MFA is good! Wondering what is the plan for Sora Currently it looks like this
MULTIMODAL AI
-
ChatGPT introduces new DALL-E image style and aspect ratio controls
By
–
ICYMI: ChatGPT is A/B testing additional DALL-E controls which help enhance your prompts. It comes with a selection of different image styles which you can preview, as well as an aspect ratio control. https://t.co/oDwkUzuFsS pic.twitter.com/ODqtZpXUiZ
— 🚨 AI News | TestingCatalog (@testingcatalog) 7 mars 2024ICYMI: ChatGPT is A/B testing additional DALL-E controls which help enhance your prompts. It comes with a selection of different image styles which you can preview, as well as an aspect ratio control.
-
Observations on Sora video platform development and upcoming release
By
–
In case you are wondering: the Sora video platform is WIP Currently, its subdomain exposes 2 URLs:
– /new – /favorites Feels like we will get a totally standalone tool which is not a part of ChatGPT which we already know What will come first? Sora or GPT-5? -
Large Multimodal Datasets: Unsung Heroes Behind AI Breakthroughs
By
–
The unsung hero behind many breakthroughs (including Stable Diffusion, and GPT-4) is large multimodal datasets. Last October, Assistant Professor Ludwig Schmidt from the University of Washington introduced DataComp, an approach to enhance data quality.
-
User experience with AI voice generation tool
By
–
Generating a voice from the text takes 2 credits and it often fails with a "Face not detected" error. But I was mainly trying on cartoon characters.
-
PopAi: Create PowerPoint Presentations in Minutes Using AI
By
–
Prepare PowerPoint Presentations in minutes using AI. The time of spending hours for creating a presentation is now GONE. I am now using PopAi, which interprets images and PDFs and prepares my presentation. STEPS
-
DALL-E image editing and memory features in development
By
–
DALL-E is being touched Smthig is happening around image editing / Memory. Example, this WIP image view layout
-
DALL-E Model Updates and New Image Interface Testing
By
–
Now I have a better guess – they are updating their DALL-E model and deploying a new image view layout for testing (potentially upcoming image editing feature). Still early WIP
-
Potential New Image Editing Mode for ChatGPT
By
–
There is also a possibility that we may get a new mode for working with images directly in ChatGPT (A previously leaked Edit mode or something similar to Copilot Designer) Currently, I only can see a new page layout.
-
DALL-E now supports vertical image generation
By
–
Smith is happening with DALL-E It is the first time I see it generating vertical images