Difference between revisions of "Stability AI"
m (→Stable Diffusion) |
m |
||
| Line 31: | Line 31: | ||
<img src="https://scholar.harvard.edu/sites/scholar.harvard.edu/files/styles/os_files_large/public/binxuw/files/diffusion_proc1.gif" width="400"> | <img src="https://scholar.harvard.edu/sites/scholar.harvard.edu/files/styles/os_files_large/public/binxuw/files/diffusion_proc1.gif" width="400"> | ||
| + | |||
| + | |||
| + | <youtube>f6PtJKdey8E</youtube> | ||
| + | <youtube>_7rMfsA24Ls</youtube> | ||
= DeepFloyd = | = DeepFloyd = | ||
| Line 37: | Line 41: | ||
Text-to-image generative AI model called DeepFloyd IF | Text-to-image generative AI model called DeepFloyd IF | ||
| + | |||
| + | <youtube>6ktXlBDf4hQ</youtube> | ||
| + | <youtube>g1G6JC-xFso</youtube> | ||
= Clipdrop = | = Clipdrop = | ||
Revision as of 03:49, 4 May 2023
YouTube ... Quora ...Google search ...Google News ...Bing News
- Stability AI
- Capabilities
- Video/Image ... Vision ... Colorize ... Image/Video Transfer Learning
- Generative AI ... Conversational AI ... OpenAI's ChatGPT ... Perplexity ... Microsoft's Bing ... You ...Google's Bard ... Baidu's Ernie
Stability AI is the world’s leading open source generative AI company1. Their goal is to maximize the accessibility of modern AI to inspire global creativity and innovation. They have developed cutting-edge AI models applied to imaging, language, code, audio, video, 3D content, design, biotech and other scientific research. They are also behind Stable Diffusion, a pioneering text-to-image model that powers many popular applications
Stable Diffusion
Stable Diffusion is a latent text-to-image diffusion model capable of generating photo-realistic images given any text input, cultivates autonomous freedom to produce incredible imagery, empowers billions of people to create stunning art within seconds.
DeepFloyd
DeepFloyd IF relies on the T5-XXL-1.1 model. The more flexible foundation model gives DeepFloyd IF more features and often performs better than the standard version of Stability’s more famous model. For instance, it can generate legible text in various forms and fonts and produces more photorealistic images than many of the current text-to-image engines. The images can also be customized in the text prompt to match non-standard aspect ratios instead of always starting as a square. DeepFloyd IF is also designed for image-to-image manipulation as seen at the top of the page. The model resizes the initial image, then deliberately adds noise before processing the new prompt to alter the style and complete the modification without repeated fine-tuning and tinkering. “DeepFloyd IF is a state-of-the-art text-to-image model released on a non-commercial, research-permissible license that provides an opportunity for research labs to examine and experiment with advanced text-to-image generation approaches,” Stability AI explained in its announcement. “Incorporating the intelligence of the T5 model, DeepFloyd IF generates coherent and clear text alongside objects of different properties appearing in various spatial relations. Until now, these use cases have been challenging for most text-to-image models.” Stability AI Debuts New Text-to-Image Model DeepFloyd IF | Eric Hal Schwartz - Voicebot.ai
Text-to-image generative AI model called DeepFloyd IF
Clipdrop
- Clipdrop
- Stability AI Acquires Image Editing App Clipdrop Developer Init ML | Eric Hal Schwartz - Voicebot.ai
Generative AI image creation and editing service which provides advanced image manipulation tools on Windows and Mac computers, iOS and Android mobile apps, and as an Adobe Photoshop plug-in. Users can clean up a photo by removing extraneous objects and text or just isolate and export the subject of the image. The AI can also adjust lighting or “enhance” a blown-up section of the image like so many TV shows have imagined. Clipdrop rounds out its toolkit with a Stable Diffusion-based text-to-image generator for wholesale AI visual production, at least for the beta version of its app.
