DALL·E API in action 🎬
— Lilian Weng (@lilianweng) 16 novembre 2022
Ref: https://t.co/pwg5emm17f https://t.co/FSrxbd6ok2
DALL·E API in action Ref: https://
openai.com/blog/dall-e-ap
i-now-available-in-public-beta/
…
MULTIMODAL AI
-
DALL-E API Now Available in Public Beta
By
–
-
Using AI-Generated Images to Enhance Machine Translation Models
By
–
Training models on “hallucinated images”, like @OpenAI’s Dall-E, to improve machine translation pic.twitter.com/TM9hvBvixr
— IBM Data, AI & Automation (@IBMData) 16 novembre 2022Training models on “hallucinated images”, like @OpenAI
’s Dall-E, to improve machine translation -
AI Models Learn Emergent Languages Through Images
By
–
Using images to teach #AI models emergent languages, making it easier to learn non-Indo-European languages 🗣️ pic.twitter.com/aaunITPKsl
— IBM Data, AI & Automation (@IBMData) 16 novembre 2022Using images to teach #AI models emergent languages, making it easier to learn non-Indo-European languages
-
Pantheon Lab Creates Realistic AI Human with Natural Voice
By
–
The person in this video is not a real human…
— Pascal Bornet (@pascal_bornet) 16 novembre 2022
She was created by start-up Pantheon Lab. The progress made over the last 2 years is amazing: natural face, voice and lipsync using AI. This opens up opportunities in healthcare, services#innovation #artificialintelligence #tech pic.twitter.com/OzQomS1b0NThe person in this video is not a real human… She was created by start-up Pantheon Lab. The progress made over the last 2 years is amazing: natural face, voice and lipsync using AI. This opens up opportunities in healthcare, services #innovation #artificialintelligence #tech
-
Robot Dog Walks on Stools Using Onboard Vision
By
–
New work from @berkeley_ai and @CMU_Robotics on visual locomotion enables a robot dog walking on tall bar stools in @ashishkr9311's living room — entirely from onboard cameras and compute. Trained in simulation and deployed directly in the real world!https://t.co/kBEpOCsRob https://t.co/wVIeiMgfd2
— Berkeley AI Research (@berkeley_ai) 15 novembre 2022New work from @berkeley_ai and @CMU_Robotics on visual locomotion enables a robot dog walking on tall bar stools in @ashishkr9311
's living room — entirely from onboard cameras and compute. Trained in simulation and deployed directly in the real world! http://
vision-locomotion.github.io -
AI tutors offering personalized online classes with real-time video
By
–
Coming soon: online classes with one-on-one, real-time video interactions with AI tutors.
-
Breeze: Real-Time Traffic Updates via NVIDIA Riva Text-to-Speech
By
–
Find out why Breeze users love getting real-time traffic, road updates, and parking information in a local Singaporean voice developed by @NCSGroupSG with #NVIDIARiva text-to-speech. #speechAI #speechrecognition https://
nvda.ws/3Eyf4iQ -
UPainting Unifies Simple Complex Scene Image Generation
By
–
We proposed UPainting to unify simple and complex scene image generation. The model integrates cross-modal guidance into a text-conditional diffusion model. UPainting outperforms other models in caption similarity & image fidelity. More details: https://
upainting.github.io -
Contrastive Language-Audio Pretraining with Feature Fusion
By
–
Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation Wu et al.: https://
arxiv.org/abs/2211.06687 #Artificialintelligence #DeepLearning #MachineLearning -
Create Midjourney-Style Images with Open Source Stable Diffusion
By
–
Midjourney without Midjourney… @prompthero has fine-tuned Stable Diffusion so you can create images in the style of Midjourney, but with an open source model. You can run it on the web or via an API on Replicate: