Interface administrators, Administrators (Semantic MediaWiki), Curators (Semantic MediaWiki), Editors (Semantic MediaWiki), Suppressors, Administrators
7,785
edits
Stable Diffusion: Difference between revisions
no edit summary
PauloPacheco (talk | contribs) (Created page with "thumb|Figure 1. Stable Diffusion developer adoption. Source: A16S and GitHub. Stable Diffusion is a text-to-image latent diffusion model developed by Stability AI, allowing users to generate art in seconds based on their natural language inputs, known as prompts. <ref name="”1”"> Stability AI. Stable Diffusion launch announcement. Stability AI. https://stability.ai/blog/stable-diffusion-a...") |
No edit summary |
||
| Line 1: | Line 1: | ||
[[File:1. Stable Diffusion developer adoption.png|thumb|Figure 1. Stable Diffusion developer adoption. Source: A16S and GitHub.]] | [[File:1. Stable Diffusion developer adoption.png|thumb|Figure 1. Stable Diffusion developer adoption. Source: A16S and GitHub.]] | ||
[[Stable Diffusion]] is a [[text-to-image]] [[latent diffusion model]] developed by [[Stability AI]], allowing users to [[AI art|generate art]] in seconds based on their natural language inputs, known as [[prompt]]s. <ref name="”1”"> Stability AI. Stable Diffusion launch announcement. Stability AI. https://stability.ai/blog/stable-diffusion-announcement</ref> <ref name="”2”"> Stable Diffusion GitHub. Stable Diffusion. GitHub. https://github.com/CompVis/stable-diffusion#stable-diffusion-v1</ref> This model, released to the public with an open-source license, can also perform tasks like inpainting, outpainting, and image translation. <ref name="”3”"> Raj, G (2022). What is Stable Diffusion? A complete guide on how to run, copyright, use cases. Decentralized Creator. https://decentralizedcreator.com/what-is-stable-diffusion-a-complete-guide-on-how-to-run-copyright-use-cases/</ref> <ref name="”4”"> Borji, A (2022). Generated faces in the wild: Quantitative comparison of Stable Diffusion, Midjourneyu and DALL-E 2. arXiv:2210.00586v1</ref> Furthermore, it can run on consumer GPUs. <ref name="”5”"> Hachman, M (2022). The new killer app: Creating AI art will absolutely crush your PC. PC World. https://www.pcworld.com/article/916785/creating-ai-art-local-pc-stable-diffusion.html</ref> | |||
Stable Diffusion is a [[text-to-image]] [[latent diffusion model]] developed by [[Stability AI]], allowing users to [[AI art|generate art]] in seconds based on their natural language inputs, known as [[prompt]]s. <ref name="”1”"> Stability AI. Stable Diffusion launch announcement. Stability AI. https://stability.ai/blog/stable-diffusion-announcement</ref> <ref name="”2”"> Stable Diffusion GitHub. Stable Diffusion. GitHub. https://github.com/CompVis/stable-diffusion#stable-diffusion-v1</ref> This model, released to the public with an open-source license, can also perform tasks like inpainting, outpainting, and image translation. <ref name="”3”"> Raj, G (2022). What is Stable Diffusion? A complete guide on how to run, copyright, use cases. Decentralized Creator. https://decentralizedcreator.com/what-is-stable-diffusion-a-complete-guide-on-how-to-run-copyright-use-cases/</ref> <ref name="”4”"> Borji, A (2022). Generated faces in the wild: Quantitative comparison of Stable Diffusion, Midjourneyu and DALL-E 2. arXiv:2210.00586v1</ref> Furthermore, it can run on consumer GPUs. <ref name="”5”"> Hachman, M (2022). The new killer app: Creating AI art will absolutely crush your PC. PC World. https://www.pcworld.com/article/916785/creating-ai-art-local-pc-stable-diffusion.html</ref> | |||
Stable Diffusion is available in different formats: a public demo on [[HuggingFace]], slower and often breaks, a software beta named [[DreamStudio]], which is easier to use, faster but the user is charged after a certain number of [[image generation]]s, and a full-fat version of the model that everyone can download for unlimited art generation. <ref name="”5”"></ref> <ref name="”6”"> Vincent, J (2022). Anyone can use this [[AI art generator]] — that’s the risk. The Verge. https://www.theverge.com/2022/9/15/23340673/ai-image-generation-stable-diffusion-explained-ethics-copyright-data</ref> Third-party developers have contributed to make the software easier to download and use, such as in case of the version for macOS with a simple one-click installer. <ref name="”6”"></ref> | Stable Diffusion is available in different formats: a public demo on [[HuggingFace]], slower and often breaks, a software beta named [[DreamStudio]], which is easier to use, faster but the user is charged after a certain number of [[image generation]]s, and a full-fat version of the model that everyone can download for unlimited art generation. <ref name="”5”"></ref> <ref name="”6”"> Vincent, J (2022). Anyone can use this [[AI art generator]] — that’s the risk. The Verge. https://www.theverge.com/2022/9/15/23340673/ai-image-generation-stable-diffusion-explained-ethics-copyright-data</ref> Third-party developers have contributed to make the software easier to download and use, such as in case of the version for macOS with a simple one-click installer. <ref name="”6”"></ref> | ||