Back ستيبل ديفيوجن Arabic Stable Diffusion Azerbaijani Stable Diffusion Bulgarian Stable Diffusion Catalan Stable Diffusion Czech Stable Diffusion German Stable Diffusion Spanish استیبل دیفیوژن Persian Stable Diffusion Finnish Stable Diffusion French

Stable Diffusion

Stable Diffusion
Original author(s)Runway, CompVis, and Stability AI
Developer(s)Stability AI
Initial releaseAugust 22, 2022
Stable release
SD 3.5 (model)[1] / October 22, 2024
Repository
Written inPython[2]
TypeText-to-image model
LicenseStability AI Community License
Websitestability.ai/stable-image Edit this on Wikidata

Stable Diffusion is a deep learning, text-to-image model released in 2022 based on diffusion techniques. The generative artificial intelligence technology is the premier product of Stability AI and is considered to be a part of the ongoing artificial intelligence boom.

It is primarily used to generate detailed images conditioned on text descriptions, though it can also be applied to other tasks such as inpainting, outpainting, and generating image-to-image translations guided by a text prompt.[3] Its development involved researchers from the CompVis Group at Ludwig Maximilian University of Munich and Runway with a computational donation from Stability and training data from non-profit organizations.[4][5][6][7]

Stable Diffusion is a latent diffusion model, a kind of deep generative artificial neural network. Its code and model weights have been released publicly,[8] and it can run on most consumer hardware equipped with a modest GPU with at least 4 GB VRAM. This marked a departure from previous proprietary text-to-image models such as DALL-E and Midjourney which were accessible only via cloud services.[9][10]

  1. ^ "Stable Diffusion 3.5". Stability AI. Archived from the original on October 23, 2024. Retrieved October 23, 2024.
  2. ^ Ryan O'Connor (August 23, 2022). "How to Run Stable Diffusion Locally to Generate Images". Archived from the original on October 13, 2023. Retrieved May 4, 2023.
  3. ^ "Diffuse The Rest - a Hugging Face Space by huggingface". huggingface.co. Archived from the original on September 5, 2022. Retrieved September 5, 2022.
  4. ^ "Leaked deck raises questions over Stability AI's Series A pitch to investors". sifted.eu. Archived from the original on June 29, 2023. Retrieved June 20, 2023.
  5. ^ "Revolutionizing image generation by AI: Turning text into images". www.lmu.de. Archived from the original on September 17, 2022. Retrieved June 21, 2023.
  6. ^ Mostaque, Emad (November 2, 2022). "Stable Diffusion came from the Machine Vision & Learning research group (CompVis) @LMU_Muenchen". Twitter. Archived from the original on July 20, 2023. Retrieved June 22, 2023.
  7. ^ Cite error: The named reference stable-diffusion-launch was invoked but never defined (see the help page).
  8. ^ Cite error: The named reference stable-diffusion-github was invoked but never defined (see the help page).
  9. ^ "The new killer app: Creating AI art will absolutely crush your PC". PCWorld. Archived from the original on August 31, 2022. Retrieved August 31, 2022.
  10. ^ Cite error: The named reference verge was invoked but never defined (see the help page).

Developed by StudentB