Attending #NeurIPS2023? At 12:45pm, visit the Google booth where Xiuye Gu will describe DaTaSeg, a universal multi-dataset, multi-task segmentation model well-suited for memory-limited applications, e.g., for multiple segmentation tasks on mobile devices.
MULTIMODAL AI
-
Generate Emotion with Gen-2: Runway Academy Tutorial
By
–
Generate emotion with Gen-2.
— Runway (@runwayml) 12 décembre 2023
Learn how with today’s Runway Academy: https://t.co/2p9FX1YL8O pic.twitter.com/F7VYx5raphGenerate emotion with Gen-2. Learn how with today’s Runway Academy: https://
academy.runwayml.com/gen2/how-to-ge
nerate-emotion
… -
GPT4 tested across multiple languages
By
–
And I maintain that saying this is simply false because since GPT2, they have also tested it in other languages. + There is an entire section in the GPT4 technical report that explains how they tested it, for example, on MMLU by translating it into other languages.
-
Pika 1.0 Text-to-Video Tool Now Available for Waitlist Users
By
–
We’re beginning to let people in off the waitlist, and want to welcome our first Pika 1.0 users!
— Pika (@pika_labs) 11 décembre 2023
Here’s how to start creating with text-to-video.
Sign up at https://t.co/nqzjGy82Lx pic.twitter.com/GXVx9WhM2iWe’re beginning to let people in off the waitlist, and want to welcome our first Pika 1.0 users! Here’s how to start creating with text-to-video. Sign up at http://
pika.art -
Runway ML: Generate Video and Creative Content with AI
By
–
Generate this and that.https://t.co/ekldoIshdw pic.twitter.com/1Syf9Yd2lV
— Runway (@runwayml) 11 décembre 2023Generate this and that. http://
runwayml.com -
SeeTRUE: Google’s Text-Image Alignment Testing Tool at NeurIPS
By
–
At 12:15am today, the #NeurIPS2023 Google booth will host Yonatan Bitton for a demo of SeeTRUE, a tool for testing the alignment between text and images that can pinpoint areas of mismatch and can help adjust ranking in text-to-image generation tasks.
-
DreaMoving: AI Video Generation with Face Transfer and Pose Control
By
–
This looks interesting – like AnimateAnyone and MagicAnimate, but with prompting and face transfer.
— fofr (@fofrAI) 11 décembre 2023
DreaMoving:
reference image + pose sequence + prompthttps://t.co/Ey45v2g7JY pic.twitter.com/sqpW3sSm3hThis looks interesting – like AnimateAnyone and MagicAnimate, but with prompting and face transfer. DreaMoving:
reference image + pose sequence + prompt https://
dreamoving.github.io/dreamoving/ -
ChatGPT Screenshot to Code GPT converts website screenshots to code
By
–
ChatGPT can be a powerful coding assistant..
— God of Prompt (@godofprompt) 11 décembre 2023
That's why I've built Screenshot to Code GPT.
Upload any screenshot of a website, and it will turn it to code in seconds!
Try it here: https://t.co/0dcCMJGR41 #CustomGPTs #GPTs #GPTPlus #GPTStore #ChatGPT4 #ChatGPTPlus #OpenAI… pic.twitter.com/ayqbSvpUV9ChatGPT can be a powerful coding assistant.. That's why I've built Screenshot to Code GPT. Upload any screenshot of a website, and it will turn it to code in seconds! Try it here: https://
godofprompt.ai/gpts/screensho
t-to-code-gpt
… #CustomGPTs #GPTs #GPTPlus #GPTStore #ChatGPT4 #ChatGPTPlus #OpenAI -
New Research Initiative on General World Models Announced
By
–
Introducing General World Models.
— Runway (@runwayml) 11 décembre 2023
We believe the next major advancement in AI will come from systems that understand the visual world and its dynamics, which is why we’re starting a new long-term research effort around general world models.
Learn more: https://t.co/Z4JWm6dJjG pic.twitter.com/X8dW8fSv1YIntroducing General World Models. We believe the next major advancement in AI will come from systems that understand the visual world and its dynamics, which is why we’re starting a new long-term research effort around general world models. Learn more: http://
bit.ly/3RexmuJ -
SDXL Fine-tune Model Based on Upscaled Emoji Data
By
–
We need an SDXL fine tune based on upscaled emoji