stablediffusion

Most of the latent and stable diffusion authors also work at Stability AI, as do many other generative AI research leaders in media. Naming rights on the model were no part of the compute grant, we give them incredibly freely and also support. Naming was suggested by the researchers in this case. We don't just put out compute, but made sure to clear up everything from Stable Diffusion 2 onwards 100% trained by Robin and team: https://github.com/Stability-AI/stablediffusion

Dreambooth implementation https://github.com/JoePenna/Dreambooth-Stable-Diffusion AUTOMATIC1111 https://github.com/AUTOMATIC1111/stable-diffusion-webui Stable Diffusion https://github.com/Stability-AI/StableDiffusion ?

If you're using stable diffusion 2.0 or later you can use its depth-to-image mode[0] to create variations of an image which respect its composition without having to keep your parameters within a narrow range. [0] https://github.com/Stability-AI/stablediffusion#image-modifi...

Stable diffusion is a big open source AI project. https://github.com/Stability-AI/stablediffusion

Did you miss the first part of the article? > It is our pleasure to announce the open-source release of Stable Diffusion Version 2.[0] > The original Stable Diffusion V1 led by CompVis changed the nature of open source AI models and spawned hundreds of other models and innovations all over the world. It had one of the fastest climbs to 10K Github stars of any software, rocketing through 33K stars in less than two months. [0] https://github.com/Stability-AI/stablediffusion

Read the license of the model: https://github.com/Stability-AI/stablediffusion/blob/main/LI... 5. and 7. make it not open source

Someone seeming to be emad below says the license was changed (the post got flagged for some reason): https://news.ycombinator.com/item?id=33727177 https://github.com/Stability-AI/stablediffusion/commit/ca86d...

(Edit: it may have removed that wording now: https://github.com/Stability-AI/stablediffusion/commit/ca86d... ) They can force model upgrades too: > The New AI Model Licenses Have a Legal Loophole (OpenRAIL-M of Stable Diffusion) https://www.youtube.com/watch?v=W5M-dvzpzSQ

GitHub Repo: https://github.com/Stability-AI/stablediffusion HuggingFace Space (currently overloaded unsurprisingly): https://huggingface.co/spaces/stabilityai/stable-diffusion Doing a 2.0 release on a (US) 2-day holiday weekend is an interesting move. It seems a tad more difficult to set up the model than the previous version.