Sharing design sketches for an outdoor sofa company, just for inspiration of what custom image models can do. These are trained with about 50 samples of the company's furniture.
Beyond reading from Internet, it's a new dimension unlocked to have the write capability for gpt models. What happens if we couple this with RLHF?
Feels like a lightweight, open-sourced version of Adept AI.
Just gave GPT-4 access to use Chrome however it wants (click, scroll, fill forms) thru @langchain Auto-GPT agent. The results were mind-blowing!
Here's what it did: 👇
🎧Bought me an AirPod
🎉Helped me find an event venue and filled out the contact form
🍽️Booked restaurants
Trained a couple LoRA models of Duke Chapel in traditional Chinese ink painting style. The training takes about 40 minutes and 20 cents. Performant and cheap alternative to DreamBooth.
@LiamRSharp Hey Liam, sorry to hear this is happening to you. To facilitate the regulation we are working on a dedicated site to monitor and assist taking down stolen artworks as NFTs. https://t.co/w0MuNyC3eE.
I for sure hope one day we don't need service like this anymore.
@YudranArt@opensea@NFTtheft I'm sorry for this to happen. For what it's worth, https://t.co/w0MuNyC3eE is a site dedicated to protect against NFT thefts.
@NFTPhotograph@MarcoGrassi_ Look up all your works across every marketplaces in a single search: https://t.co/R0tAAysWE5, so that you have a coherent fan base!
@NFTPhotograph@cinnadine It could be a real pain to track fans across different marketplaces @cinnadine Try look up all your work in a single search on lighthouse: https://t.co/TNaBPvusPU.
@NFTPhotograph@BagerArt@BagerArt Love the arts. I saw you have works across a couple marketplaces: opensea, superrare, foundation. This likely result in segregated fan bases.
Check out all of your works in a single search: https://t.co/362X7fAMaZ.