Meet pjit-21k: a new pixel-space diffusion model for text-to-image generation. It skips…
This is a AI post classified by AGK Intelligence as AI image (a model release), kept by the AI Radar because it carries real work, not commentary.
Meet pjit-21k: a new pixel-space diffusion model for text-to-image generation. It skips the latent space and works directly on pixels. Small but promising for research. #AI #Diffusion
Posted by Hugging Models (73.3k followers) 41 min ago · 2 likes · 578 views · view the original post on X. Kept by the AI Radar as AI image.
More AI work like this
- Turn your profile picture or any photo to an entire fashion editorial? ✨ — @icreatelife
- Pastel pop, real down to the knit. Made with Krea 3 by @krea_ai 🩷 — @carolletta
- @flowersslop — @flowersslop
- @RobotCleopatra Here one made today in Midjourney. — @Shinebynous
- Basically this was just me playing with our new Imagen until I found something I like.… — @Dimillian
- Meet IDOL: an image to 3D model that turns flat pictures into stunning 3D gaussian… — @HuggingModels
- 试用了一下，速度不错，质量好像也还可以 — @leo114119
- GPT Image 2.6 Flare + Sunburst is live on Venice. — @AskVenice
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.3k posts from 5k X accounts over the last 14 days, 10.6k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-07 22:45 UTC. Full method.