Saved by Jason Shen
Lore AI Newsletter #7: Stable Diffusion 2.0
We are excited to announce the release of Stable Diffusion Version 2!
Stable Diffusion V1 changed the nature of open source AI & spawned hundreds of other innovations all over the world. We hope V2 also provides many new possibilities!
Link → https://t.co/QOSSmSRKpG https://t.co/z0yu3FDWB5
Older models hallucinate images. GPT-4o writes them.
Old diffusion models like DALL·E 2 or Midjourney generate images by starting with random noise (a seed) and refining the whole canvas at once—much like a photo gradually developing in a darkroom. The final image “emerges” from the fog, loosely guided by the prompt.
OpenAI’s new models work
... See more