Jump to content

Stable Diffusion

From Wikipedia, the free encyclopedia

This is an old revision of this page, as edited by PHaze (talk | contribs) at 04:56, 7 September 2022 (fixed broken reference URL). The present address (URL) is a permanent link to this revision, which may differ significantly from the current revision.

Stable Diffusion
Original author(s)Patrick Esser, Robin Rombach, et al.
Developer(s)StabilityAI
Initial releaseAugust 22, 2022
Stable release
1.4 (model) / August 22, 2022
Repositorygithub.com/CompVis/stable-diffusion
Written inPython
Operating systemAny that support CUDA kernels
TypeTransformer language model
LicenseCreative ML OpenRAIL-M
Websitegithub.com/CompVis/stable-diffusion
Part of a series on
Artificial intelligence
Major goals
Approaches
Applications
Philosophy
History
Glossary

Stable Diffusion is a machine learning model developed by StabilityAI, in collaboration with EleutherAI and LAION[1], to generate digital images from natural language descriptions. The model can be used for other tasks too, like generating image-to-image translations guided by a text prompt.[2]

It can run on most consumer hardware equipped with a modest GPU and was hailed by PC World as "the next killer app for your PC".[3]

License

Unlike competing models like DALL-E, Stable Diffusion is open source.[4] Its license prohibits certain harmful use cases.[5][6] Critics have raised concerns about AI ethics, stating that the model can be used to create deepfakes[7] and also questioning the legality of generating images with a model trained on a dataset containing copyrighted content without the consent of the original artists.[8]

Training

Stable Diffusion was trained on a subset of the LAION-Aesthetics V2 dataset.[9] It was built on 256 A100s at a cost of $600k.[10]

See also

References

  1. ^ "Stable Diffusion Launch Announcement". Stability.Ai. Retrieved 2022-09-06.
  2. ^ "Diffuse The Rest - a Hugging Face Space by huggingface". huggingface.co. Retrieved 2022-09-05.
  3. ^ "The new killer app: Creating AI art will absolutely crush your PC". PCWorld. Retrieved 2022-08-31.
  4. ^ "Stable Diffusion Public Release". Stability.Ai. Retrieved 2022-08-31.
  5. ^ "Ready or not, mass video deepfakes are coming". The Washington Post. Retrieved 2022-08-31.
  6. ^ "License - a Hugging Face Space by CompVis". huggingface.co. Retrieved 2022-09-05.
  7. ^ "Deepfakes for all: Uncensored AI art model prompts ethics questions". TechCrunch. Retrieved 2022-08-31.
  8. ^ "AI Creating 'Art' Is An Ethical And Copyright Nightmare". Kotaku. Retrieved 2022-09-02.
  9. ^ "LAION-Aesthetics | LAION". laion.ai. Retrieved 2022-09-02.
  10. ^ Mostaque, Emad (August 28, 2022). "Cost of construction". Twitter. Retrieved 2022-09-06.
Wikimedia Commons has media related to Stable Diffusion.
Retrieved from "https://en.wikipedia.org/w/index.php?title=Stable_Diffusion&oldid=1108956050"