Voilà ce que j'ai dis le 1er décembre par rapport à l' #AI et les contenus qui vont apparaitre (images, videos, textes) #midjourney #ChatGPT #GPT4
MULTIMODAL AI
-
AI NPCs Revolutionize Virtual Gaming Experiences
By
–
Revolutionizing Games: http://
Parametrix.ai Unveils the Potential of Virtual Interactive Experiences Powered by AI NPCs https://
syncedreview.com/2023/03/30/rev
olutionizing-games-parametrix-ai-unveils-the-potential-of-virtual-interactive-experiences-powered-by-ai-npcs/
… -
Virtual Holographic AI Companion Technology and Applications
By
–
Virtual holographic AI companion: https://t.co/hMpvElP8QO
— Greg Brockman (@gdb) 30 mars 2023Virtual holographic AI companion:
-
Kaggle Grand Master Compares Top Image Generation AI Tools
By
–
Today, our very own #KaggleGrandMaster @bhutanisanyam1 will be comparing current tools for #ImageGenerativeAI models. Expect detailed comparisons of these + the fine nuances of their "personality." • #Midjourneyv5 • #AdobeFirefly • #StableDiffusion https://
youtube.com/watch?v=xonFd-
bh5Qs
… -
Physics-Grounded AI Agents: Learning, Reasoning, Robotics Integration
By
–
1) learning from experience (although you already mentioned it in the dynamic memory part) 2) physics grounding: llm-agent that can observe and act in an environment, reason spatially, plan, etc 3) integration with robotics
-
AI Image Generation Boom: From DALL-E to Meme Culture
By
–
It really reminds me of the Dall-E era of AI image-generation. I suspect we're going to see a similar boom in ridiculous AI memes.
-
Genmo Chat: AI Copilot for Video Creation Using GPT-4
By
–
Genmo Chat, a copilot to create and edit videos with text using GPT-4.
— AI Breakfast (@AiBreakfast) 28 mars 2023
link: https://t.co/uL2e7PsuPx
Demo video “Snack to the Future”pic.twitter.com/Gq8qMB89CdGenmo Chat, a copilot to create and edit videos with text using GPT-4. link: http://
genmo.ai Demo video “Snack to the Future” -
GPT-4 Vision Capabilities: Multimodal Reasoning and Image Generation
By
–
I haven't even touched on the vision capabilities possible in gpt-4 some obvious ones:
-multi-modal reasoning and action (e.g. MM-REACT paper)
-better image gen (imagine gpt-4 iterates on your Midjourney prompts) -few-shot prompting and learning through images/videos -
AI Hallucination: Will Smith Eating Spaghetti Image Generation
By
–
An AI program hallucinating Will Smith eating spaghetti. Welcome to the future.
-
Aesthetic ControlNet Open-Sourced for Image Generation
By
–
we just open-sourced Aesthetic ControlNet! this model can produce highly aesthetic results from an input image and a text prompt. https://
buff.ly/3Zh6XhX