New top story on Hacker News: Show HN: Open Prompts – dataset of 10M Stable Diffusion generations
Show HN: Open Prompts – dataset of 10M Stable Diffusion generations
5 by vipermu | 1 comments on Hacker News.
Open Prompts is the dataset used to build krea.ai. The data comes from the Stability AI Discord and includes around 10M images from 2M prompts. You can use it for creating semantic search engines of prompts, training LLMs, fine-tuning image-to-text models like BLIP, or extracting insights from the data—like the most common combinations of modifiers.
September 23, 2022 at 02:03AM vipermu 5 https://ift.tt/8MZCcLN Show HN: Open Prompts – dataset of 10M Stable Diffusion generations 1 Open Prompts is the dataset used to build krea.ai. The data comes from the Stability AI Discord and includes around 10M images from 2M prompts. You can use it for creating semantic search engines of prompts, training LLMs, fine-tuning image-to-text models like BLIP, or extracting insights from the data—like the most common combinations of modifiers. https://ift.tt/WwYdUlL
5 by vipermu | 1 comments on Hacker News.
Open Prompts is the dataset used to build krea.ai. The data comes from the Stability AI Discord and includes around 10M images from 2M prompts. You can use it for creating semantic search engines of prompts, training LLMs, fine-tuning image-to-text models like BLIP, or extracting insights from the data—like the most common combinations of modifiers.
September 23, 2022 at 02:03AM vipermu 5 https://ift.tt/8MZCcLN Show HN: Open Prompts – dataset of 10M Stable Diffusion generations 1 Open Prompts is the dataset used to build krea.ai. The data comes from the Stability AI Discord and includes around 10M images from 2M prompts. You can use it for creating semantic search engines of prompts, training LLMs, fine-tuning image-to-text models like BLIP, or extracting insights from the data—like the most common combinations of modifiers. https://ift.tt/WwYdUlL
Nhận xét
Đăng nhận xét