T2V Turbo V2 – a Hugging Face Space by TIGER-Lab
HART: Efficient Visual Generation with Hybrid Autoregressive Transformer
BiGR
“A German court dismissed a copyright lawsuit against LAION, a nonprofit that compiles large-scale image datasets for training models like Midjourney and Stable Diffusion. Learn more in #TheBatch:
Microsoft may have an audio-to-image generator in the works, new patent shows | ZDNET
Adobe
“Adobe Sneaks off to a fire start! Project Clean Machine: “Nothing can get in the way” of your subject — flashes recovered and occluders removed easily using AI. Project Remix A Lot: convert hand-drawn sketches to editable vector art, and resize it in a content aware fashion.
“Project Perfect Blend at Adobe Sneaks. They better ship this into Photoshop, because the audience went wild 😂 Basically PBR estimation to de-light and re-light any layer to make compositing a LOT easier. Until then, you can already do this with tools like Beeble today.
FLUX
FLUX LoRa Lab – a Hugging Face Space by multimodalart
MidJourney
Midjourney plans to let anyone on the web edit images with AI | TechCrunch
Leave a Reply