CLIP samples tag

Gwern Branwen

See Also
Links
Miscellaneous

[Warning: JavaScript Disabled!]

[For support of key website features (link annotation popups/popins & transclusions, collapsible sections, backlinks, tablesorting, image zooming, sidenotes etc), you must enable JavaScript.]

Links

NoaNabeshima

“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’, not ‘Granny Smith’!”

RiversHaveWings

“Here are some GLIDE demo prompts that I ran with the new 1.45B parameter latent diffusion model from CompVis: ‘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’”

advadnoun

“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.”

dribnet

“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”

genekogan

“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)”

metasemantic

“CLIP + StyleGAN + #mylittlepony A thread 🧵 starting with @ElvisPresley ‘A pony that looks like Elvis Presley’”

quasimondo

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

Miscellaneous

[Quote Of The Day] [Site Of The Day] [Annotation Of The Day]