PulseAugur / Brief
EN
LIVE 09:03:51

Brief

last 24h
[3/3] 221 sources

Multi-source AI news clustered, deduplicated, and scored 0–100 across authority, cluster strength, headline signal, and time decay.

  1. TOOL · Replicate blog Română(RO) ·

    Run FLUX.2 on Replicate

    Black Forest Labs has launched FLUX.2, an advanced image generation model available on Replicate. This new model offers improved realism, detail rendering, and editing capabilities compared to its predecessor, FLUX.1. FLUX.2 comes in three variants—pro, flex, and dev—each with different generation speeds, costs, and quality levels, designed for applications ranging from creative photography to enterprise-level content generation. AI

    Run FLUX.2 on Replicate

    IMPACT Enhances realism and editing capabilities in AI image generation, offering more precise control for creative and commercial applications.

  2. SIGNIFICANT · Together AI blog English(EN) · · [2 sources]

    Expanding Together AI Model Library into multimedia generation with 40+ new image and video models

    Together AI has expanded its platform to include advanced multimedia generation capabilities, integrating over 40 new image and video models. This move aims to simplify development by offering a unified API for text, image, and video generation, eliminating the need for developers to manage multiple providers. The platform now hosts models like FLUX.2 for consistent character and product image generation, alongside video models from major players such as OpenAI, Google, and ByteDance. AI

    Expanding Together AI Model Library into multimedia generation with 40+ new image and video models

    IMPACT Consolidates generative media tools, potentially reducing friction for developers building AI-native applications.

  3. RESEARCH · arXiv cs.AI English(EN) · · [12 sources]

    EditCaption: Human-Refined SFT and HAE-DPO for Image Editing Instruction Synthesis

    Researchers have introduced new benchmarks and datasets for evaluating image editing models, addressing limitations in current systems. VINS-120K offers a large-scale dataset for ultra-high-resolution image editing, while VDE Bench focuses on modifying visual documents with dense text in multiple languages. VIBE, another benchmark, assesses models' ability to follow visual instructions, revealing that proprietary models currently outperform open-source alternatives but still struggle with complex tasks. Additionally, Together AI has launched FLUX.1 Kontext models, which enable in-context image generation and editing using both text and image prompts without requiring fine-tuning. AI

    IMPACT New benchmarks and models are pushing the boundaries of AI image editing, enabling more precise control and higher resolutions.