Kontext Komposer edits your images, Kling upgrades its AI Art, and Grok 4
All the news from the AI world for creatives
New AI-powered tools are quietly reshaping how we create videos, shop, code, and how we invent characters in seconds.
1️⃣ Kontext Komposer adds editing magic to your images
2️⃣ Kling upgrades its image generation
3️⃣ Grok 4 is out
4️⃣ Quick news you may have missed
5️⃣ Prompt Fight: Monster in the Depths
6️⃣ Video AI of the Week
Let’s dive in.
Kontext Komposer adds editing magic to your images
Black Forest Labs shipped Kontext Komposer, which lets you restyle images without writing prompts by using polished presets. While some of those are cute effects for fun, there are a few with extraordinary depth:
✓ Move Camera
✓ Transform the light of your image
✓ Change product placements
✓ Create movie posters.
It works surprisingly well with complex images. Take a look:
Live now for free on the Flux Playground
Kling upgrades its image generation
Kolors 2.1 is an advanced AI-powered image generation model developed by Kuaishou, a Chinese tech company, under its Kling AI platform. It is designed to create high-quality, realistic, and stylized images from text prompts or reference images, and integrates with its AI Video tool.
Here’s what it brings to the table:
Enhanced realism and fine details
Fast compliance for quicker generation
Broader style & feature versatility
High-quality visual text integration
Grok 4 is out
Elon Musk's xAI has launched Grok 4, claiming PhD-level performance across all academic subjects, alongside the introduction of a premium $300-per-month (👀) SuperGrok Heavy subscription tier.
xAI has declared Grok 4 Heavy deploys multiple AI agents that work simultaneously on problems and compare results "like a study group" to find the best answers.
Sounds good. But those $300 are out of my reach. Would be awesome if you could share you experience with it.
Quick news you may have missed
Want to build your own Video Game World? Exists Beta is Live! This is the world-first AI world-model on Unreal Engine. You just type a prompt and get a playable world.
Freepik is offering unlimited AI video of the MiniMax 02 model by Hailuo_AI. This is live only for 7 days for Premium+ and Pro users.
Flow users can now animate input images and make them talk using Veo 3, access to which has also expanded to 140+ countries.
Perplexity has introduced Comet, its first AI-powered web browser, marking a bold challenge to Google's dominance in how people access and interact with information online.
Prompt Fight: Volumetric light rays
Let’s test the best AI Tools for art.
Photorealistic underwater scene captured in National Geographic documentary style. An upright kaiju skeleton sits motionless on the ocean floor, resembling a throne made of its own ribcage and spine. The enormous skull is angled downward, as if watching. Layers of silt coat the bones, and nothing stirs but the slow drift of dust. Divers hover at a respectful distance, dwarfed by the remains, their flashlights illuminating only fragments of the structure. No fantasy lighting, no supernatural signs just a lifeless monument of bone. Canon EOS R5, cinematic realism, ultra wide-angle lens, silent and sobering
Have a prompt you would like me to test? Send me a DM
Video of the Week
Joanna Stern of the WSJ took a deep dive into AI Film, and shared both the end result and the process in this video. Take a look.
Thanks for reading. Enjoy your Sunday, touch grass, and have a nice coffee.