Section
Video & Image
The latest Video & Image news, analysed daily by the i10X newsroom.
FilterCompanies & models
Gallery
The latest image and video stories
Grok Imagine Odyssey Pilot Exposes AI Video Limits
Gemini Publish Feature: Reusable Styles for Images & Veo
Nano Banana 2 and 2.1: Google DeepMind AI Image Models
Nano Banana 2.1: Google’s 50% Cheaper AI Image Generation Model
Live Avatars: Real-Time AI Faces and Infrastructure Demands
GPT-Image-2.5 Sunburst on Replicate: API Image Generation
AI Image Prompts: Shift to Deterministic Rendering Engines
Grok Imagine Odyssey: xAI’s Long-Form Video Ambitions-
Grok Imagine Odyssey Pilot Exposes AI Video Limits
xAI and Wonder Studios released the first seven-minute episode of an AI-generated Odyssey using Grok Imagine. While some landscape shots show promise, the pilot struggles with character consistency, logical flow, and emotional depth, underscoring that…
By
-
Gemini Publish Feature: Reusable Styles for Images & Veo
Google is testing a Publish feature in Gemini that lets users share custom visual styles publicly. Discover how…
-
Nano Banana 2 and 2.1: Google DeepMind AI Image Models
Google DeepMind launches Nano Banana 2 and 2.1, combining Pro-level visual reasoning with Flash speeds, halved API costs,…
-
Nano Banana 2.1: Google’s 50% Cheaper AI Image Generation Model
Google’s Nano Banana 2.1 slashes AI image API costs by 50% with 4K output, mask editing, and C2PA…
-
Live Avatars: Real-Time AI Faces and Infrastructure Demands
Live Avatars move from async video to live streaming endpoints via Gemini 3.8 and 14B diffusion models. Discover…
More stories
-
GPT-Image-2.5 Sunburst on Replicate: API Image Generation
Discover how GPT-Image-2.5 Sunburst on Replicate delivers scalable API access for text-to-image generation and editing. Ideal for developers building production-grade visual AI workflows. Explore the guide.
-
AI Image Prompts: Shift to Deterministic Rendering Engines
The AI image generation landscape is fracturing between abstracted tools like DALL-E and parameter-driven platforms like Stable Diffusion. Learn why enterprises are moving beyond prompts to…
-
Grok Imagine Odyssey: xAI’s Long-Form Video Ambitions
Elon Musk announced Grok Imagine for a full-length, historically accurate Odyssey film. Explore the massive AI infrastructure and temporal consistency challenges this project presents. Learn more.
-
Generative AI for 2D-to-3D CAD: Editable Geometry, Not Meshes
Generative AI is shifting from fast 3D meshes to accurate, editable CAD programs. See why MIT research and on-premise solutions matter for manufacturers protecting IP. Learn…
-
Measuring Creativity in Diffusion Models | Google Research
Google Research introduces an empirical framework to measure novelty, surprise, and usefulness in diffusion models. Learn how CFG, score dynamics, and noise scheduling enable controllable creativity…
-
Nano Banana 2: The New AI Image Model Inside Artlist
Nano Banana 2 brings Google’s Gemini-powered image generation to Artlist. Learn how this changes creator workflows, the current limitations, and what it means for IP rights.…
-
3D AI Directing: Reallusion AI Studio with SeeDance Integration
Discover how Reallusion AI Studio and ByteDance SeeDance enable precise 3D AI directing, replacing unpredictable text prompts with spatial control for professional animation pipelines. Explore the…
-
AI-Generated Retro Photography: DIY 90s Yearbook Mastery
Learn how everyday creators are using tools like Nano Banana for hyper-personalized AI-generated retro photography that emulates classic 80s and 90s styles with consistent results and…
-
Ask YouTube: Gemini AI Makes Videos Interactive and Searchable
YouTube’s Ask YouTube uses Gemini Omni to deliver timestamped answers from video content. See how this multimodal AI transforms viewing habits and creates new challenges for…
-
OpenAI Verify: Fusing SynthID and C2PA for AI Image Provenance
OpenAI’s Verify system layers SynthID watermarks with C2PA metadata to create resilient detection for synthetic images. This provenance fusion approach tackles deepfakes and regulatory needs. Discover…
-
GPT-Image-2 Tops Image Arena: AI Image Gen Insights
GPT-Image-2 has claimed the top spot in Image Arena for text-to-image models, signaling potential shifts from OpenAI. Explore the implications for developers, stakeholders, and why details…
-
Claude Design: Anthropic’s AI for Visual Workflows
Discover Anthropic’s Claude Design, an AI-powered tool aimed at transforming team-based visual content creation for marketing and campaigns. Analyze its potential benefits, enterprise challenges like security…