Termsslug: multimodal-generation

Multimodal Generation

多模态生成

The ability of models to process multiple data types like text and images simultaneously and generate corresponding content.

Curated Intelligence

21 items · Page 1/3
量子位官网T2·Tools
42 pts
Genspark Launches Media Studio Aggregating Multiple Models for Zero-Barrier Video Generation

Genspark has officially launched Media Studio, a video agent workbench that orchestrates LLMs and multimodal models to automate short drama production. The tool supports one-click template replication and interactive storyboarding, significantly lowering the barrier for non-professional creators. A promotional discount on member credits is currently active.

Google DeepMindT1·Models
88 pts
Google Unveils Genie 4 for Real-Time Multimodal World Simulation

Google has released Genie 4, a new world model that integrates Gemini Omni's visual anchoring and reasoning capabilities to enable unprecedented real-time interactive simulation. Natively multimodal, it simultaneously generates ambient audio, music, and dialogue, significantly enhancing physical consistency and behavioral coherence in virtual environments as a key step toward AGI.

Hugging Face BlogT1·Models
68 pts
NVIDIA Open-Sources RFD4-Proteina to Streamline Protein Design

NVIDIA released the open-source model RFD4-Proteina on Hugging Face as part of the BioNeMo series. It addresses information loss in traditional protein design by unifying multi-modal generation capabilities into a single end-to-end workflow. The model supports defining design goals and generating candidate proteins, and is integrated with the Proteinbase competition platform to accelerate experimental validation.

IT之家 · 智能时代T2·Models
68 pts
Study Shows AI-Edited Images Implant False Memories and Undermine Human Oversight

Recent research reveals that viewing AI-edited images or reading inaccurate AI summaries significantly increases the likelihood of false memories, with subjects exhibiting higher confidence in these fabricated details. The study demonstrates that even when users are warned about AI involvement, they remain susceptible to misinformation, suggesting that human oversight as a safeguard against AI errors may be fundamentally compromised.

Hacker News AIT2·Models
68 pts
Kombai Launches Design Creativity Bench: GPT-6 Astra Scores 65.5 vs Human 92.3 on UI Originality

Kombai introduces Design Creativity Bench, evaluating AI creativity in UI design across originality, creative range, and appropriateness. Results reveal a significant gap between frontier models and human designers, with the top model GPT-6 Astra scoring 65.5 against a human reference of 92.3. The benchmark's methodology and datasets are open-sourced to make design creativity a measurable dimension of model capability.

IT之家 · 智能时代T2·Models
48 pts
OpenAI GPT-6 Astra Boosts Higgsfield Video Generation to 10 Minutes with Agentic Tool Use

OpenAI announced a partnership with video platform Higgsfield, leveraging the new GPT-6 Astra model to extend AI video generation limits from 1 minute to 10 minutes. This breakthrough relies on GPT-6 Astra's 'creative agent' capabilities, which utilize external tools like 3D modeling to maintain consistency in characters, scenes, and visual details over longer durations. Additionally, Higgsfield integrated GPT-Image-2.5 for stable text rendering in images and used Codex to accelerate internal product development.