If You’d like to Give It a Go Yourself. This Codebase Builds off of Previous Work from Many People including @advadnoun @RiversHaveWings @NerdyRodent as well as ClipDraw from @kvfrans @crosslabstokyo @err_more and @okw”

“Here’s What a Few Years of Progress on Text-to-image Generation Looks Like, One Prompt at a Time.”Frank Sinatra As a Purple Alien in Surrealist Style”: 1. AttnGAN (2018) · 2. CLIP+VQGAN (2020) · 3. CLIP+Diffusion (2021) · 4. DALL·E 2 (2022)”

“Here’s what a few years of progress on text-to-image generation looks like, one prompt at a time. "Frank Sinatra as a purple alien in surrealist style": 1. AttnGAN (2018) · 2. CLIP+VQGAN (2020) · 3. CLIP+Diffusion (2021) · 4. DALL·E 2 (2022)”

“CLIP + StyleGAN + #mylittlepony A Thread 🧵 Starting With @ElvisPresley ‘’A Pony That Looks like Elvis Presley’’”

“I Added #CLIP to My Image Labeling Tool and Have Now Full Text Search over My Various Collections. Here Are Potato”

“I added #CLIP to my image labeling tool and have now full text search over my various collections. Here are potato”