Comments URL: https://news.ycombinator.com/item?id=47064945

Points: 2

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=46958791

Points: 4

# Comments: 0

Unlike traditional prompt → copy → paste workflows, this lets users generate, edit, and remix images and video directly on the canvas. You can even compose visual prompts using annotations, references, or multiple images to guide generation. We designed it for real-world creative workflows, beyond simple concept generation.

- Works with any model or API - AI for image, sticker, video and audio generation - Try the live demo in your browser

You are not limited to these workflows; Our plugin system allows you to extend several parts of the UI and create tailored workflows depending on the models you want to use.

Would love feedback or to hear how others are thinking about AI-powered creative tooling. Questions and ideas welcome!

Comments URL: https://news.ycombinator.com/item?id=44668944

Points: 2

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=44056805

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=43934945

Points: 3

# Comments: 2

Instead of prompting in ChatGPT and pasting outputs into a design tool, this lets you generate, edit, and remix images all in one canvas. This allows for really interesting new workflows, like quickly mixing multiple images, or creating visual prompts by using annotations and reference on the canvas.

Some key details:

- Built with our plugin system in CE.SDK (CreativeEditor SDK) - Works with any multi modal model/API, not just OpenAI - You can bring your own API key, or extend it however you like - Focused on real-world workflows, not just concept generation

We put together a live demo and wrote a bit more on why we built it.

Would love feedback or to hear how others are thinking about AI in creative tools. If you have questions or ideas, let us know!

Comments URL: https://news.ycombinator.com/item?id=43924702

Points: 23

# Comments: 8

Imagine it's 2014 and you're deciding between two hot new framework ember and react, this is not just a question about what is hot or shiny and new.

Instead of:

"Benchmarking Multimodal RAG through a Chart-based Document Question-Answering Generation Framework

Multimodal Retrieval-Augmented Generation (MRAG) enhances reasoning capabilities by integrating external knowledge. However, existing benchmarks primarily focus on simple image-text interactions, overlooking complex visual formats like charts that are prevalent in real-world applications. In this work, we introduce a novel task, Chart-based MRAG, to address this limitation. To semi-automatically generate high-quality evaluation samples, we propose CHARt-based document question-answering GEneration (CHARGE), a framework that produces evaluation data through structured keypoint extraction, crossmodal verification, and keypoint-based generation. By combining CHARGE with expert validation, we construct Chart-MRAG Bench, a comprehensive benchmark for chart-based MRAG evaluation, featuring 4,738 question-answering pairs across 8 domains from real-world documents. Our evaluation reveals three critical limitations in current approaches: (1) unified multimodal embedding retrieval methods struggles in chart-based scenarios, (2) even with ground-truth retrieval, state-of-the-art MLLMs achieve only 58.19% Correctness and 73.87% Coverage scores, and (3) MLLMs demonstrate consistent text-over-visual modality bias during Chart-based MRAG reasoning. The CHARGE and Chart-MRAG Bench are released at https://github.com/Nomothings/CHARGE.git."

Give me: " "AI Fails Hard at Reading Charts: New Study Exposes Shocking Weaknesses!"

A groundbreaking study reveals that even the smartest AI models struggle with charts, scoring just 58% accuracy—proving your brain might still be better than AI at decoding data! "

Comments URL: https://news.ycombinator.com/item?id=43089528

Points: 3

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=42710192

Points: 2

# Comments: 0