My Wishlist is to see AI features integrated into GIMP 4 by default: - Image generation that will do completions based on prompts on arbitrary areas. Something like this: https://www.adobe.com/ca/products/photoshop/generative-fill.html - Meta's segment anything integrated so that there is no need to painstakenly select objects. https://segment-anything.com It would also label everything in the model, which... - Source: Hacker News / about 2 months ago

- Control the number of retrieved tiles with a slider We use OpenAI's CLIP model (https://openai.com/index/clip/) to put texts and images into the same embedding space. We do a similarity search within this space using text query or source image. We are using CLIP finetuned on pairs of satellite images and OpenStreetMap (https://www.openstreetmap.org/) tags (https://github.com/wangzhecheng/SkyScript) and... - Source: Hacker News / 8 months ago

Segment Anything 2 (SAM 2) which was released on July 29th, 2024 represents a major leap forward in segmentation technology, offering cutting-edge performance in both images and videos. Building on the foundation of the original Segment Anything, which Meta released in April 2023, SAM 2 not only enhances image segmentation but also introduces advanced video capabilities. With SAM 2, users can achieve precise... - Source: dev.to / 8 months ago

> A segment then is a collection of images that follow each other in time? A segment is a visually distinctive... Segment of image, segmentation is basically splitting an image into segments corresponding to objects: https://segment-anything.com, as such it has nothing to do with time or video. Now SAM 2 is about video, so they seem to add object tracking (that is attributing same id to the same object/segment... - Source: Hacker News / 9 months ago

Image segmentation is a crucial task in computer vision, where the goal is to extract the instance segmentation mask for a desired object within the image. I've already worked on a project, SamGIS, that focuses on this particular application of computer vision. A logical progression now would be incorporating the ability to recognize objects through text prompts. This apparently simple activity is actually... - Source: dev.to / 11 months ago

Strongly recommend using Apache Tika[1] for this. It's industry standard for ubiquitous document text extraction. You can take the text output from Tika, chunk it with something like Chonkie[2], and embed it for your search index. -[1]https://tika.apache.org/ -[2]https://chonkie.ai/. - Source: Hacker News / 24 days ago

Apache Tika could help extract the relevant bits of PDFs, couldnt it? https://tika.apache.org/. - Source: Hacker News / 11 months ago

Apache Tika has worked well for me in the past, ended up running it on an AWS Lambda https://tika.apache.org/. - Source: Hacker News / almost 2 years ago

If you accept running Java, the Apache Tika is extremely good at parsing content (https://tika.apache.org/). - Source: Hacker News / almost 2 years ago

Apache Tika can spit out text from lots of formats. I've used it with grep (or rg) to make a small scale searching of local folders. Tika does a really good job at OCR for finding if text is in a file. Source: about 2 years ago