Image & Video - News Articles

Canva Releases Canva Craft, Its First Image Generation Model

Oct 22, 2026

TechCrunch

Canva releases Canva Craft, its first image generation model, built by its research team to compete with Google, OpenAI, ByteDance, and Meta. Canva says it produces images up to 2K resolution in 30 aspect ratios and legible text, trained on human-designed templates rather than photographs. It is available to all users through the Dream Lab tab.

Image & Video Business

Gemini Notebook Adds Review Toggle to Edit Slides and Videos Before Rendering

Oct 20, 2026

Google

Gemini Notebook added a Review toggle that lets users inspect and edit outline notes for Slide Decks and producer notes for Video Overviews before rendering. Product managers Viraj Doshi and Shan Wang said the co-creation flow suggests topics from a user's sources and rolls out globally to all users over the coming week.

Consumer Products Image & Video

Black Forest Labs Releases FLUX 3 Image Klein, a 5.6B Open Weights Model

Oct 16, 2026

bfl.ai

Black Forest Labs releases FLUX 3 Image Klein, a 5.6B-parameter open weights model for text-to-image generation and editing with up to 10 reference images. The company says it tops its internal evaluations against larger open models. The FLUX Kommunity License permits free commercial use below $5M annual revenue, and API pricing starts at $0.009 per 1K image.

Image & Video Open Source Foundation Models

Jon Wheatley's Pixel Path Skill Turns Any Two Places into Pixel-Art Road Fly-Throughs

Oct 14, 2026

GitHub

Jon Wheatley publishes Pixel Path, a Claude Code skill that routes a trip from OpenStreetMap data and builds a pixel-art fly-through. He says art costs $0.18 a picture at RetroDiffusion, with a moderate two-region run at $5.76. Node 18 or newer is required, and routes are driving-only from OSRM's car profile.

Coding & Developer Tools Image & Video

Noiz AI and HKUST Release Helix World, a Video and Stereo Sound World Model

Oct 13, 2026

noiz.ai

Noiz AI and HKUST release Helix World, an interactive world model that generates video and stereo sound together from a single image, steered with WASD and arrow keys. The developers report 24 frames per second at 768x512 on one NVIDIA H800 and a 79.9 WBench navigation score. A preview checkpoint is on Hugging Face.

Image & Video Audio & Voice Foundation Models

Ryan Releases Anatomy Skill That Draws Ideas as Isometric SVG Machines

Oct 12, 2026

GitHub

Ryan (@wheresryan22) releases Anatomy, an agent skill that turns technical ideas into interactive isometric SVG figures of invented machines, such as a token bucket rate limiter drawn as a pin-tumbler lock. It runs in Claude Code, OpenCode and Codex and installs with npx skills add wheresryan22/anatomy. Node 20.10 or later is required, and the 3D mode is beta.

Coding & Developer Tools Agents Image & Video

IWF Assesses 6,310 AI Child Abuse Images in 2026, 40% Above All of 2025

Oct 08, 2026

the Guardian

The Internet Watch Foundation says it has assessed 6,310 AI-generated images meeting the legal definition of child sexual abuse so far in 2026, 40% above the more than 4,500 in all of 2025. Most depict girls aged seven to 13. IWF policy head Hannah Swirsky backs binding UK legislation forcing companies to build safer models.

Misuse Regulation Image & Video

Google Launches SynthID Website to Verify AI-Generated Images, Videos, and Audio

Oct 07, 2026

TechCrunch

Google opens its SynthID website to everyone, letting users check whether images, videos, or audio were made with AI. The tool reads watermarks from Google models like Nano Banana, Veo, and Lyria, plus Gemini, Flow, ProducerAI, and Vids. OpenAI, Nvidia, and Kakao support it, and Google reports 1 million daily verification requests.

Trust Image & Video Audio & Voice

Google DeepMind Publishes Model Card for Nano Banana 2.1 Image Model

Oct 07, 2026

Google DeepMind

Google DeepMind published the model card for Nano Banana 2.1, an image generation and editing model in the Gemini 3 series, on 6 October 2026. The model, built on Gemini 3.6 Flash, accepts text and image inputs with a 1M token context window. October evaluations show its Thinking variant scoring 1050 in text-to-image preference and 1026 in general editing.

Image & Video Foundation Models

Gatewai Launches Framefields Beta for Native WebGPU Video Rendering in Node.js

Oct 06, 2026

GitHub

Gatewai launches the beta of Framefields, an Apache-2.0 Node.js package that renders code-first video directly via WebGPU, Dawn, Metal or Vulkan instead of headless Chromium, while offering on-device ONNX vision tools for segmentation, pose tracking and person mattes.

Image & Video Coding & Developer Tools Computer Vision Open Source