it’s all renaissance paintings tonight
AI
-
Robot Helper to Automate Snow Shoveling This Winter
By
–
Tired of shoveling snow this winter? This robot will help you out and clean the way. #CES23 #CES2023 #ces #ArtificialIntelligence #AI #tech pic.twitter.com/USnav6jgi8
— Sean Gardner (@2morrowknight) 7 janvier 2023Tired of shoveling snow this winter? This robot will help you out and clean the way. #CES23 #CES2023 #ces #ArtificialIntelligence #AI #tech
-

ChatGPT vs. Claude: Comparing AI Models with a Literary Prompt
By
–

Side-by-side comparison: @OpenAI
's ChatGPT vs. @AnthropicAI
's Claude Each model is asked to compare itself to the machine from Stanisław Lem's "The Cyberiad" (1965) that can create any object whose name begins with "n": -
Denoising Errors Transformed Into Image Generation via Diffusion
By
–
When denoising goes haywire and makes stuff up, call it diffusion and use it for image generation.
-

Claude AI Model Compared to ChatGPT for Factual Accuracy
By
–

Compared to ChatGPT, @AnthropicAI
's new model, Claude, feels somewhat less likely to make up facts, but the tendency is still there. E.g., when discussing what happened on each season of ABC's Lost, its memory is even more confused than most people's: -
AI and Art: Historical Journey to Present Day with Artificial Intelligence
By
–
Combining #AI and art: Fabio Comparelli has prepared a very nice video describing the adventure of art from the early ages to the present day with #ArtificialIntelligence.
— Sean Gardner (@2morrowknight) 7 janvier 2023
(via @arkeologbirey) #CES2023 #ces23 #iot #ML #AIart #art pic.twitter.com/XhD42bzMZNCombining #AI and art: Fabio Comparelli has prepared a very nice video describing the adventure of art from the early ages to the present day with #ArtificialIntelligence. (via @arkeologbirey
) #CES2023 #ces23 #iot #ML #AIart #art -
AUTOMATIC1111 High Resolution Fix Implementation Guide
By
–
Yes! AUTOMATIC1111 has "High res fix", need to figure out how to do this myself
-
Beyond Text: Multimodal AI’s Stunning Potential Beyond GPT
By
–
Wrong lesson from GPT paradigm — text is all you need. Other modalities will be incredibly stunning. Can feel it already from DALL-E, which can do something quite useful despite its nascent language ability.
-
Training costs for stable diffusion models scale exponentially
By
–
SD 512 cost $600k to train, SD 768 probably $1.3M and 4K would cost $10M I think to train also where do you source billions of images
-
Training Costs Stable Diffusion 512 768 4K Models Data
By
–
SD 512 cost $600k to train, SD 768 probably $1.3M and 4K would cost $10M I think to train also where do you source billions of images
