ByteDance launched its latest image editing model, SeedEdit, on November 11, becoming the first productized universal image editing tool in China. Users can simply input a straightforward natural language instruction to change the background, transform styles, and add or remove elements in images, without the need for complex tracing and painting. SeedEdit excels at understanding commands, accurately interpreting both Chinese and English prompts, including idioms and proper nouns. For example, a user can just input 'replace the watermelon with grapes,' and SeedEdit...

ByteDance announced that its AI smart assistant Doubao PC has launched a new feature that allows users to easily edit images without the need for professional photo editing skills. Users can simply visit doubao.com, select 'Image Generation' to create an image, click 'Continue Editing', and enter simple instructions to complete the editing with one click. Additionally, users can upload images for further processing through the 'Reference Image' entry.

French AI newcomer Mistral AI recently launched a new content moderation API service, highlighting its ambition in the global AI field and demonstrating deep thought on AI safety governance. This moderation system, built on the Ministral8B model, can accurately identify nine categories of potentially harmful content, including sexual content, hate speech, violence, dangerous activities, and personal identity information. Notably, the API supports 11 major languages, including Arabic, Chinese, English, French, and more.

Generating high-quality, temporally continuous videos requires a significant amount of computational resources, especially for longer time spans. The latest Diffusion Transformer model (DiTs) has made significant progress in video generation, but its reliance on larger models and more complex attention mechanisms has resulted in slower inference speeds, exacerbating the challenge. To address this issue, researchers at Meta AI have proposed a training-free method called AdaCache to accelerate video DiTs.

Recently, reports have surfaced that Amazon is considering a new investment in artificial intelligence startup Anthropic, marking the first funding injection since the $4 billion deal struck with the company last year. According to The Information, Amazon is negotiating with Anthropic, planning to invest billions of dollars. The structure of this investment will be similar to the last one, but with a new condition: Amazon wants Anthropic to use its developed silicon chips and integrate with Amazon Web Services.

The rapid development of generative AI has raised the challenge of comprehensively evaluating its performance. A plethora of models have emerged, each showcasing increasingly impressive results. However, the pressing question remains: how do we assess the effectiveness of these text-to-image models? Traditional evaluation methods often rely on subjective visual assessments or simple metrics like CLIPScore, which frequently fail to capture the intricate details found in complex text prompts, such as relationships between objects and logical reasoning. This leads to inaccurate evaluation outcomes for many text-to-image models.

On Friday, Apple announced the acquisition of Pixelmator, a news that has garnered widespread attention. As a company that develops several popular photo editing applications, this acquisition may bring new changes to the Apple platform. While some are skeptical about the deal, there are optimists who believe it could address a major issue users encounter while using their iPads—software inadequacy, especially when trying to use Adobe's Photoshop for i.

Stability AI has once again broken through technical barriers by launching the new Stable Diffusion 3.5 Medium model. This AI art tool aimed at the general public is not only completely free for commercial use but also achieves a perfect balance between high performance and accessibility. With its multimodal diffusion transformer (MMDiT-X) architecture and a streamlined design of 2.5 billion parameters, this model cleverly addresses the hardware threshold for ordinary users, requiring only 9.9GB of VRAM to run smoothly on most consumer-grade graphics cards.