No Images Are Needed! Allen AI’s CLOSE Learns to Complete Visual Tasks From Text Inputs Alone
MULTIMODAL AI
-
Conformal Prediction for Uncertainty in AI-Generated Images
By
–
Hyper-realistic AI-generated images are becoming increasingly commonplace.
— MIT CSAIL (@MIT_CSAIL) 29 novembre 2022
Using conformal prediction, researchers show how to construct uncertainty intervals w/meaning, i.e. a person’s hair color or the amount they’re smiling: https://t.co/GqTCP7fWnu@swamiviv1 @phillip_isola pic.twitter.com/bBKKxgFQ2zHyper-realistic AI-generated images are becoming increasingly commonplace. Using conformal prediction, researchers show how to construct uncertainty intervals w/meaning, i.e. a person’s hair color or the amount they’re smiling: http://
bit.ly/3Fbuzxq @swamiviv1 @phillip_isola -
NSFW filter removal improves image generation experience
By
–
no NSFW base means no NSFW filter detector needed. this was a major frustration, waiting for your image generations only to find out they had been blocked!
-
Fine-Tuning Vision Models with SGD Optimization
By
–
How to Fine-Tune Vision Models with SGD Kumar et al.: https://
arxiv.org/abs/2211.09359 #ArtificialIntelligence #DeepLearning #MachineLearning -
Stable Diffusion 2 Improves Safety Filter with SFW Focus
By
–
was catching up on this reading and noticed that the #NeurIPS2022 paper on “Red-Teaming the Stable Diffusion Safety Filter” is already out of date thanks to #StableDiffusion2 SD2 becoming a SFW "foundational txt2img" model means less spurious NSFW triggers! behold, dolphins!
-
Testing Stable Diffusion 2’s image generation capabilities
By
–
Testing out Stable Diffusion 2 on @playground_ai – quite impressed with the level of detail from simple prompts.
-
Guess the AI-Generated Image Prompts Interactive Game
By
–
Guess the prompt behind these AI-generated images – fun game! @le_roux_nicolas https://
flip.it/CX2Kle -
Request to Explore More Artists in Similar Style
By
–
Impressive! Can you try more such as Cassatt, OKeefe, Picasso, Picabia, Warhol, Kiefer, Guston, Simmons, El Anatsui, Refik Anadol,…? https://t.co/YPFdKR6OF1
— Ken Goldberg (@Ken_Goldberg) 27 novembre 2022Impressive! Can you try more such as Cassatt, OKeefe, Picasso, Picabia, Warhol, Kiefer, Guston, Simmons, El Anatsui, Refik Anadol,…?
-
OpenAI DALLE-2 Outpainting Fills Image Blanks
By
–
DALLE – 2 outpainting. @OpenAI fills in the blank around and between images, blending styles and mediums. pic.twitter.com/A7RtiuOfwS
— AI Breakfast (@AiBreakfast) 26 novembre 2022DALLE – 2 outpainting. @OpenAI fills in the blank around and between images, blending styles and mediums.
-
Polyhistor: Parameter-Efficient Multi-Task Dense Vision Adaptation
By
–
Polyhistor: Parameter-Efficient Multi-Task Adaptation for Dense Vision Tasks Liu et al.: https://
arxiv.org/abs/2210.03265 #ArtificialIntelligence #DeepLearning #MachineLearning