Today, we are releasing Stable Video Diffusion, our first foundation model for generative AI video based on the image model, @StableDiffusion. As part of this research preview, the code, weights, and research paper are now available.
Additionally, today you can sign up for our waitlist to access a new upcoming web experience featuring a Text-To-Video interface.
To access the model & sign up for our waitlist, visit our website here: https://t.co/IcuPJr45S9
Everyone's favorite ChatGPT tool is the one they created themselves! ๐คฃ Here's mine, a text editor for power users of ChatGPT, inspired by the flexibility of SQL workbench. I despise constantly switching between ChatGPT and VSCode just to copy and paste text for further editing.
Lexeme is my attempt to solve workflow issues like this, along with a few other improvements. You can easily start a chat with ChatGPT by highlighting any text. Lexeme allows you to create multiple chats within the same document, keeping each chat context separate to support an iterative writing process with the help of ChatGPT.
I have been using it almost daily for the past 4-5 months and have added a couple of features to fit my specific use cases. I'm not sure how useful this will be to others, but it's there lol
demo: https://t.co/pDwW1n32Gz
code: https://t.co/lDsaPqY9E0
For those who are new to ComfyUI and want to dive right in, I've been working on a serverless version. Feel free to give it a try and share your thoughts. You can find it at https://t.co/z28nEc4HVO
Here's a demo on running AnimateDiff with LCM:
PromptSearch is essentially a quick way to sample the vector space for prompts and find a nice starting point. Give it a try and explore the vector space! https://t.co/6of0cUiTJK
You can snap a photo or upload an image to do reverse image search on #PromptSearch. Now all of this is one just one call way with our new public API! Give it a try and integrate with your own workflows. Happy prompting! https://t.co/XQnofgprSB #StableDiffusion@EMostaque